UIST 2025
| title | author | length |
|---|---|---|
| Wrist2Finger: Sensing Fingertip Force for Force-Aware Hand Interaction with a Ring-Watch Wearable | Yingjing Xiao, ZhiChao Huang, Junbin Ren, Yuting Bai, Haichuan Song, Zhanpeng Jin, Yang Gao | 11m |
A wearable system combines a ring with 9-axis IMU and a watch with single-channel EMG plus a dual-branch transformer with cross-attention to jointly predict 3D… | ||
| POET: Supporting Prompting Creativity and Personalization with Automated Expansion of Text-to-Ima... | Evans Xu Han, Alice Qian, Haiyi Zhu, Hong Shen, Paul Pu Liang, Jane Hsieh | 12m |
POET is a real-time tool that uses prompt inversion (soft prompt tuning + CLIP similarity) to extract homogeneous prompt embeddings, an LLM to categorize and… | ||
| Touch-n-Curl: Designing and Constructing Skeletal Form through 3D Printing Flattened Zipper Assembly | Deying Pan, Fanqi Zhou, Yitao Fan, Tianshu Dong, Fanke Qi, Yongbo Ni, Ye Tao, Lingyun Sun, Guanyun Wang | 08m |
Touch-n-Curl converts a 3D skeleton into a pack of 3D-printed flattened zipper ribbons that unroll from conical, developable patches; a computational pipeline… | ||
| Using an Array of Needles to Create Solid Knitted Shapes | François Guimbretière, Victor F Guimbretiere, Amritansh Kwatra, Scott E. Hudson | 13m |
A small 6x6 needle machine prototype physically fabricates traditional knits, horizontal knits across the needle plane, and true solid knits with overhangs and… | ||
| Squiggle: Multimodal Lasso Selection in the Real World | Jacqui Fashimpaur, Tovi Grossman, Ben Lafreniere, Naveen Sendhilnathan, Kashyap Todi, Tianyi Wang, Ting Zhang, Tanya R. Jonker | 14m |
Squiggle lets users sweep an invisible lasso with a pinch ring and smart glasses gaze to produce image masks (Project Ares hardware; VR data collected on Meta… | ||
| VR Side-Effects: Memory & Proprioceptive Discrepancies After Leaving Virtual Reality | Antonin Cheymol, Pedro Lopes | 12m |
Two lab studies measure concrete lingering effects after exiting VR: one shows hand retargeting causes residual proprioceptive offsets of up to 7 cm that take… | ||
| CoSight: Exploring Viewer Contributions to Online Video Accessibility Through Descriptive Commenting | Ruolin Wang, Xingyu Bruce Liu, Biao Wang, Wayne Zhang, Ziqian Liao, Ziwen Li, Amy Pavel, Xiang 'Anthony' Chen | 12m |
CoSight is a Chrome extension that adds visual indicators of accessibility gaps, pop-up hints for what to describe, real-time reminders to replace vague… | ||
| Rethinking Dataset Discovery with DataScout | Rachel Lin, Bhavya Chopra, Wenjing Lin, Shreya Shankar, Madelon Hulsebos, Aditya Parameswaran | 11m |
DataScout uses LLMs plus embedding collections and search indices to map a user goal to actual datasets, precomputing descriptions and three embedding levels… | ||
| Talking Spell: A Wearable System Enabling Real-Time Anthropomorphic Voice Interaction with Everyd... | Xuetong WANG, Ching Christie PANG, Pan Hui | 14m |
A wearable system called Talking Spell turns any object into a talking persona by combining an eye‑level camera (OV2640 on an ESP32‑S3 scope) and a wand… | ||
| TalkLess: Blending Extractive and Abstractive Speech Summarization for Editing Speech to Preserve... | Karim Benharrak, Puyuan Peng, Amy Pavel | 12m |
TalkLess combines extractive cuts and LLM-driven abstraction to shorten speech while keeping voice style, generating 25 candidates per segment and scoring them… | ||
| Designing Looms as Kits for Collaborative Assembly | Samantha Speer, Nickolina Yankova, Joey Huang, Carolyn Rosé, Kylie A Peppler, James McCann, Melisa Orta Martinez | 11m |
A study compares two loom kits — Ashford Loom for single users and RoboLoom (40 motor assemblies) designed for group work — by video coding eight participants… | ||
| Steering Semantic Data Processing With DocWrangler | Shreya Shankar, Bhavya Chopra, Mawil Hasan, Stephen Lee, Bjoern Hartmann, Joseph M. Hellerstein, Aditya Parameswaran, eugene Wu | 10m |
DocWrangler is an IDE that layers on DocETL to turn LLM calls into repeatable map/reduce-style pipelines, letting users inspect outputs, annotate them, and… | ||
| Branch Explorer: Leveraging Branching Narratives to Support Interactive 360° Video Viewing for Bl... | Shuchang Xu, Xiaofu Jin, Wenshuo ZHANG, Huamin Qu, Yukang Yan | 11m |
Branch Explorer converts 360° videos into branching narratives using an offline multi-modal ML pipeline with three modules: branch diversity optimization… | ||
| EmoShortcuts: Emotionally Expressive Body Augmentation for Social Mixed Reality Avatars | HyunA Seo, Youngki Lee, Rajesh Balan, Thivya Kandappu | 14m |
A system called EmoShortcuts automatically maps detected emotion types to prerecorded, motion-captured body animations and lets users pre-tune per-emotion… | ||
| InSituTale: Enhancing Augmented Data Storytelling with Physical Objects | Kentaro Takahira, Yue Yu, Takanori Fujiwara, Ryo Suzuki, Huamin Qu | 12m |
Prototype InSituTale enables presenters to manipulate visualizations by physically moving objects, claiming real-time augmented data storytelling with tangible… | ||
| Synthia: Visually Interpreting and Synthesizing Feedback for Writing Revision | Chao Zhang, Kexin Phyllis Ju, Zhuolun Han, Grace Yu-Chun Yen, Jeffrey M Rzeszotarski | 12m |
Synthia breaks dozens of free‑text critiques into interactive feedback bubbles that cluster, color, and resize by issue or actionability, links each unit to… | ||
| VRSight: An AI-Driven Scene Description System to Improve Virtual Reality Accessibility for Blind... | Daniel Killough, Justin Feng, Zheng Xue Ching, Daniel Wang, Rithvik Dyava, Yapeng Tian, Yuhang Zhao | 13m |
An end-to-end, post-hoc system recognizes VR scenes with object detection, depth estimation, OCR, edge-based pointer detection and LLM-driven tone selection… | ||
| Delusionized? Potential Harms of Proprioceptive Manipulations through Hand Redirection in Virtual... | Martin Feick, Kora Persephone Regitz, André Zenner | 14m |
A controlled experiment with 22 participants measures effects of unnoticeable hand redirection in VR using the joint position reproduction (JPR) method: after… | ||
| AbstractExplorer: Leveraging Structure-Mapping Theory to Enhance Comparative Close Reading at Scale | Ziwei Gu, Joyce Zhou, Ning-Er (Nina) Lei, Jonathan K. Kummerfeld, Mahmood Jasim, Narges Mahyar, Elena L. Glassman | 13m |
AbstractExplorer claims to let users form a corpus-level mental model of 1,000+ conference abstracts while preserving sentence detail by splitting abstracts… | ||
| NFCGest: Gesture Interaction with NFC terminal Enabled by Super High Speed ADC | Bu Li, Robert Xiao | 13m |
Custom streaming ADC on an STM32 microcontroller reads I/Q RX analog outputs from a PN532 NFC terminal at ~848 kHz, streams amplitude–phase trajectories, and… | ||
| StoryEnsemble: Enabling Dynamic Exploration & Iteration in the Design Process with AI and Forward... | Sangho Suh, Michael Lai, Kevin Pu, Steven P. Dow, Tovi Grossman | 11m |
Tool called StoryEnsemble builds a node-link interface that wires AI generators to personas, problem statements, solutions and storyboards and implements… | ||
| Semantic Commit: Helping Users Update Intent Specifications for AI Memory at Scale | Priyan Vaithilingam, Munyeong Kim, Frida-Cecilia Acosta-Parenteau, Daniel Lee, Amine Mhedhbi, Elena L. Glassman, Ian Arawjo | 14m |
SemanticCommit is a mixed-initiative interface that detects semantic conflicts when users add new intent to natural-language intent specifications and lets… | ||
| HydroHaptics: High-Fidelity Force-Feedback on Soft Deformable Interfaces using Hydrostatic Transm... | James David Nash, Kim Sauvé, Catharina Maria van Riet, Anke van Oosterhout, Adwait Sharma, Christopher Clarke, Jason Alexander | 12m |
HydroHaptics uses hydrostatic transmission (water-filled hydraulic cells and tubing) driven by a brushless DC motor and lead screw to deliver bidirectional… | ||
| StreetViewAI: Making Street View Accessible Using Context-Aware Multimodal AI | Jon E. Froehlich, Alexander J. Fiannaca, Nimer M Jaber, Victor Tsaran, Shaun K. Kane | 15m |
StreetViewAI is a working accessible Street View prototype that combines GIS data, image analysis and multimodal Gemini models (Gemini Flash for structured… | ||
| Do You See What I See? Bring Live Pedestrians into an Outdoor Collaborative Mixed Reality Experience | Jingyi Zhang, Ziwen Lu, Changrui Zhu, Simon Julier, Anthony Steed | 12m |
System streams live pedestrian positions from a laptop camera through a server into a virtual replica built with Bentley iTwin Capture and rendered on a Meta… | ||
| VisMimic: Integrating Motion Chain in Feedback Video Generation for Motor Coaching | Liqi Cheng, Xiao Xie, Yiwei Peng, Minghao Feng, Yuchen He, Anqi Cao, Yihong Wu, Hui Zhang, Yingcai Wu | 13m |
VisMimic builds an authoring pipeline that automatically extracts key poses by detecting extrema in joint trajectories, converts motions into a motion chain… | ||
| ChairPose: Pressure-based Chair Morphology Grounded Sitting Pose Estimation through Simulation-As... | Lala Shakti Swarup Ray, Vitor Fortes Rey, Bo Zhou, Paul Lukowicz, Sungho Suh | 12m |
A system estimates full-body seated pose from a thin chair-agnostic pressure mattress plus a single 3D chair scan, using a two-stage generative model with a… | ||
| MagTex: Machine-Knitted Magnetoactive Textiles for Bidirectional Human-Machine Interface | Sen Zhang, Yuxuan Miao, Jazlin Taylor, Yiyue Luo | 13m |
MagTex combines soft magnetized silicone fibers and copper wire coils knitted on a digital machine to make a single-layer wearable that both senses motion and… | ||
| Repurposing Audio Playback Tools to Test Human Localization with 6DoF Sound | Dan Rehberg, Adam Sinclair Williams, Anil Ufuk Batmaz, Francisco Raul Ortega | 13m |
A practical method records directional human speech with a first-order spherical microphone array, builds a triangulated octahedron mesh for spherical-weighted… | ||
| SlideAudit: A Dataset and Taxonomy for Automated Evaluation of Presentation Slides | Zhuohao (Jerry) Zhang, Ruiqi Chen, Mingyuan Zhong, Jacob O. Wobbrock | 12m |
Dataset of 2,400 slides and a 27 flaw types taxonomy across five categories, created with designers and annotated via trained Prolific workers (three… | ||
| StringTouch: A Non-occlusive 3DoF Haptic Interface Using String Structures for Modulating Finger ... | YoungIn Kim, Jisu Yim, Yohan Yun, Donghyeon Ko, Geehyuk Lee | 13m |
StringTouch is a wearable fingertip frame that uses 0.2mm nylon threads pulled by three servo motors via Bowden cables to produce 3DoF skin deformations… | ||
| Meridian: A Design Framework for Malleable Overview-Detail Interfaces | Bryan Min, Haijun Xia | 12m |
Introduces a declarative ODI spec that encodes number of overviews/details, attribute placement, and representation types, plus a runtime that maps spec… | ||
| Viago: Exploring Visual-Audio Modality Transitions for Social Media Consumption on the Go | Ruei-Che Chang, Tovi Grossman, Carine Rognon, Michael Glueck, Christopher Collins, Amy Karlson, Hemant Bhaskar Surale, Rachel Zhang | 12m |
Viago is a background Android accessibility service that automates transitions between visual and audio modes for mobile task management while walking, built… | ||
| LuxAct: Enhance Everyday Objects for Visual Sensing with Interaction-Powered Illumination | Xiaoying Yang, Qian Lu, Jeeeun Kim, Yang Zhang | 13m |
LuxAct encodes object ID and sensor data into sequences of RGB blinks that are powered by interaction-powered piezoelectric generators (striking and plucking)… | ||
| Transforming Everyday Objects into Dynamic Interfaces using Smart Flat-Foldable Structures | Violet Yinuo Han, Amber Yinglei Chen, Mason Zadan, Jesse T Gonzalez, Dinesh K Patel, Wendy Fangwen Yu, Carmel Majidi, Alexandra Ion | 14m |
A thin, self-contained motion layer called Lemo attaches as an object's bottom surface and combines vibration motors and battery for energy with steerable… | ||
| EchoLadder: Progressive AI-Assisted Design of Immersive VR Scenes | Zhuangze Hou, Jingze Tian, Nianlong Li, Farong Ren, Can Liu | 11m |
EchoLadder is a VR authoring pipeline that breaks vague verbal prompts into executable suggestions using a large vision-language model and a JSON action layer… | ||
| EclipseTouch: Touch Segmentation on Ad Hoc Surfaces using Worn Infrared Shadow Casting | Vimal Mollyn, Nathan DeVrio, Chris Harrison | 12m |
Headset-mounted IR illuminators plus an IR camera produce structured shadows that encode finger-to-surface distance; a neural model trained on per-LED shadow… | ||
| BioLIG: Functionalizing Biocomposites with Laser-induced Graphene for Bio-Rapid Prototyping of El... | Yuqing Lucy Li, Vlasta Kubušová, Wedyan Babatain, Jean-Baptiste Labrune, Sage Widder, Bernice Y Sun, Jack Forman, Hiroshi Ishii | 10m |
A CO2 laser turns five bio-based recipes into conductive laser-induced graphene on three sheets and two paints, with the best ink matching polyimide LIG and… | ||
| Meta-antenna: Mechanically Frequency Reconfigurable Metamaterial Antennas | Marwa AlAlawi, Regina Zheng, SooYeon Ahn, Katherine Arianna Yan, Ticha Sethapakdi, Junyi Zhu, Stefanie Mueller | 13m |
A design and fabrication pipeline creates mechanically reconfigurable metamaterial antennas that shift resonance across 500 MHz to 6.3 GHz (≥10 dB) by… | ||
| Answering Developer Questions with Annotated Agent-Discovered Program Traces | Litao Yan, Jeffrey Tao, Lydia B. Chilton, Andrew Head | 12m |
Trailblazer is a system that uses an agent-guided exploration combining static analysis and IDE operations like go-to-definition and find-all-references to… | ||
| HAGI: Head-Assisted Gaze Imputation for Mobile Eye Trackers | Chuhan Jiao, Zhiming Hu, Andreas Bulling | 10m |
A diffusion-based imputation model uses time-aligned head orientation (rotation + translation) and observed gaze to reconstruct missing gaze segments, training… | ||
| Scaling Context-Aware Task Assistants that Learn from Demonstration and Adapt through Mixed-Initi... | Riku Arakawa, Prasoon Patidar, Will Page, Jill Fain Lehman, Mayank Goel | 12m |
PrISM is a multimodal assistant that trains a smartwatch-based step tracker from a single demonstration using event detection and an LLM-generated task… | ||
| Enhancing XR Audio Realism via Multimodal Scene-Aware Acoustic Rendering | Tianyu Xu, Jihan Li, Penghe Zu, Pranav Sahay, Maruchi Kim, Kwadwo Obeng-Marnu, Farley Miller, Xun Qian, Katrina Passarella-Ward, Mahitha Rachumalla, Rajeev Nongpiur, D Shin | 13m |
Samosa is an on-device hybrid pipeline that combines geometric ray-based shoebox estimation with learned acoustic priors to synthesize dynamic RIRs and… | ||
| Primed Action: Preserving Agency while Accelerating Reaction Time via Subthreshold Brain Stimulation | Yudai Tanaka, Hunter G Mathews, Pedro Lopes | 11m |
A system applies subthreshold TMS—single 300 µs pulses delivered near motor cortex timed before a cue—to raise neuronal excitability without causing… | ||
| WORM: Programming Collaborative Robots Through Manual Actions for Craft-Aligned Digital Fabrication | Sam Bourgault, Alejandro Aponte, Megumi Ondo, Emilie Yu, Jennifer Jacobs | 12m |
A system lets artists physically drive a cobot end effector like a handheld tool, record a low-level craft action (brushstroke, carving), then replay it as… | ||
| TwinSpin: A Virtual Ball in a VR Controller Enabling In-Hand 3DoF Rotation | Changsung Lim, Taejun Kim, Geehyuk Lee | 12m |
TwinSpin is a VR power‑grip controller that embeds two 6 mm mini-trackballs mounted orthogonally to simulate rolling a single virtual ball, letting fingers… | ||
| FiberCircuits: A Miniaturization Framework To Manufacture Fibers That Embed Integrated Circuits | Cedric Honnet, Wedyan Babatain, Yiyue Luo, Ozgun Kilic Afsar, Chloe Bensahel, Sarah Nicita, Yunyi Zhu, Andreea Danielescu, Neil Gershenfeld, Joseph A. Paradiso | 14m |
Framework demonstrates how to manufacture thin, flexible circuit fibers that hide full electronics: 1.4 mm-wide ARM microcontroller, 0.9 mm magnetometer, and 1… | ||
| GaussianShopVR: Facilitating Immersive 3D Authoring Using Gaussian Splatting in VR | Yulin Shen, Boyu Li, Jiayang Huang, David Yip, Zeyu Wang | 10m |
GaussianShopVR is a VR authoring system that enables point-level editing of 3D Gaussian Splatting using a controller-bound adjustable selection sphere for fast… | ||
| UltraPoser: Pushing the Limits of IMU-based Full-Body Pose Estimation with Ultrasound Sensing on ... | Yadong Li, Shuning Wang, Yongjian Fu, Justin Chen, Xingyu Chen, Ju Ren, Xinyu Zhang, Akshay Gadre, Ke Sun | 13m |
UltraPoser fuses IMU data from a smartphone smartwatch and earbud with ultrasound sensing using built-in speakers and microphones to extend coverage and remove… | ||
| Outline and Detail: A Semantic-Driven Framework for Layered 2D Character Generation | Qirui Sun, Yunyi Ni, Haixin Qiao, Jingjing Zhang, Fan Yang, Teli Yuan, Zhihao Yao, Haipeng Mi | 12m |
A pipeline called Spiritus produces layered, rigged 2D characters from mixed text and sketch inputs in minutes by semantic-matching prompts to an open mask… | ||
| Denicek: Computational Substrate for Document-Oriented End-User Programming | Tomas Petricek, Jonathan Edwards | 11m |
Denicek claims a reusable computational substrate that models programs as edit histories and exposes three concrete operations: edit application, merge +… | ||
| GyFoam: Fabricating Lattice Foam with Customizable Stiffness through Uniform Expansion | Guanyun Wang, Haotian Chen, Yufeng Wang, Songyun Li, Yue Tao, Fanke Qi, Lizhuo Cao, Xiao Jin, Ye Tao, Jiaji Li, Haoting Chen | 12m |
GyFoam combines Thermo-Expandable Microspheres, silicone, dissolvable PVA latticed molds and standard 3D printers to produce foam that shows uniform expansion… | ||
| SCENIC: A Location-based System to Foster Cognitive Development in Children During Car Rides | Liuqing Chen, Yaxuan Song, Ke Lyu, Shuhong Xiao, Yilang Shen, Lingyun Sun | 14m |
SCENIC is a location-based system for children aged 6–11 that uses an LLM fine-tuned with few-shot examples from children's storybooks to deliver six cognitive… | ||
| BandEI: A Flexible Electrical Impedance Sensing Bandage for Deep Muscles and Tendons | Hongrui Wu, Feier Long, Hongyu Mao, JaeYoung Moon, Junyi Zhu, Yiyue Luo | 12m |
BandEI is a bandage-like electrical impedance sensor that uses woven conductive fabric and laser-cut silicone layers to sense deep and small muscles and… | ||
| Accessibility Scout: Personalized Accessibility Scans of Built Environments | William Huang, Xia Su, Jon E. Froehlich, Yang Zhang | 14m |
An LLM-based system called Accessibility Scout analyzes photos to produce personalized accessibility scans by building a user model, iteratively updating via… | ||
| Spatialstrates: Cross-Reality Collaboration through Spatial Hypermedia | Marcel Borowski, Jens Emil Sloth Grønbæk, Peter W. S. Butcher, Panagiotis D. Ritsos, Clemens Nylandsted Klokmose, Niklas Elmqvist | 10m |
Spatialstrates is a WebXR-based proof-of-concept platform that composes 2D and 3D content via a projection plane for bidirectional mapping, containers for… | ||
| Personalized Bistable Orthoses for Rehabilitation of Finger Joints | Yuyu Lin, Dian Zhu, Anoushka Naidu, Kenneth Yu, Deon Harper, Eni Halilaj, Douglas Weber, Deborah Kenney, Adam J. Popchak, Mark Baratz, Alexandra Ion | 14m |
A bistable finger orthosis is built as a single-piece 3D-printed mechanism of two rigid links, compliant hinges, and an elastic band that 3D printed in one… | ||
| Reality Proxy: Fluid Interactions with Real-World Objects in MR via Abstract Representations | Xiaoan Liu, Difan Jia, Xianhao Carton Liu, Mar Gonzalez-Franco, Chen Zhu-Tian | 10m |
The system replaces direct selection of physical items with generated proxies so users pinch to spawn representations for nearby objects, then skim or brush… | ||
| EI-Lite: Electrical Impedance Sensing for Micro-gesture Recognition and Pinch Force Estimation | Junyi Zhu, Tianyu Xu, Jiayu Wang, Emily Guan, JaeYoung Moon, Stiven Morvan, D Shin, Andrea Colaço, Stefanie Mueller, Karan Ahuja, Yiyue Luo, Ishan Chatterjee | 15m |
A lightweight wrist-worn electrical impedance board with 16 electrodes and 100 Hz sampling recognizes six micro-gestures plus idle and estimates index-thumb… | ||
| Cooperative Design Optimization through Natural Language Interaction | Ryogo Niwa, Shigeo Yoshida, Yuki Koyama, Yoshitaka Ushiku | 10m |
A system combines batch Bayesian optimization with a large language model to let designers give outcome-focused natural language directives and receive a… | ||
| Typing Haptically: Towards Enabling Non-auditory Smartphone Text Entry with Haptic Feedback for B... | Jisu Yim, Donghyeon Ko, Taeho Kim, Taejun Kim, Jonggi Hong, Geehyuk Lee | 12m |
TypeHap maps letters to short, memorable vibrations delivered by two piezo actuators in an attachable USB module and a distinct tactile overlay for the middle… | ||
| BaroPoser: Real-time Human Motion Tracking from IMUs and Barometers in Everyday Devices | Libo Zhang, Xinyu Yi, Feng Xu | 11m |
BaroPoser fuses IMU and barometer readings from two everyday devices (smartwatch on the wrist, smartphone in the side pocket) to output full-body pose and… | ||
| Squidgets: Sketch-based Widget Design for Scene Manipulation | Joonho Kim, Fanny Chevalier, Karan Singh | 12m |
A system implemented as a Maya plugin interprets user strokes to select and manipulate visual outlines that map to scene parameters, claiming direct… | ||
| At a Glance to Your Fingertips: Enabling Direct Manipulation of Distant Objects Through SightWarp | Yang Liu, Thorbjørn Mikkelsen, Zehai Liu, Gengchen Tian, Diako Mardanbegi, Qiushi Zhou, Hans Gellersen, Ken Pfeuffer | 11m |
SightWarp summons a scaled near-space proxy of a looked-at object whenever users align gaze and hand, supporting two modes gaze-to-hand and hand-to-gaze that… | ||
| "This is My Fault", Really? Understanding Blind and Low-Vision People’s Perception of Hallucinati... | Yilin Tang, Yuyang Fang, Tianle Wang, Lingyun Sun, Liuqing Chen | 13m |
Analysis of 3,467 real-world VQA cases (WizWiz plus Ask Vision) uses GPT-4 answers and human coding to show 17% of cases contain hallucinations, categorized… | ||
| LightLink: Enhancing Smartwatch Sensing and Actuation Through Visible Light Communication | Antony Albert Raj Irudayaraj, Aditya Shekhar Nittala | 11m |
System uses a smartwatch's ambient light sensor as a receiver and the screen as a transmitter, locating the ALS 9.5 mm from top edge and forcing responses by… | ||
| NoteIt: A System Converting Instructional Videos to Interactable Notes Through Multimodal Video U... | Run Zhao, Zhihan Jiang, Xinchen Zhang, Chirui Chang, Handi Chen, Weipeng Deng, Luyao Jin, xiaojuan qi, Xun Qian, Edith C. H. Ngai | 11m |
NoteIt automatically converts instructional videos into editable, interactable notes using a pipeline that extracts hierarchical structure extraction (chapters… | ||
| Vestibular Stimulation Enhances Hand Redirection | Kensuke Katori, Yudai Tanaka, Yoichi Ochiai, Pedro Lopes | 11m |
Uses galvanic vestibular stimulation to induce a subtle body sway that aligns perceived center of gravity with the visually redirected virtual hand, reducing… | ||
| IMUCoCo: Enabling Flexible On-Body IMU Placement for Human Pose Estimation and Activity Recognition | Haozhe Zhou, Riku Arakawa, Yuvraj Agarwal, Mayank Goel | 13m |
Framework maps IMU time series from any skin location into a unified feature space using XYZ spatial coordinates plus a region category and feeds that into… | ||
| BIOGEM: A Fully Biodegradable Gelatin-Based McKibben Actuator with Embedded Sensing | Gaolin Ge, Haoran Lu, Yingting Gao, Qifeng Yang, Josiah Hester, Tingyu Cheng, Yiyue Luo | 10m |
BIOGEM is a fully biodegradable gelatin-based McKibben actuator with integrated resistive sensing using conductive ionic gelatin. Material recipes… | ||
| Guided Reality: Generating Visually-Enriched AR Task Guidance with LLMs and Vision Models | Ada Yi Zhao, Aditya Gunturu, Ellen Yi-Luen Do, Ryo Suzuki | 13m |
An iPad-fronted system plus a Python backend uses ChatGPT‑4o to decompose a user query into a JSON step plan, Gemini 2.5 to detect 2D bounding boxes, and… | ||
| Sculptable Mesh Structures for Large-Scale Form-Finding | Jesse T Gonzalez, Yanzhen Zhang, Dian Zhu, Alice Yu, Sapna Tayal, Nazm Furniturewala, Ziying Qi, Somin Ella Moon, Leyi Han, Alexandra Ion, Scott E. Hudson | 15m |
A room-scale sculptable mesh is built from adjustable beams that tuck excess FR4 strips under the surface and sense extension with resistive length sensors… | ||
| StabilizAR: Enabling Hands-Free Head Pointing while Mobile | Yonghwan Shin, Mingyu Han, Ian Oakley | 11m |
Introduces velocity capping and temporal scoring for head-cursor selection on HoloLens 2 with a torso IMU; velocity capping limits cursor speed when eye and… | ||
| Generative Trigger-Action Programming with Ply | Timothy J. Aveni, Hila Mor, Armando Fox, Bjoern Hartmann | 11m |
Ply uses LLMs and a vision-language model to generate composable trigger-action code by building incremental layers: a layer abstraction that decomposes… | ||
| Knoll: Creating a Knowledge Ecosystem for Large Language Models | Dora Zhao, Diyi Yang, Michael S. Bernstein | 11m |
Knoll is a browser extension that lets users create, share, and import self-contained knowledge modules clipped from the web or authored in Google Docs and… | ||
| DialogLab: Authoring, Simulating, and Testing Dynamic Human-AI Group Conversations | Erzhen Hu, Yanhe Chen, Mingyi Li, Vrushank Phadnis, Pingmei Xu, Xun Qian, Alex Olwal, David Kim, Seongkook Heo, Ruofei Du | 14m |
DialogLab is a prototyping toolkit that lets designers build multi-party human‑AI scenes with drag‑and‑drop avatars, attach content, and configure free and… | ||
| InReAcTable: LLM-powered Interactive Visual Data Story Construction from Tabular Data | Gerile Aodeng, Guozheng Li, Yunshan Feng, Qiyang Chen, Yu Zhang, Chi Harold Liu | 13m |
A framework and prototype called InReAcTable (In-RACTIVE) combines an Acting module with insight graph structural filtering and a Reasoning module with… | ||
| ProMemAssist: Exploring Timely Proactive Assistance Through Working Memory Modeling in Multi-Moda... | Kevin Pu, Ting Zhang, Naveen Sendhilnathan, Sebastian Freitag, Raj Sodhi, Tanya R. Jonker | 13m |
A smart-glasses system models a user’s working memory in real time from camera and microphone signals, encoding perception as 7-slot perception buffer items… | ||
| HandOver: Enabling Precise Selection & Manipulation of 3D Objects with Mouse and Hand Tracking | Esen K. Tütüncü, Mar Gonzalez-Franco, Eric J Gonzalez | 16m |
HandOver combines a mouse-driven depth-adaptive 3D cursor with hand tracking so lifting a hand into a ~5 cm trigger region spawns a hand replica at the cursor… | ||
| PricoEye: The Eye of Primary Colors for Fast and Convenient 3D Reconstruction of Fine-grained Pal... | Di Duan, Kaicheng Xiao, Lixing He, Wei Gao, Guoliang Xing | 12m |
An ultra‑compact add‑on under 3 mm thick and under $2 attaches to a smartphone camera, flashes PCB LEDs in time‑division or frequency‑division multiplexing to… | ||
| Imago Obscura: An Image Privacy AI Co-pilot to Enable Identification and Mitigation of Risks | Kyzyl Monteiro, Yuchen Wu, Sauvik Das | 11m |
Imago Obscura is an intent-aware copilot that takes a user’s natural-language sharing intent plus visual annotations, runs a vision model and a multimodal LLM… | ||
| RAGTrace: Understanding and Refining Retrieval-Generation Dynamics in Retrieval-Augmented Generation | Sizhe Cheng, Jiaping Li, Huanchen Wang, YUXIN MA | 11m |
RAGTrace is an interactive system that lets users trace retrievals, inspect which documents the generator actually uses, and regenerate answers after swapping… | ||
| Content-Independent Avatar Ownership Detection for Preventing Sockpuppet-Enabled Violations in th... | Jiangyu Wang, Guohao Li, Lu Zhou, li yang, Haixin Ye | 11m |
AvatarJudger identifies all avatars controlled by the same person using 3D finger-joint telemetry rather than account metadata, claiming cross-device ownership… | ||
| BloomIntent: Automating Search Evaluation with LLM-Generated Fine-Grained User Intents | Yoonseo Choi, Eunhye Kim, Hyunwoo Kim, Donghyun Park, Honggu Lee, Jinyoung Kim, Juho Kim | 11m |
BloomIntent automatically expands ambiguous queries into LLM-generated fine-grained intents grounded on taxonomies derived from Naver search logs, runs an… | ||
| StitchFlow: Enabling In-Situ Creative Explorations of Crochet Patterns With Stitch Tracking and P... | Zofia Marciniak, Punn Lertjaturaphat, Andrea Bianchi | 13m |
StitchFlow is a working system that records and reconstructs crochet activity using an IMU-embedded crochet hook and a foot switch for stitch signaling… | ||
| Streaming, Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving | Chang Xiao, Brenda Z. Yang | 11m |
Proposes cognitive-load-aware streaming that paces token output by inferred difficulty using two predictors: Flesch–Kincaid and LLM self-prediction (it embeds… | ||
| Ultra-low-power ring-based wireless tinymouse | Yifan Li, Masaaki Fukumoto, Mohamed Kari, Shigemi Ishida, Akihito Noda, Tomoyuki Yokota, Takao Someya, Yoshihiro Kawahara, Ryo Takahashi | 12m |
picoRing mouse implements semi-passive inductive telemetry: a small ring coil with distributed capacitors encodes thumb/index inputs via an MCU-driven… | ||
| FabObscura: Computational Design and Fabrication for Interactive Barrier-Grid Animations | Ticha Sethapakdi, Maxine Perroni-Scharf, Mingming Li, Jiaji Li, justin solomon, Arvind Satyanarayan, Stefanie Mueller | 13m |
A computational parameterization treats barrier masks as mathematical functions, proving any valid barrier obeys seriality, periodicity, discreteness and must… | ||
| The Potential of Cognitive Circles to Measure Mental Load | Gonzalo Gabriel Méndez, Luis Galárraga, Rodne Quijije, Miguel A. Nacenta | 12m |
Finger kinematics from tracing circles on a tablet while doing arithmetic, reading, or spatial tasks predict task difficulty: 40 participants yield 240… | ||
| GestureCoach: Rehearsing for Engaging Talks with LLM-Driven Gesture Recommendations | Ashwin Ram, Varsha Suresh, Artin Saberpour Abadian, Vera Demberg, Jürgen Steimle | 11m |
System fine-tunes LLMs with adapter modules on gesture data from 10 TED talks (about 1,000 annotated regions and 340 unique video clips) to split the task: the… | ||
| SparseEMG: Computational Design of Sparse EMG Layouts for Sensing Gestures | Anand Kumar, Antony Albert Raj Irudayaraj, Ishita Chandra, Adwait Sharma, Aditya Shekhar Nittala | 13m |
Computational tool generates sparse forearm EMG layouts from a chosen gesture set and ML parameters and predicts accuracy; evaluated across six datasets (28… | ||
| RingByte: Enhancing Text-Entry Practicality via A Singular Wearable Rotating Smart Ring | Rucheng Wu, Tao Ni, Zehua Sun, Jiande Sun, Weitao Xu | 12m |
A single wearable rotating smart ring combines a stable inner band and a rotating outer band with one low-cost IMU to enable touchless T9-style typing; a… | ||
| DropPop: Designing Drop-to-Deploy Mechanisms with Bistable Scissors Structures | Yibo Fu, Emily Guan, Jianzhe Gu, Dinesh K Patel, Justin U Soza Soto, Yichi Luo, Carmel Majidi, Josiah Hester, Lining Yao | 14m |
A deployable scissor lattice uses a single bistable hemispherical cap to store and release elastic energy, driving rapid expansion in 0.2–0.7 s deployment… | ||
| Extendlibur: Dynamic Haptic Retargeting for Length-Mismatched Proxies in Co-Located VR | Junyu Chen, Qianyuan Zou, Yingjie Chang, Seungjae Oh, Seungwoo Je | 11m |
System uses optical tracking with a server-client retargeting pipeline that shifts users’ virtual hands to align a single physical stick with mismatched… | ||
| Towards Unobtrusive Physical AI: Augmenting Everyday Objects with Intelligence and Robotic Moveme... | Violet Yinuo Han, Jesse T Gonzalez, Christina Yang, Zhiruo Wang, Scott E. Hudson, Alexandra Ion | 14m |
System augments everyday objects with onboard motion via robotic wheel platforms and a pipeline that streams camera frames to an off‑the‑shelf VLM for… | ||
| Illusory-UMH: A Systematic Comparison of Tactile Illusions and Modulation Techniques in Ultrasoni... | Zhouyang Shen, Joanna Bergström, Madhan Kumar Vasudevan, Marianna Obrist, Diego Martinez Plasencia | 13m |
Compares Ultrasonic Mid‑Air Haptics (UMH) using focused acoustic focal points with three rendering methods—cutaneous rabbit effect, funneling effect and… | ||
| EvalAssist: Insights on Task-Specific Evaluations and AI-Assisted Judgment Strategy Preferences | Zahra Ashktorab, Michael Desmond, Qian Pan, James M. Johnson, Martin Santillan Cooper, Elizabeth M. Daly, Rahul Nair, Tejaswini Pedapati, Hyo Jin Do, Werner Geyer | 09m |
EvalAssist is an open-source LLM-judge toolkit and UI that helps practitioners iteratively refine evaluation criteria across direct assessment and pairwise… | ||
| GaussianNexus: Room-Scale Real-Time AR/VR Telepresence with Gaussian Splatting | Xincheng Huang, Dieter Frehlich, Ziyi Xia, Peyman Gholami, Robert Xiao | 15m |
System builds a photo‑real, fully navigable room using Gaussian Splatting from a 3‑minute scan, sampling 300–400 images, 30 min training and per‑object Saga… | ||
| MACEDON : Supporting Programmers with Real-Time Multi-Dimensional Code Evaluation and Optimization | Xuye Liu, Yuzhe You, Xinrong Qiu, Tengfei Ma, Jian Zhao | 12m |
MACEDON provides real-time multi-dimensional evaluation of C/C++ code along five metrics—time, space, clarity, redundancy, documentation—using measurements… | ||
| EmbroChet: A Hybrid Textile Fabrication Approach for 3D Personalized Handicraft via Heat-Shrinking | Guanyun Wang, Zhiqi Wang, Fanyu Li, Qinyang Liu, Tianshu Dong, Zixiang Hong, Xinyi Li, Kuangqi 'Eddie' Zhu, Jiaji Li, Xiaoliang Zhao, Ye Tao | 15m |
Embroidery-based method embeds a chain stitch through a three-layer sandwich with POF heat-shrink film in the middle, laser-cuts flat baseboards, then heats to… | ||
| Ecolor: Synthesis of EInk Microcapsules for Fabricating DIY Displays | Wenda Zhao, Muhammad Yasir Khan, Daniele Baiocco, Zhibing Zhang, Anne Roudaut | 13m |
A reproducible, lower‑hazard method produces EInk microcapsules by adapting microencapsulation "mayonnaise" method with surface modification of titanium… | ||
| AROMA: Mixed-Initiative AI Assistance for Non-Visual Cooking by Grounding Multimodal Information ... | Zheng Ning, Leyang Li, Daniel Killough, JooYoung Seo, Patrick Carrington, Yapeng Tian, Yuhang Zhao, Franklin Mingzhe Li, Toby Jia-Jun Li | 11m |
AROMA is a working mixed-initiative system that grounds video recipes to reality by combining a wearable chest-mounted camera, non-visual user cues (touch… | ||
| Invisibility Cloak: Personalized Smartwatch-Guided Camera Obfuscation | Xue Wang, Yang Zhang | 12m |
System links smartwatch IMU signals to on-camera motion to remove a person’s pixels at the edge before streaming to cloud services, using a contrastive… | ||
| InterQuest: A Mixed-Initiative Framework for Dynamic User Interest Modeling in Conversational Search | Yu Mei, Yuanxi Wang, Shiyi Wang, Qingyang Wan, Zhuojun Li, Chun Yu, Weinan Shi, Yuanchun Shi | 13m |
An LLM-based conversational agent named InterQuest dynamically builds a non-hierarchical user model from past interactions, measures confidence via LM… | ||
| Privacy Equilibrium: Balancing Privacy Needs in Dynamic Multi-User Augmented Reality Scenarios | Shwetha Rajaram, Jiasi Chen, Michael Nebeling | 13m |
Proposes Privacy Equilibrium, a constrained-optimization framework that computes per-user AR sensing permissions to maximize UX while minimizing privacy risk… | ||
| Empowering Children to Create AI-Enabled Augmented Reality Experiences | Lei Zhang, Shuyao Zhou, Amna Liaqat, Tinney Mak, Brian Berengard, Yunbing Qian, Andrés Monroy-Hernández | 14m |
Capybara is an AR visual programming environment that lets children create and animate 3D characters using speech-to-3D generative models, record movements… | ||
| CineVision: An Interactive Pre-visualization Storyboard System for Director–Cinematographer Colla... | Zheng Wei, Hongtao Wu, lvmin Zhang, Xian Xu, Yefeng Zheng, Pan Hui, Maneesh Agrawala, Huamin Qu, Anyi Rao | 13m |
CineVision is an AI-driven pre-visualization system that links script input to real-time storyboard images, using fine-tuned Stable Diffusion on a… | ||
| FEDT: Supporting Experiment Design and Execution in HCI Fabrication Research | Valkyrie Savage, Harrison Goldstein, Nóra Püsök, Jia Yi Ren, Bhaskar Dutt, Chandrakana Nandi, Lora Oehlberg | 14m |
FEDT is an openly available tool that encodes fabrication experiments as an embedded Python DSL, letting researchers generate flowcharts, produce artifacts… | ||
| GraspR: A Computational Model of Spatial User Preferences for Adaptive Grasp UI Design | Arthur Caetano, Yunhao Luo, Adwait Sharma, Misha Sra | 12m |
Computational model that predicts pairwise preferences for single‑finger microgestures, trained on 1,520 two‑alternative forced‑choice labels from eight… | ||
| AmbigChat: Interactive Hierarchical Clarification for Ambiguous Open-Domain Question Answering | Jiaju Ma, Lei Shi, Kenneth Aleksander Robertsen, Peggy Chi | 13m |
AmbigChat constructs an automated disambiguation tree by combining an ambiguity taxonomy from 5,000 queries with web search and LLM grounding, extracting 10… | ||
| GLITTER: An AI-assisted Platform for Material-Grounded Asynchronous Discussion in Flipped Learning | Weirui Peng, Yinuo Yang, Zheng Zhang, Toby Jia-Jun Li | 12m |
GLITTER is a web platform that links readings (left pane) to movable discussion blocks (right pane) and uses LLM-based features: semantic post navigation… | ||
| GuitarPie: Using the Fretboard of an Electric Guitar for Audio-Based Pie Menu Interaction | Frank Heyen, Marius Labudda, Michael Sedlmair, Andreas Rene Fender | 13m |
GuitarPie maps menu items to locations on the electric guitar fretboard so playing a note opens an audio-based pie menu and neighboring string/fret notes… | ||
| KiriInflate: Fabricating Cross-Scale Inflatables with Large-Magnitude Contraction and Tunable Str... | Yue Yang, Chuang Chen, Yulu Chen, Ge Gao, Lei Ren, Bolan Yao, Lingyun Sun, Ye Tao, Guanyun Wang | 11m |
KiriInflate presents a one-step fabrication using an off-the-shelf laser cutter + electrostatic PE film process that simultaneously cuts and heat-welds to… | ||
| Tweeq: Parameter-Tuning GUI Widgets by/for Creative Professionals | Baku Hashimoto, Jun Kato | 15m |
Tweeq is a drop-in, open-source Vue.js widget library that replaces sliders, knobs, and color pickers with a drag-to-tweak interaction (horizontal drag for… | ||
| Efficient Visual Appearance Optimization by Learning from Prior Preferences | Zhipeng Li, Yi-Chi Liao, Christian Holz | 11m |
Meta-PO integrates preferential Bayesian optimization with meta-learning, stores prior users' surrogate models and uses similarity-weighted acquisition… | ||
| Kinethreads: Soft Full-Body Haptic Exosuit using Low-Cost Motor-Pulley Mechanisms | Vivian Shen, Chris Harrison | 11m |
Kinethreads is a soft full-body exosuit that uses off-the-shelf BLDC motors with reel attachments and string-pulley routings mounted on a MOLLE vest, producing… | ||
| Can You Move These Over There? Exploring an LLM-based VR Mover to Support Natural Multi-object Ma... | Xiangzhi Eric WANG, Zackary P. T. Sin, Ye Jia, Dan Archer, Wynonna H. Y. Fong, Qing Li, Chen Li | 11m |
A VR mover that combines spoken instructions, pointing and drawn lines with scene perception and an LLM to produce atomic API calls rather than generated code… | ||
| ImaginateAR: AI-Assisted In-Situ Authoring in Augmented Reality | Jaewook Lee, Filippo Aleotti, Diego Mazala, Guillermo Garcia-Hernando, Sara Vicente, Oliver James Johnston, Isabel Kraus-Liang, Jakub Powierza, Donghoon Shin, Jon E. Froehlich, Gabriel Brostow, Jessica Van Brummelen | 14m |
A mobile AR authoring pipeline that combines a modified OpenMask3D scene-understanding step, automatic GPT-4 labeling, Niantic VPS localization and a fast 3D… | ||
| Buoyancé: Reeling Helium-Inflated Balloons with Mobile Robots on the Ground for Mid-Air Tangible ... | Alan Pham, Yuxiao Li, Miyu Fukuoka, Ken Nakagaki | 13m |
A room-scale system reels helium-inflated balloons via ground robots to create mid-air tangible objects controllable in 3D and—by linking multiple tethers—up… | ||
| Touchscreens in Motion: Quantifying the Impact of Cognitive Load on Distracted Drivers | Xiyuan Shen, Seokhyun Hwang, Junhan Kong, Alexandre L. S. Filipowicz, Andrew Best, Jean Costa, Scott Carter, James Fogarty, Jacob O. Wobbrock | 12m |
Study uses N‑back to induce four cognitive loads, a Fitts’ ring task on a driving simulator, pupil and skin conductance, hand‑tracking and gaze to measure real… | ||
| 3D Sketching + 2D Generative AI for Car Exterior Design | Seung-Jun Lee, Jeongche Yoon, Sang-Hyun Lee, Joon Hyub Lee, Seok-Hyung Bae | 12m |
A workflow combines 3D sketching backbone with Photoshop and 2D generative AI to produce view-consistent car exteriors: four tuned 3D sketch modes (plane… | ||
| StorySage: Conversational Autobiography Writing Powered by a Multi-Agent Framework | Shayan Talaei, Meijin Li, Kanu Grover, James Kent Hippler, Diyi Yang, Amin Saberi | 14m |
A system called StorySage implements a five-agent pipeline — Interviewer, Session Scribe, Planner, Section Writer, Session Coordinator — that stores responses… | ||
| ReSpark: Leveraging Previous Data Reports as References to Generate New Reports with LLMs | Yuan Tian, Chuhan Zhang, Xiaotong Wang, Sitong Pan, Weiwei Cui, Haidong Zhang, Dazhen Deng, Yingcai Wu | 11m |
ReSpark uses LLMs to reverse-engineer hidden analysis workflows from past reports, modeling each report as a sequence of analysis segments (objective →… | ||
| EarPressure VR: Ear Canal Pressure Feedback for Enhancing Environmental Presence in Virtual Reality | Seongjun Kang, Gwangbin Kim, Bocheon Gim, Jeongju Park, Semoo Shin, SeungJun Kim | 13m |
System modulates ear canal pressure with sealed earbuds and a linear stepper motor–driven syringe to produce safe variations (±40 hPa) that deform the eardrum… | ||
| Shape n’ Swarm: Hands-on, Shape-aware Generative Authoring with Swarm UI and LLMs | Matthew Jeung, Anup Sathya, Steven Arellano, Wanli Qian, Luke Jimenez, Raymond Qian, Ken Nakagaki | 11m |
Proof-of-concept Shape n’ Swarm combines hand-arranged tabletop robots and speech to produce physical animations and interactions: a shape-aware generative… | ||
| ViviClay: Designing and Fabricating Ceramics with Animation Effects on Physical Surfaces | Guanhong Liu, Jingxin Ye, Qiaoqiao Jin, Chao Yuan, Xuechen Li, Yang Shi, Qing Chen, Nan Cao | 10m |
Embeds internal fluidic channels in 3D‑printed clay coated with thermochromic pigments, so hot water flowing through channels produces programmable, reversible… | ||
| DissolvPCB: Fully Recyclable 3D-Printed Electronics with Liquid Metal Conductors and PVA Substrates | Zeyu Yan, Su Hwan Hong, Josiah Hester, Tingyu Cheng, Huaishu Peng | 13m |
A fully recyclable PCB fabrication pipeline uses PVA substrate printed on consumer FDM printers and injected EGaIn conductors, with an open-source… | ||
| Oak Story: Improving Learner Outcomes with LLM-Mediated Interactive Narratives | Alan Y. Cheng, Carolyn Q Zou, Anthony Xie, Matthew Hsu, Felicia Yan, Felicity Huang, David Kai Zhang, Arjun Sharma, Rashon Poole, Daniel Wan Rosli, Andrea Cuadra, Roy Pea, James A. Landay | 13m |
A mobile app teaches 4th–6th graders about oak woodlands using a scene-graph narrative, AR activities, and a learning-goal-directed LLM architecture that… | ||
| Visual Story-Writing: Writing by Manipulating Visual Representations of Stories | Damien Masson, Zixin Zhao, Fanny Chevalier | 14m |
A text editor that auto-generates an entity-interaction graph, a world map of character locations, and a synchronized drag-to-edit timeline links visual… | ||
| MorphKeys: A Reconfigurable Keyboard System Using Switched NFC Tags | Koki Yamagami, Masato Goto, Junichiro Kadomoto, Hidetsugu Irie | 12m |
A working prototype implements battery-free NFC keys that become active only while pressed, a reader with relay resonators to extend range, and a molded… | ||
| Creating General User Models from Computer Use | Omar Shaikh, Shardul Sapkota, Shan Rizvi, Eric Horvitz, Joon Sung Park, Diyi Yang, Michael S. Bernstein | 15m |
A system-level architecture builds a general user model from screenshots and other unstructured interactions, converting observations into confidence-weighted… | ||
| QUILT: Supporting Modular Design of Machine-Knitting Programs | Jack Hester, Sebastian Law, Megan Hofmann | 14m |
QUILT is a tool built on Knitout and KnitScript that turns complete knit programs into reusable swatches, stores courses/wales and carriage passes, and… | ||
| Image-based Tactile Rendering Method Using Frequency Modulation under the Weber Fractions Constra... | Hong Fei, Yan Zhang, Xiaoying Sun | 14m |
An electrovibration pipeline maps image texels to frequency-modulated square wave drive signals constrained by measured Weber fractions so rendered friction… | ||
| Garden of Papers: Finding, Reading, and Organizing Research Papers in a Visual, Integrated, and F... | Donghyeok Ma, Hanbee Jang, Joon Hyub Lee, Seok-Hyung Bae | 12m |
A 2D canvas system converts simple sketches into node‑link diagrams, uses pen and multi‑touch to open PDFs, highlight sentences, leave notes, and auto‑generate… | ||
| LiDArgus: Accommodating Diverse Privacy Preferences in LiDAR Sensing Through Configurable Sub-Zoning | Borui Li, Jinda Yang, Apurva Jain, William Newberry, Xing-Dong Yang | 13m |
A prototype implements configurable LiDAR sub-zones using a Lumotive M30 and a projector, letting each zone toggle on/off, change spatial size, resolution, and… | ||
| OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language ... | Adam J Coscia, Shunan Guo, Eunyee Koh, Alex Endert | 13m |
OnGoal is a chat interface that automatically infers, merges, evaluates conversational goals from each user message, generates LLM explanations and extractive… | ||
| VisRing: A Display-Extended Smartring for Nano Visualizations | Taiting Lu, Christian Krauter, Runze Liu, Mara Schulte, Alexander Achberger, Tanja Blascheck, Michael Sedlmair, Mahanth Gowda | 13m |
A wearable ring integrates a 160×32 bendable OLED into a multilayer PCB and 3D-printed housing, packing IMU, PPG, temperature sensor, Bluetooth, and MCU into a… | ||
| Vid2Coach: Transforming How-To Videos into Task Assistants | Mina Huh, Zihui Xue, Ujjaini Das, Kumar Ashutosh, Kristen Grauman, Amy Pavel | 13m |
System converts how-to videos into a wearable camera assistant that extracts step-level demonstration details with an LLM classifier and CLIP embeddings… | ||
| Refashion: Reconfigurable Garments via Modular Design | Rebecca Lin, Michal Lukáč, Mackenzie Leake | 13m |
A modular garment system provides a compact set of square foundation, pleat, and dart modules with double-sided snap buttons as reversible connectors, a design… | ||
| UniKey: Enabling Surface-Based Typing with Commodity Smartwatches via Cross-Modal Learning | Sean Rui Xiang Tan, Mun Choon Chan, Jun Han | 13m |
UniKey uses only a commodity smartwatch—smartwatch microphone for inter-keystroke timing and an IMU-based left/right hand signal—to map tap timing and… | ||
| Mallet-Based Assembly: Enabling Load-Bearing Laser-Cut Models | Shohei Katakura, Chiao Fang, Mehdi Gouasmi, Lino Hellige, Yoan Tchorenev, David Bizer, Conrad Lempert, Martin Taraz, Muhammad Abdullah, Patrick Baudisch | 13m |
Laser-cut, load-bearing assemblies require mallet-tight joints but often break or block during hammering; the paper analyzes 400 tension-critical models… | ||
| Beyond the Page: Enriching Academic Paper Reading with Social Media Discussions | Run Huang, Anna Katherine Zhao, Zeinabsadat Saghi, Sadra Sabouri, Souti Chattopadhyay | 14m |
Researchers build SURF, an interface that pulls social-media posts by DOI/X/Google, parses PDFs, uses LLMs (prompt-tuned with DSPy) to map comments to paper… | ||
| Reality Promises: Virtual-Physical Decoupling Illusions in Mixed Reality via Invisible Mobile Robots | Mohamed Kari, Parastoo Abtahi | 13m |
A system called Reality Promises creates mixed‑reality illusions by privately directing an invisible mobile robot to pick up and place objects so visual… | ||
| Ragged Blocks: Rendering Structured Text With Style | Sam Cohen, Ravi Chugh | 12m |
A layout algorithm builds ragged blocks (aka rocks) as rectilinear polygons that let nested syntax display borders and padding while preserving original line… | ||
| Understood: Real-Time Communication Support for Adults with ADHD Using Mixed Reality | Shizhen Zhang, Shengxin Li, Quan Li | 14m |
Understood is an MR system on HoloLens 2 that uses GPT-4 to provide real-time dialogue summaries, context-aware next-word suggestions, and topic-shift… | ||
| Subthreshold Jitter in VR Can Induce Visual Discomfort | Samuel J Levulis, Kevin W. Rio, James P. Wilmott, Pablo Ramon Soria, Charlie S Burlingham, Phillip Guan | 11m |
Psychophysical testing finds peak sensitivity to XY jitter at intermediate frequencies with a 50% detection point around 0.23 mm at 12 Hz (1 m viewing… | ||
| agentAR: Creating Augmented Reality Applications with Tool-Augmented LLM-based Autonomous Agents | Chenfei Zhu, Shao-Kang Hsia, Xiyun Hu, Ziyi Liu, Jingyu Shi, Karthik Ramani | 09m |
agentAR uses a tool-augmented LLM autonomous agent plus a reusable tool library (object detection, speech recognition, pose tracking, rendering, UI modules) to… | ||
| HeatFlow: A Thermal-Tactile Display for Dynamic 2D Thermal Movements | Yatharth Singhal, Daniel Honrales, Jin Ryong Kim | 12m |
A wearable grid of nine tactile actuators and one thermal actuator renders moving heat by combining thermal masking with apparent tactile motion, using phantom… | ||
| Efficient Finger Model and Accurate Tracking for Hover-and-Touch, Mid-air and Microgesture Intera... | Quentin Zoppis, Sergi Pujades, Laurence Nigay, François Bérard | 11m |
Marker-based optical tracking uses four markers per finger, an articulated cylinder-and-sphere finger model, and a 7-minute per-user calibration to get 600… | ||
| Mod2Hap: Two Level Modular Haptic System for Body- and Hand- Interactions using Magnetorheologica... | Yong Hae Heo, Seok Hun Lee, Hongmin Yoon, Jaeyeon Lee, Sang-Youn Kim | 12m |
Mod2Hap is a two-level modular haptic system that uses magnetorheological (MR) fluid to provide passive, tunable resistance for body- and hand-scale… | ||
| DxHF: Providing High-Quality Human Feedback for LLM Alignment with Interactive Decomposition | Danqing Shi, Furui Cheng, Tino Weinkauf, Antti Oulasvirta, Mennatallah El-Assady | 13m |
DxHF decomposes long responses into decomposed claims, links similar statements, encodes claim relevance, and keeps raw text visible; an LLM-driven workflow… | ||
| Multi-Click: Cross-Tab Web Automation via Action Generalization | Jiacheng Zhang, Jiawen Li, Maryam Arab, Steve Oney | 12m |
A browser extension called Multi-Click performs the same click or typing action across tabs by letting users pick one element, use hover+scroll generalization… | ||
| CAnnotator: Photo-Guided Color Annotation for Degraded Ancient Paintings | Tan Tang, Yanhong Wu, Yihan Gao, Junming Gao, Songela Nur, Buwei Zhou, Yuchen Lin, Yingcai Wu, Xiaosong Wang, Xiaojiao Chen | 10m |
CAnnotator is an interactive system built over a 2‑year study that links degraded paintings to photo collections, extracts textures with a fine‑tuned tracker… | ||
| SustainaPrint: Making the Most of Eco-Friendly Filaments | Maxine Perroni-Scharf, Jennifer Xiao, Cole Paulin, Zhi Ray Wang, Ticha Sethapakdi, Muhammad Abdullah, Patrick Baudisch, Stefanie Mueller | 10m |
SustainaPrint combines finite element stress simulation with material-aware assignment to replace only low-stress regions with recycled or biodegradable… | ||
| PaperBridge: Crafting Research Narratives through Human-AI Co-Exploration | Runhua ZHANG, Yang Ouyang, Leixian Shen, Yuying Tang, Xiaojuan Ma, Huamin Qu, Xian Xu | 13m |
Tool that pulls publications from Google Scholar, clusters them with LLMs, and lets users alternate between bi-directional analysis engine top-down intent and… | ||
| ATCion: Exploring the Design of Icon-based Visual Aids for Enhancing In-cockpit Air Traffic Contr... | Yue Lyu, Xizi Wang, Hanlu Ma, Yalong Yang, Jian Zhao | 11m |
Built an icon-based system called ATCion icon set that turns action words into icons and preserves numeric tokens, places panels in the line of sight, and… | ||
| Texergy: Textile-based Harvesting, Storing, and Releasing of Mechanical Energy for Passive On-Bo... | Yu Jiang, Alice C Haynes, Jürgen Steimle | 13m |
Texergy harvests energy from everyday clothing interactions, stores it in elastic rubber cords with soft textile ratchets and latches, and releases it later… | ||
| HiLT: A Library for Generating Human-in-the-Loop Data Transformation GUIs | Sora Kanosue, Xiaorui Liu, Parker Ziegler, Eric Rawn, Sarah E. Chasins | 11m |
HiLT is a Python library that generates web GUIs, backend code, and a database from a pipeline of Stage abstractions (each stage is a Python function that… | ||
| SignGlass: First-Person View Comprehensive and Generalizable ASL Translation Using Wearable Glass | Yongxiang Cai, Taiting Lu, Zhenghao Li, Hao Zhou, Kenneth DeHaan, Xuhai "Orson" Xu, Mahanth Gowda, Yincheng Jin | 10m |
A wearable glasses prototype with three onboard micro‑cameras captures both hands and face and runs on-device streaming over Wi‑Fi to produce real‑time… | ||
| LegisFlow: Enhancing Korean Legal Research with Temporal-Aware LLM Interfaces | Junghwan Kim, Hyeonseok Jeon, Dongseok Heo, Jung Lee, Bongwon Suh | 12m |
LegisFlow is a web interface that retrieves statute versions by date from a temporal-aware JSON database with vectors, shows side-by-side laws, and offers an… | ||
| Demystifying Reward Design in Reinforcement Learning for Upper Extremity Interaction: Practical G... | Hannah Selder, Florian Fischer, Per Ola Kristensson, Arthur Fleig | 12m |
Systematically trains over 450 policies across three tasks (choice reaction, pointing, tracking) and varies three reward components. Finds distance (proximity)… | ||
| Morae: Proactively Pausing UI Agents for User Choices | Yi-Hao Peng, Ding Li, Jeffrey P. Bigham, Amy Pavel | 14m |
Morae is a browser-extension UI agent that uses large multimodal models to detect decision points, pause, and ask concise disambiguation questions so blind and… | ||
| Understanding Users' Perceptions and Expectations toward a Social Balloon Robot via an Explorator... | Chongyang Wang, Tianyi Xia, Yifan Wang, Gang Yu, Zixuan Zhao, Siqi Zheng, Manqiu Liao, Chen Liang, Yuan Gao, Chun Yu, Yuntao Wang, Yuanchun Shi | 10m |
A hardware prototype named BalloonBot prototype integrates ESP32 cameras, microphones, servos, tiny speakers and a helium balloon and manages to fly stably… | ||
| MagnePins: A Modular, Affordable, and DIY Refreshable Braille and Tactile Display | Jim Smiley, Swamy Ananthanarayan, Leona M Holloway, Matthew Butler, Tim Dwyer | 13m |
A modular refreshable tactile display is built as a 24x89 pin array with 2.5 mm pin pitch and a separate 6x32 Braille module, assembled in a makerspace from… | ||
| MapStory: Prototyping Editable Map Animations with LLM Agents | Aditya Gunturu, Ben Pearman, Keiichi Ihara, Morteza Faraji, Bryan Wang, Rubaiat Habib Kazi, Ryo Suzuki | 13m |
MapStory generates editable map-animation prototypes from plain text using a dual-agent LLM architecture that first produces a scene breakdown of camera moves… | ||
| Computational Scaffolding of Composition, Value, and Color for Disciplined Drawing | Jiaju Ma, Chau Vu, Asya Lyubavina, Catherine Liu, Jingyi Li | 12m |
ArtKrit is a Krita plugin that scaffolds disciplined drawing into three steps—composition, value, color—and gives adaptive guidance like composition lines… | ||
| Flowco: Mixed-Initiative Authoring of Reliable End-to-End Data Analyses via Dataflow Graphs and LLMs | Stephen Freund, Brooke Simon, Emery D. Berger, Eunice Jun | 11m |
Flowco is a web-deployed system (goflow.co) that composes LLM-generated Python into explicit dataflow graphs whose nodes have a three-level node abstraction… | ||
| VideoCraft: A Mixed Reality-Empowered Video Generation Workflow with Spatial Layer Editing for Co... | Boyu Li, Lin-Ping Yuan, Zeyu Wang | 12m |
VideoCraft combines a mixed-reality pre-stage with off-the-shelf video-to-video models (examples: Runway) and a new spatial layer mechanism to enable local… | ||
| Policy Maps: Tools for Guiding the Unbounded Space of LLM Behaviors | Michelle S. Lam, Fred Hohman, Dominik Moritz, Jeffrey P. Bigham, Kenneth Holstein, Mary Beth Kery | 13m |
Policy maps propose a concrete workflow and an interactive tool called Policy Projector that plots LLM input-output cases (from an Anthropic red‑teaming… | ||
| Adaptique: Multi-objective and Context-aware Online Adaptation of Selection Techniques in Virtual... | Chao-Jung Lai, Maurício Sousa, Tianyu Zhang, Ludwig Sidenmark, Tovi Grossman | 14m |
Adaptique is an online adapter that switches between raycasting, sticky ray, and ray-cursor by scoring each technique on four concrete objectives: Fitts' Law… | ||
| Thing2Reality: Enabling Spontaneous Creation of 3D Objects from 2D Content using Generative AI in... | Erzhen Hu, Mingyi Li, Andrew Hong, Xun Qian, Alex Olwal, David Kim, Seongkook Heo, Ruofei Du | 13m |
Thing2Reality turns a cropped 2D image into four orthogonal views on a hand menu then a server-side pipeline fuses them into fused 3D Gaussians (preview in… | ||
| ViseGPT: Towards Better Alignment of LLM-generated Data Wrangling Scripts and User Prompts | Jiajun Zhu, Xinyu Cheng, Zhongsu Luo, Yunfan Zhou, Xinhuan Shu, Di Weng, Yingcai Wu | 11m |
ViseGPT extracts eight types of constraints from natural-language prompts, generates targeted test cases, runs LLM-produced data-wrangling scripts against… | ||
| Sensible Agent: A Framework for Unobtrusive Interaction with Proactive AR Agents | Geonsun Lee, Min Xia, Nels Numan, Xun Qian, David Li, Yanhe Chen, Achin Kulshrestha, Ishan Chatterjee, Yinda Zhang, Dinesh Manocha, David Kim, Ruofei Du | 12m |
Sensible Agent adapts both what to suggest and how to present it using egocentric cameras, Yamnet audio, vision-language models and few-shot chain-of-thought… | ||
| Weight-Induced Consumed Endurance (WICE): A Model to Quantify Shoulder Fatigue with Weighted Objects | Tinghui Li, Eduardo Velloso, Anusha Withana, Zhanna Sarsenbayeva | 10m |
Presents WICE, a quantitative shoulder-fatigue model that adds a weight term and per-person arm mass to refine shoulder-torque and center-of-mass estimates… | ||
| eTactileKit: A Toolkit for Design Exploration and Rapid Prototyping of Electro-Tactile Interfaces | Praneeth Bimsara Perera, Ravindu Madhushan Pushpakumara, Hiroyuki Kajimoto, Arata Jingu, Jürgen Steimle, Anusha Withana | 12m |
A complete open‑source toolkit that builds modular hardware and software for electro‑tactile prototyping, delivering a stacked controller plus 32-electrode… | ||
| KinemaFX: A Kinematic-Driven Interactive System for Particle Effect Exploration and Customization | Yifei Zhang, Lin-Ping Yuan, Yuheng Zhao, Jielin Feng, Siming Chen | 13m |
KinemaFX presents a kinematic-driven pipeline that lets non-experts find and customize particle effects by combining graphical and texture intent, using LLMs… | ||
| GenTune: Toward Traceable Prompts to Improve Controllability of Image Refinement in Environment D... | Wen-Fan Wang, Ting-Ying Lee, Chien-Ting Lu, Che-Wei Hsu, Nil Ponsa i Campanyà, Yu Chen, Mike Y. Chen, Bing-Yu Robin Chen | 11m |
GenTune is a toolchain that generates structured prompts with LLM brainstorming, extracts labels with a label-extraction LLM, and links image regions to those… | ||
| ImaginationVellum: Generative-AI Ideation Canvas with Spatial Prompts, Generative Strokes, and Id... | Nicolai Marquardt, Asta Roseway, Hugo Romat, Payod Panda, Michel Pahud, Gonzalo A Ramos, Steven M. Drucker, Andrew D. Wilson, Ken Hinckley, Nathalie Henry Riche | 13m |
ImaginationVellum is a working multimodal canvas that uses the entire 2D surface as an active prompt: spatial arrangement, proximity, and composition of ink… | ||
| Imaginary Joint: Proprioceptive Feedback for Virtual Body Extensions via Skin Stretch | Shuto Takashita, Jürgen Steimle, Masahiko Inami | 11m |
A wearable dual-channel skin-stretch device is built to render an “imaginary joint” at the waist, encoding tail bending and torque by superposed angle and… | ||
| SoilSense: Appropriating Soil-based Microbial Fuel Cells to Create Tangible Interfaces | Tian Min, Yuma Tsukakoshi, Chengshuo Xia, Anusha Withana, Yuta Sugiura | 10m |
SoilSense repurposes SMFC cells so pressing the cathode raises voltage instead of just harvesting energy, with clear voltage jumps on handheld demos and… | ||
| From Sports Videos to Immersive Training: Augmenting Human Motion to Enrich Basketball Training E... | Yihong Wu, Xiao Xie, Lingyun Yu, Xinyi Ruan, Runzhou Li, Liqi Cheng, Shuainan Ye, Dazhen Deng, Hui Zhang, Yingcai Wu | 10m |
Pipeline reconstructs 3D player and ball motion from broadcast video using computer-vision tools (object detection, trajectory fitting, 4D Humans, EasyMocap)… | ||
| AttraCar: Multisensory In-Car VR with Thermal, Airflow, and Motion Feedback through Built-In Vehi... | Dohyeon Yeo, Gwangbin Kim, Minwoo Oh, Jeongju Park, Bocheon Gim, Seongjun Kang, Ahmed Elsharkawy, SeungJun Kim | 13m |
AttraCar repurposes a car’s HVAC and power seat to deliver thermal, airflow, and motion cues, using PWM and CAN control, relay valves, PI loops and K-type… | ||
| ForcePinch: Force-Responsive Spatial Interaction for Tracking Speed Control in XR | Chenyang Zhang, Tiffany S Ma, John Andrews, Eric J Gonzalez, Mar Gonzalez-Franco, Yalong Yang | 12m |
ForcePinch is a hardware-backed method that maps fingertip pinch force to pointer tracking speed using a pressure-sensor prototype and a per-user cubic-spline… | ||
| UltraEdit: In-Situ Design Environment for Ultrasound Haptization | Richard Huynh Noeske, Ayush Bhardwaj, Abbas Khawaja, Jin Ryong Kim | 14m |
UltraEdit is an in‑VR authoring tool that lets users shape mid‑air ultrasound haptics as tangible blobs that are stretched, squished, copied and applied to 3D… | ||
| Sculpin: Direct-Manipulation Transformation of JSON | Joshua Horowitz, Devamardeep Hayatpur, Haijun Xia, Jeffrey Heer | 12m |
Sculpin is a direct-manipulation environment that records step-by-step JSON transformations into a reusable program, emphasizing sculptable selections, small… | ||
| Graffiti: Enabling an Ecosystem of Personalized and Interoperable Social Applications | Theia Henderson, David R Karger, David D Clark | 12m |
Graffiti provides a client-side TypeScript API and a Vue.js plugin that reduces building a social app from full‑stack work to a few lines of front-end code… | ||
| Move with Style! Enhancing Avatar Embodiment in Virtual Reality through Proprioceptive Motion Fee... | David Wagmann, Marie Muehlhaus, Jürgen Steimle | 11m |
MotionStyler implements a real-time arm-based exoskeleton that renders a designed set of proprioceptive motion cues drawn from a conceptual space of motion… | ||
| SwitchAR: Perceptual Manipulations in Augmented Reality | Jonas Wombacher, Zhipeng Li, Jan Gugenheimer | 12m |
SwitchAR reconstructs a room using Quest 3 photogrammetry and style transfer, adds pseudo-random noise and a virtual avatar, then imperceptibly switches the… | ||
| Preference-Guided Multi-Objective UI Adaptation | Yao Song, Christoph Gebhardt, Yi-Chi Liao, Christian Holz | 14m |
A system infers ranked user preferences from a few manual element moves (smoothed with a triangular moving average), maps ranks to high/mid/low priority… | ||
| NeuroSync: Intent-Aware Code-Based Problem Solving via Direct LLM Understanding Modification | Wenshuo ZHANG, Leixian Shen, Shuchang Xu, Jindu Wang, Jian Zhao, Huamin Qu, Lin-Ping Yuan | 12m |
NeuroSync extracts an LLM’s intermediate LM understanding as a task graph and lets users inspect and edit it before code generation, implementing intent–task… | ||
| StepWrite: Adaptive Planning for Speech-Driven Text Generation | Hamza El Alaoui, Atieh Taheri, Yi-Hao Peng, Jeffrey P. Bigham | 13m |
A voice-driven system decomposes composition into a QA loop that asks targeted prompts, runs a fact-checking pass, classifies tone, and generates drafts that… | ||
| NarraGuide: an LLM-based Narrative Mobile Robot for Remote Place Exploration | Yaxin Hu, Arissa J. Sato, Jingxin Du, Chenming Ye, Anjun Zhu, Pragathi Praveena, Bilge Mutlu | 14m |
NarraGuide is a working prototype: a mobile robot built on a TurtleBot base with mounted cameras, a SLAM map and a location-indexed tourbook feeding an LLM… | ||
| VIP-Sim: A User-Centered Approach to Vision Impairment Simulation for Accessible Design | Max Rädler, Mark Colley, Enrico Rukzio | 11m |
VIP-Sim presents a participatory, symptom-based simulator built with N=7 vision-impaired collaborators using the Mono Witness Protocol and iterative GPU… | ||
| PosterMate: Audience-driven Collaborative Persona Agents for Poster Design | Donghoon Shin, Daniel Lee, Gary Hsieh, Gromit Yeuk-Yin Chan | 11m |
PosterMate generates audience-driven persona agents from a marketing brief, lets each agent give contextual text and image edits on a poster canvas, and runs a… | ||
| L.ink: Procedural Ink Growth for Controllable Surprise | Eric Nai-Li Chen, Joshua Kong Yang, Jeff Huang, Tongyu Zhou | 12m |
L.ink generates branching, organic strokes by feeding L-strings from L-systems into a pen that sequentially grows ink as hierarchical SVG, enabling animated… | ||
| SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM Interaction | Zeyuan Huang, Cangjun Gao, Yaxian Shan, Haoxiang Hu, Qingkun Li, Xiaoming Deng, Cuixia Ma, Yu-Kun Lai, Yong-Jin Liu, Feng Tian, Guozhong Dai, Hongan Wang | 13m |
SketchGPT is a sketch+speech interface that wires sketches, audio, and on-screen context into a multi-agent framework that segments and aligns modalities, uses… | ||
| MorphingSkin: A Skin-like Platform that Integrates Multimodal Hydraulic Actuators Based on Flexib... | Tianyu Yu, Peisheng He, Bob Tianqi Wei, Chenyuheng Wang, Xueqing Li, Xuezhu Wang, Yao Lu, Wei Yue, Megan Teng, Zihan Wang, Liwei Lin, Haipeng Mi, Qi Lu, Lining Yao | 13m |
MorphingSkin integrates flexible EOPs into a stretchable printed‑circuit/silicone sandwich (electrodes + pump membrane + TPU adhesion) to drive 16 independent… | ||
| CoGrader: Transforming Instructors' Assessment of Project Reports through Collaborative LLM Integ... | Zixin Chen, Jiachen Wang, Yumeng Li, Haobo Li, Chuhan Shi, Rong Zhang, Huamin Qu | 11m |
CoGrader pairs teachers with LLMs to reallocate tasks: instructors human-LLM collaborative metrics design, pick benchmarking with teacher-selected exemplar… | ||
| MEDebiaser: A Human-AI Feedback System for Mitigating Bias in Multi-label Medical Image Classific... | Shaohan Shi, Yuheng Shao, Haoran Jiang, Yunjie Yao, Zhijun Zhang, Xu Ding, Quan Li | 13m |
An interactive system called MEDebiaser lets physicians upload datasets, view label distributions and co‑occurrence, and directly correct model attention by… | ||
| Why am I seeing this: Democratizing End User Auditing for Online Content Recommendations | Chaoran Chen, Leyang Li, Luke Cao, Yanfang Ye, Tianshi Li, Yaxing Yao, Toby Jia-Jun Li | 12m |
An interactive browser sandbox generates synthetic personas and substitutes their data (IP, browsing history, location, ad IDs) to test whether specific… | ||
| ShoeGenAI: A Creativity Support Tool Bridging Design Intention and Feasibility in Shoe Design | Hui-Jun Kim, Jeongho Kim, SOHYUN JEONG, MINBONG LEE, Jaegul Choo, Sung-Hee Kim | 13m |
ShoeGenAI builds three models—a generator fine-tuned on real sneaker images and human descriptors, a combiner that crops soles with SAM then reconstructs with… | ||
| FlyMeThrough: Human-AI Collaborative 3D Indoor Mapping with Commodity Drones | Xia Su, Ruiqi Chen, Jingwei Ma, Chu Li, Jon E. Froehlich | 13m |
A drone-to-map pipeline converts consumer drone RGB videos into 3D reconstructions using Metashape photogrammetry, lets users click objects on frames… | ||
| UIST 2025 Opening + Keynote | Meeyoung Cha | 01h 19m |
Launches an AI Society and Computing initiative and shows working systems: a real-time food-price estimates pipeline built with UN partners in Indonesia that… | ||
| UIST 2025 Keynote + Closing | Choong-Wan Woo | 01h 35m |
Argues that organisms trade richness for certainty over accuracy, modeling the world as an Umwelt as interface defined by evolutionarily shaped sensors… | ||
| UIST 2025 Vision | Mira Dontcheva, Juho Kim | 01h 29m |
Two linked visions argue that “easy and fast” content creation is effectively solved by generative AI and that the next frontier is body-level integration. One… | ||
| nothing matches | ||