activity
20242026
collaborators

17 papers

cs.CL2026

Context-Aware RL for Agentic and Multimodal LLMs

Peiyang Xu, Bangzheng Li, Sijia Liu +4

Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a tool…

cs.LG2026

Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework

David Huang, Jaewon Chang, Avidan Shah +2

The Rapid Response (RR) framework, deployed in production systems, including Anthropic's ASL-3 safeguards, continuously improves jailbreak-detection classifiers. When new jailbreak…

cs.LG2026

Can Small Training Runs Reliably Guide Data Curation? Rethinking Proxy-Model Practice

Jiachen T. Wang, Tong Wu, Kaifeng Lyu +4

Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the communit…

cs.LG2026

Certifiably Robust RAG against Retrieval Corruption

Chong Xiang, Tong Wu, Zexuan Zhong +3

Retrieval-augmented generation (RAG) is susceptible to retrieval corruption attacks, where malicious passages injected into retrieval results can lead to inaccurate model responses…

cs.CR2026

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search

Zeyu Shen, Basileal Imana, Tong Wu +3

Retrieval-Augmented Generation (RAG) enhances Large Language Models by grounding their outputs in external documents. These systems, however, remain vulnerable to attacks on the re…

cs.SD2025

The Model Hears You: Audio Language Model Deployments Should Consider the Principle of Least Privilege

Luxi He, Xiangyu Qi, Michel Liao +4

The latest Audio Language Models (Audio LMs) process speech directly instead of relying on a separate transcription step. This shift preserves detailed information, such as intonat…