collaborators

11 papers

cs.CL2026

From Seeing to Thinking: Decoupling Perception and Reasoning Improves Post-Training of Vision-Language Models

Juncheng Wu, Hardy Chen, Haoqin Tu +6

Recent advances in vision-language models (VLMs) emphasize long chain-of-thought reasoning; yet, we find that their performance on visual tasks is primarily limited by a lack of vi…

cs.SE2026

Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs

Yuxuan Lu, Ziyi Wang, Yingzhou Lu +12

Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environments that diverge from real API behavior…

cs.CV2026

REC-RL: Referring expression counting via Gaussian and range-based reward optimization

Hui Liu, Yunlai Teng, Kunlong Bai +4

Referring expression counting (REC) is an intention-driven task that requires context-aware visual reasoning. While recent vision-language models incorporate language for visual un…

cs.CV2026

When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs

Yahong Wang, Juncheng Wu, Zhangkai Ni +8

Vision Large Language Models (VLLMs) incur high computational costs due to their reliance on hundreds of visual tokens to represent images. While token pruning offers a promising s…

cs.LG2026

Synthesizing High-Quality Visual Question Answering from Medical Documents with Generator-Verifier LMMs

Xiaoke Huang, Ningsen Wang, Hui Liu +2

Large Multimodal Models (LMMs) are increasingly capable of answering medical questions that require joint reasoning over images and text, yet training general medical VQA systems i…

cs.CV2026

MedVLThinker: Simple Baselines for Multimodal Medical Reasoning

Xiaoke Huang, Juncheng Wu, Hui Liu +2

Large Reasoning Models (LRMs) have introduced a new paradigm in AI by enabling models to ``think before responding" via chain-of-thought reasoning. However, the absence of open and…