11 papers
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…
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…
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…
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…
Where on Earth? A Vision-Language Benchmark for Probing Model Geolocation Skills Across Scales
Zhaofang Qian, Hardy Chen, Zeyu Wang +9
Vision-language models (VLMs) have advanced rapidly, yet their capacity for image-grounded geolocation in open-world conditions, a task that is challenging and of demand in real li…
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…
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…
Efficient Long CoT Reasoning in Small Language Models
Zhaoyang Wang, Jinqi Jiang, Tian Qiu +3
Recent large reasoning models such as DeepSeek-R1 exhibit strong complex problems solving abilities by generating long chain-of-thought (CoT) reasoning steps. It is challenging to…
SFT or RL? An Early Investigation into Training R1-Like Reasoning Large Vision-Language Models
Hardy Chen, Haoqin Tu, Fali Wang +5
This work revisits the dominant supervised fine-tuning (SFT) then reinforcement learning (RL) paradigm for training Large Vision-Language Models (LVLMs), and reveals a key finding:…
m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models
Xiaoke Huang, Juncheng Wu, Hui Liu +2
Test-time scaling has emerged as a powerful technique for enhancing the reasoning capabilities of large language models. However, its effectiveness in medical reasoning remains unc…
ViLBench: A Suite for Vision-Language Process Reward Modeling
Haoqin Tu, Weitao Feng, Hardy Chen +3
Process-supervised reward models serve as a fine-grained function that provides detailed step-wise feedback to model responses, facilitating effective selection of reasoning trajec…