AI.info

Pengfei Wan

Explore Pengfei Wan on AI.info.

• PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives
• StreamHOI: Interaction-aware Temporal Memory Adaptation for Streaming HOI Video Generation
• TimeChat-Captioner: Scripting Multi-Scene Videos with Time-Aware and Structural Audio-Visual Captions
• Stable Velocity: A Variance Perspective on Flow Matching
• OmniSIFT: Modality-Asymmetric Token Compression for Efficient Omni-modal Large Language Models
• From Inpainting to Editing: Unlocking Robust Mask-Free Visual Dubbing via Generative Bootstrapping
• Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment
• GRAN-TED: Generating Robust, Aligned, and Nuanced Text Embedding for Diffusion Models
• SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder
• FilmWeaver: Weaving Consistent Multi-Shot Videos with Cache-Guided Autoregressive Diffusion
• Astra: General Interactive World Model with Autoregressive Denoising
• Monet: Reasoning in Latent Visual Space Beyond Images and Language
• MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs
• VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models
• OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes
• Latent Diffusion Model without Variational Autoencoder