5 papers
Long Live The Balance: Information Bottleneck Driven Tree-based Policy Optimization
Hao Jiang, Shurui Li, Tianpeng Bu +7
Recent advances in online reinforcement learning (RL) for large language models (LLMs) have demonstrated promising performance in complex reasoning tasks. However, they often exhib…
DynFrame: Adaptive Reasoning-Driven Multimodal Framework with Dynamic Frame Augmentation for Complex Video Understanding
Peng Zhang, Guanghao Zhang, Wanggui He +10
Recent video multimodal large language models (MLLMs) increasingly couple step-by-step reasoning with on-demand visual evidence retrieval, allowing models to revisit relevant video…
RoMo: A Large-Scale, Richly Organized Dataset and Semantic Taxonomy for Human Motion Generation
Jiahao Zhang, Joseph Liu, Young-Yoon Lee +9
Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable models. 3D Human motion, how…
Diffusion-APO: Trajectory-Aware Direct Preference Alignment for Video Diffusion Transformers
Jingyuan Zhu, Biaolong Chen, Le Zhang +3
Efficiently aligning large-scale video diffusion models with human intent requires a scalable and trajectory-aware pathway that bridges the inherent discrepancy between training no…
SAG: Style-Aligned Article Generation via Model Collaboration
Chenning Xu, Fangxun Shu, Dian Jin +2
Large language models (LLMs) have increased the demand for personalized and stylish content generation. However, closed-source models like GPT-4 present limitations in optimization…