5 papers
Group-of-Latents: Perceptual Video Compression at Extreme Bitrates via Masked Latent Generative Modeling
Shaokang Wang, Jinchang Xu, Peidong Jia +9
Most existing video compression algorithms follow a paradigm of transformation and quantization, optimizing the trade-off between distortion and bitrate. However, extremely low-bit…
Multimodal Unlearning Across Vision, Language, Video, and Audio: Survey of Methods, Datasets, and Benchmarks
Nobin Sarwar, Shubhashis Roy Dipta, Zheyuan Liu +1
With the growing adoption of VLMs, DMs, LLMs, and AFMs, these multimodal foundation models can inadvertently encode sensitive, copyrighted, biased, or unsafe cross-modal associatio…
IOI: Decoupling Kinematics and Physics for Interactive World Models
Chengyu Bai, Peidong Jia, Tiecheng Guo +11
Developing generalist embodied agents requires interactive environments providing visually realistic feedback and accurate action-conditioned dynamics. Interactive world models add…
MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation
Xingyuming Liu, Ruichun Ma, Heyu Guo +7
Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observation…
SafeDojo: Safe Reinforcement Learning for VLA via Interactive World Model
Kai Tang, Peidong Jia, Zhong Chu +15
Safe control is a prerequisite for real-world embodied intelligence, for which safe reinforcement learning has emerged as a promising paradigm. However, existing safe reinforcement…