6 papers
Grounded Continuation: A Linear-Time Runtime Verifier for LLM Conversations
Qisong He, Yi Dong, Xiaowei Huang
In long conversations, an LLM can produce a next utterance that sounds plausible but rests on premises the conversation has already abandoned. Context-manipulation attacks against…
Safety-Constrained Reinforcement Learning with Post-Training Reachability Verification for Robot Navigation
Qisong He, Xinmiao Huang, Jinwei Hu +4
Safe navigation for mobile robots demands policies that remain reliable under the high-consequence perception uncertainty of cluttered environments. Yet most existing safe reinforc…
FragileFlow: Spectral Control of Correct-but-Fragile Predictions for Foundation Model Robustness
Zhuoyun Li, Boxuan Wang, Jinwei Hu +2
Robust adaptation of LLMs and VLMs is often evaluated by average accuracy or average consistency under perturbations. However, these averages can hide a structured failure mode: a…
When Independent Sampling Outperforms Agentic Reasoning
Yihe Dong, Boris Shigida
We study how to allocate inference-time compute for competitive programming under fixed budgets. Evaluating 216 Codeforces problems across Divisions 1-3, we compare agent-based rea…
Metadata Conditioning Accelerates Language Model Pre-training
Tianyu Gao, Alexander Wettig, Luxi He +3
The vast diversity of styles, domains, and quality levels present in language model pre-training corpora is essential in developing general model capabilities, but efficiently lear…
Cache Me If You Can: How Many KVs Do You Need for Effective Long-Context LMs?
Adithya Bhaskar, Alexander Wettig, Tianyu Gao +2
Language models handle increasingly long contexts for tasks such as book summarization, but this leads to growing memory costs for the key-value (KV) cache. Many prior works have p…