5 papers
MMGist: A Comprehensive Multimodal Benchmark for 2027
Wenzhen Yuan, Jiacheng Ruan, Wutao Xiong +3
We conduct a systematic study of 18 widely used vision-language benchmarks and identify three major issues: 1) many items do not rely on visual cues and therefore fail to effective…
Small Model as Master Orchestrator: Learning Unified Agent-Tool Orchestration with Parallel Subtask Decomposition
Wenzhen Yuan, Wutao Xiong, Fanchen Yu +7
Multi-agent systems (MAS) demonstrate clear advantages in tackling complex problems by coordinating diverse agents and external tools. However, most existing orchestration methods…
Wisdom of the Crowd: Reinforcement Learning from Coevolutionary Collective Feedback
Wenzhen Yuan, Shengji Tang, Weihao Lin +8
Reinforcement learning (RL) has significantly enhanced the reasoning capabilities of large language models (LLMs), but its reliance on expensive human-labeled data or complex rewar…
VLRMBench: A Comprehensive and Challenging Benchmark for Vision-Language Reward Models
Jiacheng Ruan, Wenzhen Yuan, Xian Gao +6
Although large visual-language models (LVLMs) have demonstrated strong performance in multimodal tasks, errors may occasionally arise due to biases during the reasoning process. Re…
MM-CamObj: A Comprehensive Multimodal Dataset for Camouflaged Object Scenarios
Jiacheng Ruan, Wenzhen Yuan, Zehao Lin +5
Large visual-language models (LVLMs) have achieved great success in multiple applications. However, they still encounter challenges in complex scenes, especially those involving ca…