DemoGrasp: Universal Dexterous Grasping from a Single Demonstration

A Paper List for Humanoid Robot Learning.

verl: Volcano Engine Reinforcement Learning for LLMs

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

Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos

Being-VL-0.5: Unified Multimodal Understanding via Byte-Pair Visual Encoding

From Pixels to Tokens: Byte-Pair Encoding on Quantized Visual Modalities

Being-0: A Humanoid Robotic Agent with Vision-Language Models and Modular Skills

Load, build and visualize volatility analytics from Deribit.

Transforms complex documents like PDFs into LLM-ready markdown/JSON for your Agentic workflows.

新燕园人的私人班车助手（非官方）。

Vector (and Scalar) Quantization, in Pytorch

使用 cutlass 实现 flash-attention 精简版，具有教学意义

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

Awesome paper for multi-modal llm with grounding ability

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

Tackling Non-Stationarity in Reinforcement Learning via Causal-Origin Representation (ICML 2024)

AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback (NAACL 2024)

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

Benchmarking the Spectrum of Agent Capabilities

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

Locally run an Instruction-Tuned Chat-Style LLM

My Blog (https://www.zhangwp.com).