6 papers
Why Keep Your Doubts to Yourself? Trading Visual Uncertainties in Multi-Agent Bandit Systems
Jusheng Zhang, Yijia Fan, Kaitong Cai +6
Vision-Language Models (VLMs) enable powerful multi-agent systems, but scaling them is economically unsustainable: coordinating heterogeneous agents under information asymmetry oft…
Self-Rewarded Multimodal Coherent Reasoning Across Diverse Visual Domains
Jesen Zhang, Ningyuan Liu, Kaitong Cai +5
Multimodal LLMs often produce fluent yet unreliable reasoning, exhibiting weak step-to-step coherence and insufficient visual grounding, largely because existing alignment approach…
MM-CoT:A Benchmark for Probing Visual Chain-of-Thought Reasoning in Multimodal Models
Jusheng Zhang, Kaitong Cai, Xiaoyang Guo +10
The ability to perform Chain-of-Thought (CoT) reasoning marks a major milestone for multimodal models (MMs), enabling them to solve complex visual reasoning problems. Yet a critica…
MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models
Zimeng Huang, Jinxin Ke, Xiaoxuan Fan +9
Large Vision-Language Models (LVLMs) have exhibited remarkable progress. However, deficiencies remain compared to human intelligence, such as hallucination and shallow pattern matc…
Failure-Driven Workflow Refinement
Jusheng Zhang, Kaitong Cai, Qinglin Zeng +4
Optimizing LLM-based workflows is typically formulated as a global search, where candidate workflows are evaluated based on a scalar metric. This paradigm, however, suffers from a…
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
Qiang Chen, Xiangbo Su, Xinyu Zhang +12
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection. The architecture is a simple stack of a ViT encoder…