4 papers
Grounding with Confidence: Controllable Generative Video Temporal Grounding
Jinhao Chen, Benlei Cui, Ruijian Jia +7
Video temporal grounding supports applications such as video search, content review, and automated editing by localizing events described in natural language. Yet existing generati…
Eq.Bot: Enhance Robotic Manipulation Learning via Group Equivariant Canonicalization
Jian Deng, Yuandong Wang, Yangfu Zhu +3
Robotic manipulation systems are increasingly deployed across diverse domains. Yet existing multi-modal learning frameworks lack inherent guarantees of geometric consistency, strug…
MathSE: Improving Multimodal Mathematical Reasoning via Self-Evolving Iterative Reflection and Reward-Guided Fine-Tuning
Jinhao Chen, Zhen Yang, Jianxin Shi +2
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language answering tasks. Despite their strengths, these models often encounter challen…
DECAMP: Towards Scene-Consistent Multi-Agent Motion Prediction with Disentangled Context-Aware Pre-Training
Jianxin Shi, Zengqi Peng, Xiaolong Chen +2
Trajectory prediction is a critical component of autonomous driving, essential for ensuring both safety and efficiency on the road. However, traditional approaches often struggle w…