The official implementation of flow Q-learning (FQL)

AnyLoc: Universal Visual Place Recognition (RA-L 2023)

DINO-Mix: Enhancing Visual Place Recognition with Foundational Vision Model and Feature Mixing

NetVLAD: CNN architecture for weakly supervised place recognition

slime is an LLM post-training framework for RL Scaling.

A Foundation Model for Generalist Gaming Agents

DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space

Efficient vision foundation models for high-resolution generation and perception.

Towards Scalable Pre-training of Visual Tokenizers for Generation

Jacobi Forcing: Fast and Accurate Diffusion-style Decoding

一个用C++编写的极速ncm解密器

一个使用C++编写的极速ncm转换GUI工具

[ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation

Official Code of "Distribution Matching Distillation Meets Reinforcement Learning"

[NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state…

[ICML 2025] Official PyTorch Implementation of "History-Guided Video Diffusion"

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

Kimi-Audio, an open-source audio foundation model excelling in audio understanding, generation, and conversation

Depth Anything 3

[NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

StreamDiffusion, Live Stream APP

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo

Contexts Optical Compression

Pixel-Space Generative Models

Native Multimodal Models are World Learners

pi-Flow: Policy-Based Few-Step Generation via Imitation Distillation

Official repo for paper "EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning"

Official Implementations for Paper - HoloCine: Holistic Generation of Cinematic Multi-Shot Long Video Narratives