Aditi Raghunathan
where else to find them
no profile links on file
what they talk about
where they keep going back
no series more than once — all 4 in the filters
on a stage with
- Daniel Hsuonce
- Danqi Chenonce
- Jhih-Yi (Janet) Hsiehonce
all 5 in the filters
who talks about the same things
nobody close enough yet
| title | conference | date |
|---|---|---|
| Vulnerability of Text-Matching in ML/AI Conference Reviewer Assignments... | USENIX Security '25 | 2025-08-13 |
Automated text-matching used for reviewer assignment is exploitable: combining adversarial archive curation (keeping only the most similar past paper) with… | ||
| Discussion Session | Special Year on Large Language Models and Transformers, Part 1 Boot Camp | 2024-09-04 |
A wide-ranging discussion maps specific research bets and failures: controlled data and open‑source training to test combinatorial creativity and diffusion… | ||
| Challenges in Making LLMs Safe and Robust | Special Year on Large Language Models and Transformers, Part 1 Boot Camp | 2024-09-04 |
Shows that transformers trained from scratch can implement both ridge vs discrete regression but fine-tuning on one task quickly ruins performance on the… | ||
| Understanding the Robustness of Deep Learning | Deep Learning Theory Workshop and Summer School 2022 | 2022-08-01 |
Pre-trained models help robustness, but the adaptation rule matters: with limited labeled adaptation data and overparameterized features, updating all weights… | ||
| Neural Networks And Spurious Correlations | Algorithmic Aspects of Causal Inference 2022 | 2022-03-18 |
Neural nets often latch onto easy but unstable cues, producing high worst-group error when spurious attributes (like background color) are easier to learn than… | ||
| nothing matches | ||