6 papers
AEGPO: Adaptive Entropy-Guided Policy Optimization for Diffusion Models
Yuming Li, Qingyu Li, Chengyu Bai +6
Reinforcement learning from human feedback (RLHF) shows promise for aligning diffusion and flow models, yet policy optimization methods such as GRPO suffer from inefficient and sta…
StreamKV: Streaming Video Question-Answering with Segment-based KV Cache Retrieval and Compression
Yilong Chen, Xiang Bai, Zhibin Wang +4
Video Large Language Models (Video-LLMs) have demonstrated significant potential in the areas of video captioning, search, and summarization. However, current Video-LLMs still face…
WoW: Towards a World omniscient World model Through Embodied Interaction
Xiaowei Chi, Peidong Jia, Chun-Kai Fan +33
Humans develop an understanding of intuitive physics through active interaction with the world. This approach is in stark contrast to current video models, such as Sora, which rely…
UniEdit-I: Training-free Image Editing for Unified VLM via Iterative Understanding, Editing and Verifying
Chengyu Bai, Jintao Chen, Xiang Bai +4
While Unified Vision-Language Models promise to synergistically combine the high-level semantic understanding of vision-language models with the generative fidelity of diffusion mo…
FastInit: Fast Noise Initialization for Temporally Consistent Video Generation
Chengyu Bai, Yuming Li, Zhongyu Zhao +5
Video generation has made significant strides with the development of diffusion models; however, achieving high temporal consistency remains a challenging task. Recently, FreeInit…
EmbodiedOcc++: Boosting Embodied 3D Occupancy Prediction with Plane Regularization and Uncertainty Sampler
Hao Wang, Xiaobao Wei, Xiaoan Zhang +6
Online 3D occupancy prediction provides a comprehensive spatial understanding of embodied environments. While the innovative EmbodiedOcc framework utilizes 3D semantic Gaussians fo…