activity
20242026
collaborators

7 papers

cs.CV2026

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…

cs.CV2025

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…

cs.CV2025

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…

cs.RO2024

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…

cs.CV2024

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…

cs.CV2024

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…