SOTA-Class TTS at Compact Scale

An MCP server that lets LLM agents play Civilization VI.

VulnGym: A Real-World, Project-Level Vulnerability Benchmark for White-Box Vulnerability-Hunting Agents

Code for paper "The Philosopher’s Stone: Trojaning Plugins of Large Language Models"

Industrial audio online policy distillation (OPD) training stack for ASR and TTS, distilling compact audio models from stronger teacher models.

A real-time and multilingual speech translation model

Video stabilization using gyroscope data

🏭 Mega Scale Multimodal DataPipeline for SOTA Foundation Models

Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.

Research of DeepSeek Engram Architecture based on Qwen-3 and Stable Diffusion series.

vLLM Adaptation for GLM ASR Nano

[AutoArk] GPA (General Purpose Audio) can do ASR, TTS and voice conversion with one tiny model!

EVA OS — A real-time multimodal AIOS for next-generation hardware, enabling your devices being “alive” and as intelligent as a real brain.

Reference PyTorch implementation and models for DINOv3

Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Fast inference engine for Transformer models

Build userspace NVMe drivers and storage applications with CUDA support

[CVPR 2024] This is the official source for our paper "SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis"

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

RepViT: Revisiting Mobile CNN From ViT Perspective [CVPR 2024] and RepViT-SAM: Towards Real-Time Segmenting Anything

[CVPR 2023] L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields

Infinite Photorealistic Worlds using Procedural Generation

IPTV直播源抓取 自动整合hao趣网直播源+TVBox直播源+其他网上直播源 择取分辨率、速度最佳视频流 定期更新

Digital Avatar Conversational System - Linly-Talker. 😄✨ Linly-Talker is an intelligent AI system that combines large language models (LLMs) with visual models to create a novel human-AI interaction…

Unity project for nerf_pl (Neural Radiance Fields)

InstantID: Zero-shot Identity-Preserving Generation in Seconds 🔥

Code release for NeRF (Neural Radiance Fields)

An interface for text-guided mesh refinement.