5 papers
Mitigating Visual Degradation in MLLMs via Spatial-Spectral Visual Anchor Learning
Qianlong Yang, Bowen Ye, Xianda Guo +4
Despite the progress of multimodal large language models (MLLMs), they continue to exhibit deficiencies in visual perception. Following visual instruction tuning, internal MLLM rep…
GRPO-TTA: Test-Time Visual Tuning for Vision-Language Models via GRPO-Driven Reinforcement Learning
Yujun Li, Hongyuan Zhang, Yuan Yuan
Group Relative Policy Optimization (GRPO) has recently shown strong performance in post-training large language models and vision-language models. It raises a question of whether t…
Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models
Zhenwei Shao, Mingyang Wang, Weijun Zhang +6
Large vision-language models (VLMs) have demonstrated remarkable capabilities in open-world multimodal understanding, yet their high computational overheads pose great challenges f…
Crab: A Scalable and Unified Audio-Visual Scene Understanding Model with Explicit Cooperation
Dongnuan Cai, Henghui Du, Chang Zhou +5
Developing Audio-Visual Large Language Models (AV-LLMs) for unified scene understanding is pivotal in multimodal intelligence. While instruction tuning enables pre-trained models w…
MindWatcher: Toward Smarter Multimodal Tool-Integrated Reasoning
Jiawei Chen, Xintian Shen, Lihao Zheng +43
Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of auto…