8 papers
Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization
Yixuan Wang, Yifei Chen, Haichao Zhang +6
Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners. However, when optimizing multiple reward obj…
MUSE: A Unified Agentic Harness for MLLMs
Jianglin Lu, Hailing Wang, Xu Ma +4
Despite rapid progress, multimodal large language models (MLLMs) still fail on tasks that humans solve effortlessly, such as navigating a grid maze from a screenshot or selecting t…
D-CoDe: Scaling Image-Pretrained VLMs to Video via Dynamic Compression and Question Decomposition
Yiyang Huang, Yizhou Wang, Yun Fu
Video large language models (Vid-LLMs), which excel in diverse video-language tasks, can be effectively constructed by adapting image-pretrained vision-language models (VLMs). Howe…
Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Jianglin Lu, Hailing Wang, Yi Xu +3
Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exh…
Boosting Large Language Models with Mask Fine-Tuning
Mingyuan Zhang, Yue Bai, Huan Wang +4
The large language model (LLM) is typically integrated into the mainstream optimization protocol. However, it remains underexplored whether maintaining the model integrity is \text…
Towards Zero-shot 3D Anomaly Localization
Yizhou Wang, Kuan-Chuan Peng, Yun Fu
3D anomaly detection and localization is of great significance for industrial inspection. Prior 3D anomaly detection and localization methods focus on the setting that the testing…
Don't Judge by the Look: Towards Motion Coherent Video Representation
Yitian Zhang, Yue Bai, Huan Wang +2
Current training pipelines in object recognition neglect Hue Jittering when doing data augmentation as it not only brings appearance changes that are detrimental to classification,…
VaQuitA: Enhancing Alignment in LLM-Assisted Video Understanding
Yizhou Wang, Ruiyi Zhang, Haoliang Wang +3
Recent advancements in language-model-based video understanding have been progressing at a remarkable pace, spurred by the introduction of Large Language Models (LLMs). However, th…