collaborators

5 papers

cs.SD2026

Never Stop Speaking: a Denial-of-Service Attack on End-to-End Speech Language Models

Shuozhe Cheng, Kunlan Xiang, Mingxuan Li +3

Many studies have shown that specially crafted inputs can induce large language models (LLMs) to generate excessively long outputs, resulting in significant computational overhead…

cs.CR2026

When Poison Fails After Retrieval: Revisiting Corpus Poisoning under Chunking and Reranking Pipelines

Xi Nie, Hongwei Li, Shenghao Wu +3

Retrieval-Augmented Generation (RAG) systems are vulnerable to corpus poisoning attacks that manipulate downstream model outputs through malicious knowledge injection. Existing stu…

physics.chem-ph2025

Solvaformer: an SE(3)-equivariant graph transformer for small molecule solubility prediction

Jonathan Broadbent, Michael Bailey, Mingxuan Li +6

Accurate prediction of small molecule solubility using material-sparing approaches is critical for accelerating synthesis and process optimization, yet experimental measurement is…

cs.CL2025

HypoEval: Hypothesis-Guided Evaluation for Natural Language Generation

Mingxuan Li, Hanchen Li, Chenhao Tan

Large language models (LLMs) have demonstrated great potential for automating the evaluation of natural language generation. Previous frameworks of LLM-as-a-judge fall short in two…

cs.AI2025

Literature Meets Data: A Synergistic Approach to Hypothesis Generation

Haokun Liu, Yangqiaoyu Zhou, Mingxuan Li +2

AI holds promise for transforming scientific processes, including hypothesis generation. Prior work on hypothesis generation can be broadly categorized into theory-driven and data-…