5 papers
Advancing MLLM-based UAV Image Understanding and Reasoning: A Benchmark and a Training-Free Multi-Agent System
Haoyu Zhang, Shuoxun Zhang, Peng Ye +5
Multimodal Large Language Model (MLLM)-based UAV aerial image understanding and reasoning is essential for aerial intelligence yet poses distinct challenges arising from extreme sc…
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
Siyao Chen, Jiakang Yuan, Jiaxin Wang +1
Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically requi…
FreshMem: Brain-Inspired Frequency-Space Hybrid Memory for Streaming Video Understanding
Kangcong Li, Peng Ye, Lin Zhang +3
Transitioning Multimodal Large Language Models (MLLMs) from offline to online streaming video understanding is essential for continuous perception. However, existing methods lack f…
Sequential Token Merging: Revisiting Hidden States
Yan Wen, Peng Ye, Lin Zhang +4
Vision Mambas (ViMs) achieve remarkable success with sub-quadratic complexity, but their efficiency remains constrained by quadratic token scaling with image resolution. While exis…
SC-Captioner: Improving Image Captioning with Self-Correction by Reinforcement Learning
Lin Zhang, Xianfang Zeng, Kangcong Li +2
We propose SC-Captioner, a reinforcement learning framework that enables the self-correcting capability of image caption models. Our crucial technique lies in the design of the rew…