3 papers
cs.CV2026
Self-Evolving Visual Questioner
Yijun Liang, Hengguang Zhou, Ming Li +3
Vision-language models (VLMs) are typically trained as passive answerers, while their ability to actively ask diverse, non-trivial, visual-centric and grounded questions remains un…
cs.LG2026
Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Training-Time Reward Hacking in Code Generation
Lichen Li, Hengguang Zhou, Yijun Liang +2
Reward hacking in code generation, where models exploit evaluation loopholes to obtain high reward without correctly solving the intended task, poses a critical challenge for Reinf…
cs.CV2025
Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
Qizhe Zhang, Mengzhen Liu, Lichen Li +5
In multimodal large language models (MLLMs), the length of input visual tokens is often significantly greater than that of their textual counterparts, leading to a high inference c…