Skip to content
View Zefan-Cai's full-sized avatar

Highlights

  • Pro

Block or report Zefan-Cai

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Showing results

a systemone proxy using embeddings that distills a teacher model

Python 532 45 Updated Nov 9, 2026

Faster inference backend for Open-Jev-27B: fused CUDA kernels, prefix tree, CUDA Graphs (B300, bf16)

Cuda 93 8 Updated Sep 28, 2026

[EMNLP 2026 Findings] Test-Time Training with Next-Token Prediction.

Python 8 2 Updated Aug 30, 2026
Python 453 67 Updated Oct 4, 2026

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.

Python 2,952 221 Updated Sep 14, 2026
JavaScript 1 Updated Nov 17, 2026

DeepSeek Harness: Everything is a Plugin.

TypeScript 284,197 35,297 Updated Nov 18, 2026

Multi-Head Attention Residuals (MHAR): zero-parameter multi-head routing over the depth history — paper + reference implementation

Python 14 Updated Aug 4, 2026

[NeurIPS'26] "QUEST: Training Frontier Deep Research Agents with Fully Synthetic Tasks"

Python 260 26 Updated Oct 25, 2026

[ICML 2026 Oral] Code for "Skip a Layer or Loop It? Learning Program-of-Layers in LLMs"

Python 48 4 Updated Sep 28, 2026

Post-training with Tinker

Python 4,274 567 Updated Nov 17, 2026

A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

234,494 23,305 Updated Apr 20, 2026

Make Any Website into CLI & Use your logged-in browser by AI agent.

JavaScript 31,185 3,049 Updated Nov 7, 2026

A theoretical reconstruction of the Claude Mythos architecture, built from first principles using the available research literature.

Python 14,932 3,264 Updated May 23, 2026

[COLM '25] Single-Pass Document Scanning for Question Answering

Python 15 Updated Sep 6, 2026

Some commonly used research experiences and processes are encapsulated into Agent skills.

Python 890 106 Updated Nov 6, 2026

AI agents running research on single-GPU nanochat training automatically

Python 100,285 13,795 Updated Mar 26, 2026

This project aims to provide a high effective KV cache manage framework for llm inference and improve memory utilization and inference speed.

Python 75 6 Updated Apr 24, 2026

UniScientist is designed to advance universal scientific research intelligence through a unified paradigm

Python 175 13 Updated Mar 14, 2026

Hypernetworks that update LLMs to remember factual information

Python 846 107 Updated Jun 15, 2026

The AI that really does things. Any OS. Any Platform. The lobster way. 🦞

TypeScript 394,831 82,937 Updated Nov 19, 2026

StreamDiffusion, Live Stream APP

Python 596 68 Updated Sep 14, 2026

The simplest, fastest repository for training/finetuning medium-sized GPTs.

Python 64,931 11,176 Updated Nov 12, 2025

Lightweight Image Video Action Generation Inference Framework

Python 3,012 307 Updated Nov 19, 2026

implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880

Shell 383 33 Updated Feb 17, 2026

Official JAX implementation of End-to-End Test-Time Training for Long Context

Python 721 54 Updated Feb 15, 2026

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

Python 3,868 279 Updated Nov 4, 2026
Python 264 17 Updated Jul 28, 2026

[ECCV 2026 Spotlight] Implementation of "Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length"

Python 2,527 291 Updated Aug 24, 2026
Next