activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

Weichen Yu, Xiaomin Li, Yizhou Zhao +8

Large language models are often post-trained with sparse verifier rewards, which indicate whether a sampled trajectory succeeds but provide limited guidance about where reasoning s…

cs.LG2026

When the Same Coefficients Reach Different Places: Asymmetric Realizability in Transplanting Tokenizers across Large Language Models

Xiaoze Liu, Weichen Yu, Matt Fredrikson +2

Tokenizer transplant in cross-vocabulary model composition reconstructs donor-only embedding rows as weighted combinations over shared lexical anchors and reuses those coefficients…

cs.LG2026

LipNeXt: Scaling up Lipschitz-based Certified Robustness to Billion-parameter Models

Kai Hu, Haoqi Hu, Matt Fredrikson

Lipschitz-based certification offers efficient, deterministic robustness guarantees but has struggled to scale in model size, training efficiency, and ImageNet performance. We intr…

cs.LG2025

Evaluating Language Model Reasoning about Confidential Information

Dylan Sam, Alexander Robey, Andy Zou +2

As language models are increasingly deployed as autonomous agents in high-stakes settings, ensuring that they reliably follow user-defined rules has become a critical safety concer…

cs.LG2025

AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents

Maksym Andriushchenko, Alexandra Souly, Mateusz Dziemian +11

The robustness of LLMs to jailbreak attacks, where users design prompts to circumvent safety measures and misuse model capabilities, has been studied primarily for LLMs acting as s…