collaborators

11 papers

cs.CV2026

SepPrune:A Separator-based Pruning Framework for Efficient Multimodal Large Language Models

Yuchen Wang, Qihui Zhu, Yang Liu +2

Recent multimodal large language models (MLLMs), such as Qwen2.5-VL and InternVL3, generate large numbers of vision tokens for high-resolution inputs, leading to substantial comput…

cs.CV2026

RP-OPSD: Resolution-Privileged On-Policy Self-Distillation for Multimodal Large Language Models

Qihui Zhu, Yuchen Wang, Zijian Wen +7

On-Policy Self-Distillation (OPSD) uses privileged information available only to the teacher to provide dense token-level supervision on trajectories generated by the student. Howe…

cs.AI2026

MAR:Multi-Agent Reflexion Improves Reasoning Abilities in LLMs

Onat Ozer, Yuchen Wang, Grace Wu +3

LLMs have shown the capacity to improve their performance on reasoning tasks through reflecting on their mistakes, and acting with these reflections in mind. However, continual ref…

cs.CL2026

Escaping the BLEU Trap: A Signal-Grounded Framework with Decoupled Semantic Guidance for EEG-to-Text Decoding

Yuchen Wang, Haonan Wang, Yu Guo +2

Decoding natural language from non-invasive EEG signals is a promising yet challenging task. However, current state-of-the-art models remain constrained by three fundamental issues…

cs.CL2026

Compose and Fuse: Revisiting the Foundational Bottlenecks in Multimodal Reasoning

Yucheng Wang, Yifan Hou, Aydin Javadov +2

Multimodal large language models (MLLMs) promise enhanced reasoning by integrating diverse inputs such as text, vision, and audio. Yet cross-modal reasoning remains underexplored,…

cs.CV2026

HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models

Qihui Zhu, Tao Zhang, Yuchen Wang +9

In multimodal large language models (MLLMs), the surge of visual tokens significantly increases the inference time and computational overhead, making them impractical for real-time…