Stars
codebase for iccv 2025 paper "One Trajectory, One Token: Grounded Video Tokenization via Panoptic Sub-object Trajectory"
Official implementation of "Slot-MLLM: Object-Centric Visual Tokenization for Multimodal LLM"
[CVPR2026] Official implementation of "OSPO: Object-centric Self-improving Preference Optimization for Text-to-Image Generation"
A Systematic Alignment Framework for High-Fidelity, Controllable, and Robust Video Generation.
[CVPR 2026]The official code and datasets for "UniVBench: Towards Unified Evaluation for Video Foundation Models"
A Mechanistic View on Video Generation as World Models: State and Dynamics
[ICML 2026] VideoLoom: A Video Large Language Model for Joint Spatial-Temporal Understanding
Long Video Gen / World Model / World Action Model (Embodied) Infrastructure
Code for "VideoRepair: Improving Text-to-Video Generation via Misalignment Evaluation and Localized Refinement [ACL 2026 Findings]"
[ICCV 2025] FiVE-Bench: A Fine-grained Video Editing Benchmark for Evaluating Emerging Diffusion and Rectified Flow Models
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
[AAAI 2026]🔥🔥🔥FocusDPO: Dynamic Preference Optimization for Multi-Subject Personalized Image Generation via Adaptive Focus
[TMLR 2025🔥] A survey for the autoregressive models in vision.
Lumina-DiMOO - An Open-Sourced Multi-Modal Large Diffusion Language Model
[ICLR 2026] RecA: visual understanding help generation through self-supervised learning
A curated list of papers on reinforcement learning for video generation
A curated list of recent diffusion models for video generation, editing, and various other applications.
🔥🔥🔥 [IEEE TCSVT] Latest Papers, Codes and Datasets on Vid-LLMs.
[ICCV 2025] TokensGen: Harnessing Condensed Tokens for Long Video Generation
Easily create large video dataset from video urls
[ECCV 2024] Enhancing Perceptual Quality in Video Super-Resolution through Temporally-Consistent Detail Synthesis using Diffusion Models
🔥 CNN for Watermark Removal using Deep Image Prior with Pytorch 🔥.
A repository containing datasets and tools to train a watermark classifier.