TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Towards Scalable Pre-training of Visual Tokenizers for Generation

[NeurIPS 2025] Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance

FinRL®: Financial Reinforcement Learning. 🔥

Bitcoin arbitrage - opportunity detector

The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Adapting Self-Supervised Representations as a Latent Space for Efficient Generation

GenExam: A Multidisciplinary Text-to-Image Exam

MiMo-Embodied

SAM 3D Objects

The repository provides code for running inference and finetuning with the Meta Segment Anything Model 3 (SAM 3), links for downloading the trained model checkpoints, and example notebooks that sho…

🔥 A minimal training framework for scaling FLA models

PyTorch implementation of JiT https://arxiv.org/abs/2511.13720

[NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Code for our paper "Next Visual Granularity Generation".

FlashRNN - Fast RNN Kernels with I/O Awareness

Omnilingual ASR Open-Source Multilingual SpeechRecognition for 1600+ Languages

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

Compress and Attend Transformers (CATs) 😸

Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity

免费开源A股量化交易数据库； 专注A股，专注量化，向阳而生； 开放、纯净、持续、为Ai(爱)发电。为个人量化交易而生，保卫3000点，珍惜底部机会......【股票数据，股票行情数据，股票量化数据，股票交易数据，k线行情数据，股票概念数据，股票数据接口，行情数据接口，量化交易数据】【多数据源融合，动态设置代理，保障数据高可用性】

An official implementation of DanceGRPO: Unleashing GRPO on Visual Generation

A survey for visual generation alignment

Post-training with Tinker