Pengfei Wan

AVoCaDO: An Audiovisual Video Captioner Driven by Temporal Orchestration

Latent Diffusion Model without Variational Autoencoder

UniVideo: Unified Understanding, Generation, and Editing for Videos

Unified In-Context Video Editing

Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?

Mitigating Noise Shift in Denoising Generative Models with Noise Awareness Guidance

VMoBA: Mixture-of-Block Attention for Video Diffusion Models

Improving Autoregressive Video Modeling with History Understanding

SimpleGVR: A Simple Baseline for Latent-Cascaded Generative Video Super-Resolution

VideoSearch Reasoner: Boosting Multimodal Reward Models through Think with Image Reasoning

From Inpainting to Editing: A Self-Bootstrapping Paradigm for Context-Rich Visual Dubbing

AdaViewPlanner: Adapting Video Diffusion Models for Viewpoint Planning in 4D Scenes

Free Lunch Alignment of Text-to-Image Diffusion Models without Preference Image Pairs

Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

Astra: General Interactive World Model with Autoregressive Denoising

RelightMaster: Precise Video Relighting with Multi-plane Light Images

A Guide to Training Consistency Models

A Reason-then-Describe Instruction Interpreter for Controllable Video Generation

VidBridge-R1: Bridging QA and Captioning for RL-based Video Understanding Models with Intermediate Proxy Tasks

Scaling Image and Video Generation via Test-Time Evolutionary Search

TivTok: Broadcasting Time-Invariant Tokens for Scalable Video Tokenization

FilMaster: Bridging Cinematic Principles and Generative AI for Automated Film Generation

OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes

Interpreting Any Condition to Caption for Controllable Video Generation

UniMMVSR: A Unified Multi-Modal Framework for Cascaded Video Super-Resolution

CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback

Efficient Training-Free High-Resolution Synthesis with Energy Rectification in Diffusion Models

OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing

PhysMaster: Mastering Physical Representation for Video Generation via Reinforcement Learning

SPF-Portrait: Towards Pure Text-to-Portrait Customization with Semantic Pollution-Free Fine-Tuning

Score Augmentation for Diffusion Models

VideoCanvas: Unified Video Completion from Arbitrary Spatiotemporal Patches via In-Context Conditioning

RealUnify: Do Unified Models Truly Benefit from Unification? A Comprehensive Benchmark

Terra: Explorable Native 3D World Model with Point Latents

VFXMaster: Unlocking Dynamic Visual Effect Generation via In-Context Learning

EmoDialogCN: A Multimodal Mandarin Dyadic Dialogue Dataset of Emotions

Bowtie-flow: Efficient High-Resolution Video Generation with Prior Preservation

Fast to Train, Fast to Sample: Stable Velocity for Flow Matching

OmniSync: Towards Universal Lip Synchronization via Diffusion Transformers

MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding

Flow-GRPO: Training Flow Matching Models via Online RL

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption

Training-Free Efficient Video Generation via Dynamic Token Carving

3DTrajMaster: Mastering 3D Trajectory for Multi-Entity Motion in Video Generation

Stable Segment Anything Model

Improving Video Generation with Human Feedback

Motion Inversion for Video Customization

Cafe-Talk: Generating 3D Talking Face Animation with Multimodal Coarse- and Fine-grained Control

SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints

SG-Adapter: Enhancing Text-to-Image Generation with Scene Graph Guidance

Kinda-45M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Content

Explicit-Constrained Single Agent for Enhanced Task-Solving in LLMs