15 papers
BadWAM: When World-Action Models Dream Right but Act Wrong
Qi Li, Xingyi Yang, Xinchao Wang
World-action models (WAMs) are emerging as a promising foundation for embodied control: rather than predicting actions alone, they learn representations that couple action generati…
dOPSD: On-Policy Self-Distillation for Diffusion Language Models
Phuong Tuan Dat, Qi Li, Xinchao Wang
Diffusion large language models (dLLMs) generate text by iteratively denoising a masked sequence, offering a parallel alternative to autoregressive models, but eliciting strong rea…
MixReasoning: Switching Modes to Think
Haiquan Lu, Gongfan Fang, Xinyin Ma +2
Reasoning models enhance performance by tackling problems in a step-by-step manner, decomposing them into sub-problems and exploring long chains of thought before producing an answ…
ViMU: Benchmarking Video Metaphorical Understanding
Qi Li, Xinchao Wang
Any new medium, once it emerges, is used for more than the transmission of overt content alone. The information it carries typically operates on two levels: one is the content dire…
On-Policy Self-Evolution via Failure Trajectories for Agentic Safety Alignment
Bo Yin, Qi Li, Xinchao Wang
Tool-using LLM agents fail through trajectories rather than only final responses, as they may execute unsafe tool calls, follow injected instructions, comply with harmful requests,…
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration
Ruhao Liu, Weiqi Huang, Qi Li +1
Membership Inference Attacks (MIAs) serve as a fundamental auditing tool for evaluating training data leakage in machine learning models. However, existing methodologies predominan…