A collection of paper/projects that trains flow matching model/policies via RL.

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

📖 This is a repository for organizing papers, codes, and other resources related to Latent Reasoning.

A collection of resources on personalized image generation.

Efficient Multimodal Large Language Models: A Survey

Physical laws underpin all existence, and harnessing them for generative modeling opens boundless possibilities for advancing science and shaping the future!

my commonly-used tools

Identity-Preserving Text-to-Video Generation by Frequency Decomposition

A curated list of practical guide resources of Medical LLMs (Medical LLMs Tree, Tables, and Papers)

The paper collections for the autoregressive visual models.

[NeurIPS 2024 D&B Spotlight] ChronoMagic-Bench: A Benchmark for Metamorphic Evaluation of Text-to-Time-lapse Video Generation

A list for Text-to-Video, Image-to-Video works

Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation

This project aim to reproducing Sora (Open AI T2V model), but we only have limited resource. We deeply wish the all open source community can contribute to this project.

🐫 CAMEL: Communicative Agents for “Mind” Exploration of Large Scale Language Model Society

[NeurIPS 2022] Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations