Highlights
- Pro
Stars
a systemone proxy using embeddings that distills a teacher model
Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)
[EMNLP 2026 Findings] Test-Time Training with Next-Token Prediction.
J-Space Cognition Suite — a model-agnostic inference-time control suite for deep reasoning, long-horizon work, verification, and recovery. Based on Anthropic's J-space global workspace research.
DeepSeek Harness: Everything is a Plugin.
Multi-Head Attention Residuals (MHAR): zero-parameter multi-head routing over the depth history — paper + reference implementation
[NeurIPS'26] "QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks"
[ICML 2026 Oral] Code for "Skip a Layer or Loop It? Learning Program-of-Layers in LLMs"
Post-training with Tinker
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
Make Any Website into CLI & Use your logged-in browser by AI agent.
A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.
[COLM '25] Single-Pass Document Scanning for Question Answering
Some commonly used research experiences and processes are encapsulated into Agent skills.
AI agents running research on single-GPU nanochat training automatically
This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed.
UniScientist is designed to advance universal scientific research intelligence through a unified paradigm
Hypernetworks that update LLMs to remember factual information
The AI that really does things. Any OS. Any Platform. The lobster way. 🦞
StreamDiffusion, Live Stream APP
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Lightweight Image Video Action Generation Inference Framework
implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880
Official JAX implementation of End-to-End Test-Time Training for Long Context
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
[ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"