We present FlashPortrait, an end-to-end video diffusion transformer capable of synthesizing ID-preserving, infinite-length videos while achieving up to 6$\times$ acceleration in inference speed.

LiveCC: Learning Video LLM with Streaming Speech Transcription at Scale (CVPR 2025)

Official repository for DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research

Local-first AI-powered document intelligence platform for investigative journalism

Taming large-scale full-parameter few-step training with self-adversarial flows! 👏🏻

Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models

MSLK (Meta Superintelligence Labs Kernels) is a collection of PyTorch GPU operator libraries that are designed and optimized for GenAI training and inference, such as FP8 row-wise quantization and …

PersonaLive! : Expressive Portrait Image Animation for Live Streaming

A python training pipeline for Apple MLX to produce a fine tuned model with Apple Neural Engine Support

Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

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

High-performance FlashAttention-2 for AMD, Intel, and Apple GPUs. Drop-in replacement for PyTorch SDPA. Triton backend for ROCm (MI300X, RDNA3), Vulkan backend for consumer GPUs. No CUDA required.

An open-source framework for detecting, redacting, masking, and anonymizing sensitive data (PII) across text, images, and structured data. Supports NLP, pattern matching, and customizable pipelines.

A lightweight suite of motion imitation methods for training controllers.

Holographic Transformers for Complex-Valued Signal Processing

SN1: An incentive mechanism for internet-scale conversational intelligence

Improved 3DGS rasterizer.

Memory infrastructure for LLMs and AI agents

Tora: Torchtune-LoRA for RL

Riemannian Adaptive Optimization Methods with pytorch optim

A general memory system for agents, powered by deep-research

Easy and Efficient dLLM Fine-Tuning

Awesome list of AI-Driven Development.

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.