Starred repositories
Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance (CVPR 2026 Highlight)
Latex template for ACM conference/Journal rebuttal.
Molecode presents molecules as code and enables LLMs to operate and reason on chemistry directly.
We propose Bidirectional Evolutionary Search (BES), a search framework that couples forward candidate evolution with backward goal decomposition.
Elevate your AI research writing, no more tedious polishing ✨
Official Implementation of OmniWeaving: Towards Unified Video Generation with Free-form Composition and Reasoning
Helios: Real Real-Time Long Video Generation Model
A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training
A collection of awesome think with videos papers.
A Curated List of Awesome Works in World Modeling, Aiming to Serve as a One-stop Resource for Researchers, Practitioners, and Enthusiasts Interested in World Modeling.
This is a collection of recent papers on reasoning in video generation models.
HunyuanVideo-1.5: A leading lightweight video generation model
Edit-R1: Reinforce Image Editing with Diffusion Negative-Aware Finetuning and MLLM Implicit Feedback
用于爬取Bilibili（B站）视频评论的爬虫🕷️，支持爬取一级评论及二级回复😊，并将数据导出为CSV文件。通过输入视频的BV号，脚本会自动获取视频信息并抓取相关评论，包含用户基本信息、评论内容、IP属地、头像、会员、等级等字段😉😉。
⭐微博评论爬取🕷，⭐⭐通过URL😏爬取指定微博下的所有评论内容⭐、用户信息🙈（IP地址、一二级评论（楼中楼）、简介、粉丝牌、微博认证、年龄、星座、学历、公司、微博注册日期、点赞、关注、评论、转发数等）附带源码与教程
Enjoy the magic of Diffusion models!
[[NeurIPS 2025] UltraVideo: High-Quality UHD Video Dataset with Comprehensive Captions
[NeurIPS 2025] The official code for "IllumiCraft: Unified Geometry and Illumination Diffusion for Controllable Video Generation"
LLM Reasoning Benchmark & Chain-of-Thoughts Dataset for Chemistry
A pipeline parallel training script for diffusion models.
Spark-Wan: Few-Step Video Diffusion Transformer via Hybrid Adversarial Post-Training
UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation
Sci-Fi: Symmetric Constraint for Frame Inbetweening