collaborators

11 papers

cs.AI2026

Code Monitor Red Teaming for Public-Test-Passing Code

Junchi Liao, Jiawen Deng, Fuji Ren

Visible tests are a common gate for LLM-generated code, but passing them does not certify specification correctness. We study a deployment-like monitoring problem: after code has p…

cs.LG2026

Understanding Reasoning from Pretraining to Post-Training

Jingyan Shen, Ang Li, Salman Rahman +4

Reinforcement learning (RL) has become central to improving large language models (LLMs) on complex reasoning tasks, yet RL post-training is largely studied in isolation from the p…

cs.CL2026

End-to-End Context Compression at Scale

Ang Li, Sean McLeish, Haozhe Chen +12

Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degra…

cs.CV2026

Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes

Joseph Hoche, Andrei Bursuc, David Brellmann +4

Large Vision-Language Models (LVLMs) often produce plausible but unreliable outputs, making robust uncertainty estimation essential. Recent work on semantic uncertainty estimates r…

cs.LG2026

How's it going? Reinforcement learning in language models recruits a functional welfare axis

Andy Q Han, David J. Chalmers, Pavel Izmailov

How does reinforcement learning shape a language model's internal representations? We present evidence that RL recruits a pre-existing representation of functional welfare: an esti…

cs.LG2026

Forgetting in Language Models: Capacity, Optimization, and Self-Generated Replay

Martin Marek, Dongkyu Cho, Shikai Qiu +3

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from p…