12 papers
Simple-OPD: Demystifying Warm-up for On-policy Distillation
Tao Liu, Taiqiang Wu, Mao Zheng +5
On-policy distillation (OPD) trains a student on its own rollouts with token-level supervision from teacher models, but its effectiveness can depend strongly on the warm-up stage b…
RGBT-GroundBench: Visual Grounding Beyond RGB in Complex Real-World Scenarios
Tianyi Zhao, Jiawen Xi, Linhui Xiao +4
Visual grounding (VG) localizes target objects in an image from natural-language expressions. In real-world perception, RGB cues often degrade under low illumination and adverse we…
Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models
Xiaomin Yu, Yi Xin, Yuhui Zhang +12
Despite the success of multimodal contrastive learning in aligning visual and linguistic representations, a persistent geometric anomaly, the Modality Gap, remains: embeddings of d…
Moment-Video: Diagnosing Temporal Fidelity of Video MLLMs on Momentary Visual Events
Xiaolin Liu, Yilun Zhu, Xiangyu Zhao +9
Video multimodal large language models (MLLMs) have made rapid progress on general and long-form video understanding, yet their ability to preserve brief answer-critical visual evi…
Internalize the Temperature: On-Policy Self-Distillation as Policy Reheater for Reinforcement Learning
Xuewei Yang, Jiachen Yu, Jie Wu +3
Reinforcement learning from verifiable rewards improves the reasoning ability of large language models, but often suffers from entropy collapse, in which increasingly concentrated…
GeoEyes: On-Demand Visual Focusing for Evidence-Grounded Understanding of Ultra-High-Resolution Remote Sensing Imagery
Fengxiang Wang, Mingshuo Chen, Yueying Li +10
The "thinking-with-images" paradigm enables multimodal large language models (MLLMs) to actively explore visual scenes via zoom-in tools. This is essential for ultra-high-resolutio…