Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Puzzles for learning Triton

🎓 Update Talking-Face Research Papers Daily, Now Integrated with LLM Analysis.

The code used to train and run inference with the ColPali architecture.

Implementation of F5-TTS in MLX

An extension that lets the AI take the wheel, allowing it to use the mouse and keyboard, recognize UI elements, and prompt itself :3...now also act as a research assistant

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

Implementation of AlphaFold 3 in PyTorch Lightning + Hydra

Implementation of Alphafold 3 from Google Deepmind in Pytorch

Entropy Based Sampling and Parallel CoT Decoding

Kolmogorov-Arnold Transformer: A PyTorch Implementation with CUDA kernel

Mixture-of-Experts for Large Vision-Language Models

A generative speech model for daily dialogue.

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

FACodec: Speech Codec with Attribute Factorization used for NaturalSpeech 3

Speech-To-Text forced-alignment Speech processing Universal PERformance Benchmark

Text to speech alignment using CTC forced alignment

Qwen2-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

An implementation of piecewise linear time warping for multi-dimensional time series alignment

Diffusion Feedback Helps CLIP See Better

AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation

Bring portraits to life!

Official implementation of EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars

We aim to build the most powerful Next-js Boilerplate. So, people don't have to write the code for same features again and again.

Using Claude Sonnet 3.5 to forward (reverse) engineer code from VASA white paper - WIP - (this is for La Raza 🎷)

Code Implementation of EfficientVMamba

Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory wh…

[NeurIPS2024] Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model

PyTorch implementation of "Distinguishing Homophenes using Multi-Head Visual-Audio Memory" (AAAI2022)