9 papers
DyCo-RL: Dynamic Cross-Modal Coordination for Visual Reasoning
Hangui Lin, Yan Shu, Zhengyang Liang +8
Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a leading paradigm for enhancing visual reasoning in Multimodal Large Language Models (MLLMs). However, existin…
Token Reduction via Local and Global Contexts Optimization for Efficient Video Large Language Models
Jinlong Li, Liyuan Jiang, Haonan Zhang +1
Video Large Language Models (VLLMs) demonstrate strong video understanding but suffer from inefficiency due to redundant visual tokens. Existing pruning primary targets intra-frame…
Video-Browser: Towards Open-web Agentic Video Browsing
Zhengyang Liang, Yan Shu, Xiangrui Liu +6
Autonomous agents are shifting information seeking from passive retrieval toward proactive, open-ended research, yet this progress has largely bypassed video, one of the web's rich…
Reverse Personalization
Han-Wei Kung, Tuomas Varanka, Nicu Sebe
Recent text-to-image diffusion models have demonstrated remarkable generation of realistic facial images conditioned on textual prompts and human identities, enabling creating pers…
A Closer Look at Conditional Prompt Tuning for Vision-Language Models
Ji Zhang, Shihan Wu, Lianli Gao +3
Despite the great promise of Prompt Tuning (PT) in adapting large Vision-Language Pretrained Models (VLPMs) to downstream tasks, they often struggle to overcome the Base-New Tradeo…
Reliable Few-shot Learning under Dual Noises
Ji Zhang, Jingkuan Song, Lianli Gao +2
Recent advances in model pre-training give rise to task adaptation-based few-shot learning (FSL), where the goal is to adapt a pre-trained task-agnostic model for capturing task-sp…
When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding
Yan Shu, Hangui Lin, Yexin Liu +7
Large Multimodal Models (LMMs) have achieved impressive progress in visual perception and reasoning. However, when confronted with visually ambiguous or non-semantic scene text, th…
VidText: Towards Comprehensive Evaluation for Video Text Understanding
Zhoufaran Yang, Yan Shu, Jing Wang +8
Visual texts embedded in videos carry rich semantic information, which is crucial for both holistic video understanding and fine-grained reasoning about local human actions. Howeve…
Memory-enhanced Retrieval Augmentation for Long Video Understanding
Huaying Yuan, Zheng Liu, Minghao Qin +5
Efficient long-video understanding~(LVU) remains a challenging task in computer vision. Current long-context vision-language models~(LVLMs) suffer from information loss due to comp…