Skip to content
View yzhuuu's full-sized avatar

Block or report yzhuuu

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

Embodied Reasoning Question Answer (ERQA) Benchmark

Python 338 19 Updated Mar 12, 2025

Official repository for RoboDojo

Python 915 137 Updated Nov 16, 2026

NVIDIA Cosmos is an open platform of world models, datasets, and tools that enables developers to build Physical AI for robots, autonomous vehicles, smart infrastructure, and more.

12,382 963 Updated Nov 11, 2026

Cosmos-RL is a flexible and scalable Reinforcement Learning framework specialized for Physical AI applications.

Python 485 77 Updated Nov 14, 2026

Unlocking Lossless Speedups in LLMs via Discrete Diffusion

Python 110 15 Updated Oct 12, 2026

A lightweight inference engine supporting speculative speculative decoding (SSD).

Python 1,022 79 Updated May 10, 2026

Jev-compatible API endpoint based on open models (prefill-only)

Python 334 45 Updated Oct 1, 2026

RL-training knowledge-work agents on APEX-Agents data with SkyRL + Harbor

Python 225 17 Updated Sep 1, 2026

A unified library of SOTA model optimization techniques like quantization, distillation, pruning, neural architecture search, speculative decoding, etc. It compresses deep learning models for downs…

Python 5,612 813 Updated Nov 17, 2026

Memory-bounded compressed sparse attention via streaming top-k. Triton kernels for the DeepSeek-V4 lightning indexer. 32x regime extension on a single H200 | by RightNow https://www.rightnowai.co/

Python 27 5 Updated May 5, 2026

🚀 Ultra Recipe for Training Long-Horizon Search Agents - matching frontier AI's search capability with a 20B model + stateful harness

Python 1,024 148 Updated Jun 15, 2026

DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms

Python 7,315 702 Updated Jul 9, 2026

A collection of skills for AI financial analysis.

JavaScript 3,564 406 Updated Nov 4, 2026

Gemini Deep Research Agent CLI

Go 20 1 Updated Nov 16, 2026

Train transformer language models with reinforcement learning.

Python 19,746 3,150 Updated Nov 17, 2026

Ongoing research training transformer language models at scale, including: BERT & GPT-2

Python 2,268 366 Updated Aug 14, 2025

Why Low-Precision Transformer Training Fails: An Analysis on Flash Attention

Python 84 8 Updated Apr 7, 2026

Self-Questioning Language Models

Python 55 7 Updated Mar 30, 2026

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Python 20,543 2,198 Updated Oct 29, 2026

Machine Learning Engineering Open Book

Python 19,721 1,302 Updated Nov 12, 2026

Official PyTorch implementation for "Large Language Diffusion Models"

Python 4,021 292 Updated Jul 15, 2026

AlgoTune is a NeurIPS 2025 benchmark made up of 154 math, physics, and computer science problems. The goal is write code that solves each problem, and is faster than existing implementations.

Python 119 16 Updated Jun 24, 2026

Darwin Gödel Machine: Open-Ended Evolution of Self-Improving Agents

Python 2,517 465 Updated Aug 13, 2025

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Python 1,553 158 Updated Nov 9, 2026

A simulation framework for RLHF and alternatives. Develop your RLHF method without collecting human data.

Python 844 66 Updated Jul 1, 2024

[ICML 2024] Break the Sequential Dependency of LLM Inference Using Lookahead Decoding

Python 1,346 86 Updated Mar 6, 2025

Haxophone, an electronic musical instrument that resembles a saxophone

XSLT 674 21 Updated Feb 24, 2025

Training and serving large-scale neural networks with auto parallelization.

Python 3,177 354 Updated Dec 9, 2023

Shortcuts for Siri using ChatGPT API, supports continuous conversations, configure the API key & save chat records. 由 ChatGPT API 模型驱动的智能 Siri,支持连续对话,配置API key,配置系统prompt,保存聊天记录。

3,659 161 Updated Feb 27, 2026
Next