9 papers
UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation
Liming Tan, Ye Chen, Hao Zhang +3
Controlling human motion and camera movement is essential for faithful human-oriented video generation, yet remains challenging in multi-person scenes with large body motions, occl…
World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration
Ye Chen, Xuanhong Chen, Yupeng Zhu +23
The fundamental obstacle to industrial grade video generation is the lack of controllability: existing models treat video as a pixel distribution sampling problem, bypassing the ex…
Unified Safe In-context Image Generation in Multimodal Diffusion Transformers via Restricting Unsafe Information Flows
Xiang Yang, Feifei Li, Mi Zhang +4
Diffusion transformers (DiTs) equipped with multimodal attention (MM-Attn) have become a dominant paradigm for image generation. However, preventing the generation of harmful conte…
Broken Memories: Detecting and Mitigating Memorization in Diffusion Models with Degraded Generations
Yuanmin Huang, Mi Zhang, Chen Chen +4
While diffusion models excel at generating high-quality images, their tendency to memorize training data poses significant privacy and copyright risks. In this work, we for the fir…
VERTIGO: Visual Preference Optimization for Cinematic Camera Trajectory Generation
Mengtian Li, Yuwei Lu, Feifei Li +3
Cinematic camera control relies on a tight feedback loop between director and cinematographer, where camera motion and framing are continuously reviewed and refined. Recent generat…
SafeRoPE: Risk-specific Head-wise Embedding Rotation for Safe Generation in Rectified Flow Transformers
Xiang Yang, Feifei Li, Mi Zhang +3
Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when…
SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
Yiming Sun, Mi Zhang, Feifei Li +2
Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world app…
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
Feifei Li, Mi Zhang, Zhaoxiang Wang +1
Interpretability of point cloud (PC) models becomes imperative given their deployment in safety-critical scenarios such as autonomous vehicles. We focus on attributing PC model out…
Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
Feifei Li, Mi Zhang, Yiming Sun +1
Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful conte…