~/talks

Yang Liu

what they talk about

all 13 in the filters

where they keep going back

no series more than once — all 18 in the filters

on a stage with

all 107 in the filters

who talks about the same things

titleconferencedate
Building Employee Experience Agents with Microsoft Copilot Studio and MCP IntegrationAgent Academy Live 20262026-05-12
Company ABC runs a demo that stitches Microsoft Copilot Studio, Power Platform and MCP servers to build three production patterns: a workplace support agent…
Talk on
CacheSlide: Unlocking Cross Position-Aware KV Cache Reuse for Accelerating LLM ServingFAST '262026-02-24
CacheSlide: Unlocking Cross Position-Aware KV Cache Reuse for Accelerating LLM Serving Yang Liu and Yunfei Gu, Shanghai Jiao Tong University; Liqiang Zhang…
Talk on
At a Glance to Your Fingertips: Enabling Direct Manipulation of Distant Objects Through SightWarpUIST 20252025-09-28
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…
Talk on
SelfDefend: LLMs Can Defend Themselves against Jailbreaking in...USENIX Security '252025-08-13
SelfDefend implements a shadow LLM that runs in parallel to a target model to detect harmful intent, using two detection templates (direct and intent prompts)…
Talk on
BlitzScale: Fast and Live Large Model Autoscaling with O(1) Host CachingOSDI '252025-07-07
System claims live, fast autoscaling by avoiding full model caching with O(1) host caching and loading parameters over compute fabrics (RDMA) using a…
Talk on
SimAI: Unifying Architecture Design and Performance Tuning for Large-Scale Large...NSDI '252025-04-28
SimAI claims a unified, high‑precision LLM training simulator that matches real runs 98.1% alignment by hijacking training frameworks (Megatron, DeepSpeed)…
Talk on
Evolution of Aegis: Fault Diagnosis for AI Model Training Service in ProductionNSDI '252025-04-28
Aegis is a production fault diagnosis system for AI model training that evolves from enhanced legacy tools to a customized collective communication library…
Talk on
Generically Automating Separation Logic by Functors, Homomorphisms, and ModulesPOPL 20252025-01-19
Claims a generic theory that generates separation logic reasoning rules from algebraic signatures (functors, homomorphisms, modules) and a compositional…
Talk
Enhancing Code Vulnerability Detection via Vulnerability-Preserving Data AugmentationLCTES 20242024-06-24
Claims a fine-grained detector that trains five binary classifiers for different CWE types and combines them by majority vote, built on an edge-aware GGNN and…
Talk on
How CIOs can reduce cloud costGoogle Cloud Next 20242024-04-09
Google Cloud announces a specific cost plan: N4 (Emerald Rapids + DRM) virtual machines let customers pick custom or predefined shapes and boost…
Talk on
Sparsifying Generalized Linear ModelsOptimization and Algorithm Design 20232023-11-27
Proves that sums F(x)=Σ f_i(<a_i,x>) with symmetric, monotone, mild growth f_i admit (1+ε)-approximate sparsifiers of support size about n/ε^2 times polylog…
Talk on
Sparsifying Sums of NormsBeyond the Boolean Cube 20232023-06-26
For N(x)=Σi Ni(x) there exist nonnegative weights w with only O(ε^{-2} n log(n/ε) (log n)^{2.5}) nonzeros and |N(x)−Σi wiNi(x)| ≤ εN(x) for all x, found by…
Talk on
Closing the B+-tree vs. LSM-tree Write Amplification Gap on Modern Storage Hardware...FAST '222022-02-22
Shows three concrete changes — deterministic page shadowing, localized modification logging, and sparse redo logging — applied to a B+-tree implementation and…
Talk on
Protect your database workloads in KubernetesKubeCon + CloudNativeCon + Open Source Summit China 20212021-12-09
Don’t miss out! Join us at our next event: KubeCon + CloudNativeCon Europe 2022 in Valencia, Spain from May 17-20. Learn more at https://kubecon.io The…
Talk on
WR-Hand: Wearable Armband can Track User's HandUbiComp 20212021-09-21
A wearable system tracks 3D positions of 14 skeleton points using commercial armband EMG plus gyroscope, running an RNN-enhanced biomedical model on a phone in…
Talk on
BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated LearningUSENIX ATC '202020-07-15
BatchCrypt encodes batches of quantized gradients into single long integers, uses two's-complement packing plus zeros padding and an analytical clipping method…
Talk on
Re-think Data Management Software Design Upon the Arrival of Storage Hardware with12th USENIX Workshop on Hot Topics in Storage and File Systems (HotStorage '20)2020-07-13
Argues that transparent compression embedded in drives (an FPGA-based flash controller exposing a standard block device) decouples logical from physical…
Talk on
POLARDB Meets Computational Storage: Efficiently Support Analytical Workloads in CloudFAST '202020-02-24
Paper reports a deployed replacement of SSDs with FPGA-based computational storage drive devices inside Alibaba Cloud POLARDB, plus coordinated changes to the…
Talk on
Increasing the trading prediction by mining aggregated human texting messagesPyData Barcelona 20172017-05-19
Claims that mining aggregated social media and news titles improves up/down stock prediction and shows modest accuracy gains but hides exact numbers; uses…
Talk on
~/search
type to search 6,249 conferences, 138,987 speakers and 185,172 talks
~/help
cmdctrl k
search every conference, speaker and series
/
focus the filter search
h
home
c
conferences
s
speakers
e
series
t
light / dark — the status bar button does the same
?
this help
esc
close this, then clear every filter — or just the search, while you are typing in it

Ignored while you are typing. Pages without a filter rail have no search to focus.