7 papers
Immune2V: Image Immunization Against Dual-Stream Image-to-Video Generation
Zeqian Long, Ozgur Kara, Haotian Xue +2
Image-to-video (I2V) generation has the potential for societal harm because it enables the unauthorized animation of static images to create realistic deepfakes. While existing def…
MoGAN: Improving Motion Quality in Video Diffusion via Few-Step Motion Adversarial Post-Training
Haotian Xue, Qi Chen, Zhonghao Wang +4
Video diffusion models achieve strong frame-level fidelity but still struggle with motion coherence, dynamics and realism, often producing jitter, ghosting, or implausible dynamics…
Point-It-Out: Benchmarking Embodied Reasoning for Vision Language Models in Multi-Stage Visual Grounding
Haotian Xue, Yunhao Ge, Yu Zeng +4
Vision-Language Models (VLMs) have demonstrated impressive world knowledge across a wide range of tasks, making them promising candidates for embodied reasoning applications. Howev…
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
Atharva Mete, Haotian Xue, Albert Wilcox +2
Generalization capabilities, or rather a lack thereof, is one of the most important unsolved problems in the field of robot learning, and while several large scale efforts have set…
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Yipu Chen, Haotian Xue, Yongxin Chen
Diffusion models (DMs) have emerged as a promising approach for behavior cloning (BC). Diffusion policies (DP) based on DMs have elevated BC performance to new heights, demonstrati…
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
Jiaojiao Fan, Haotian Xue, Qinsheng Zhang +1
There is a rapidly growing interest in controlling consistency across multiple generated images using diffusion models. Among various methods, recent works have found that simply m…