not-lain
Follow
Lists (6)
Stars
deiteris / voice-changer
Forked from w-okada/voice-changerリアルタイムボイスチェンジャー Realtime Voice Changer
Mirage: Automatically Generating Fast GPU Kernels without Programming in Triton/CUDA
Efficient implementation of DeepSeek Ops (Blockwise FP8 GEMM, MoE, and MLA) for AMD Instinct MI300X
GPU programming related news and material links
About This repository is a curated collection of the most exciting and influential CVPR 2025 papers. 🔥 [Paper + Code + Demo]
An AI-powered educational game and verification tool to combat digital scams in Tunisia. Built for the AINS hackathon.
A lightweight, completely free experiment tracking Python library built on top of 🤗 Datasets and Spaces.
High-Precision Dichotomous Image Segmentation via Probing Diffusion Capacity (ICLR2025)
🦛 CHONK your texts with Chonkie ✨ — The no-nonsense RAG chunking library
LBM: Latent Bridge Matching for Fast Image-to-Image Translation ✨ (ICCV 2025)
From data to vector database effortlessly
The simplest, fastest repository for training/finetuning small-sized VLMs.
A TTS model capable of generating ultra-realistic dialogue in one pass.
Finetune Sesame's CSM 1B model, for fun and profit
A fast, streaming‑first Rust library for processing LLM outputs by attaching callbacks to XML‑style tags supporting both streaming and buffered handlers and using aho‑corasick for ultra‑efficient, …
[CVPR 2024] The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"
[SIGGRAPH 2025] LAM: Large Avatar Model for One-shot Animatable Gaussian Head
Lumina-mGPT 2.0: Stand-alone Autoregressive Image Modeling
[ICCV 2025] AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction
A curated list of awesome resources for dichotomous image segmentation (DIS).
Patch-Depth Fusion: Dichotomous Image Segmentation via Fine-Grained Patch Strategy and Depth Integrity-Prior
YouTube Music Desktop App bundled with custom plugins
Rembg is a tool to remove images background
[CVPR'25 Highlight] Official repository of Sonata: Self-Supervised Learning of Reliable Point Representations
Model Context Protocol Servers