A web-based UI for running Claude Code as a persistent headless server. Submit prompts, manage projects, stream real-time output, and interact with Claude's tools — all from your browser.

A customized, secure, and efficient local LLM routing plugin

The code repository for "$V_{0.5}$: Generalist Value Model as a Prior for Sparse RL Rollouts"

[ICML 2026] ZwZ model family: SOTA fine-grained perception performace; ZoomBench: a new challenging perception benchmark

The code repository for "$V_0$: A Generalist Value Model for Any Policy at State Zero"

EvoCUA: Evolving Computer Use Agent

everything about llm & aigc

Witness the aha moment of VLM with less than $3.

✨✨Latest Advances on Multimodal Large Language Models

Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models (CVPR 2024 Highlight)

A framework for the evaluation of autoregressive code generation language models.

The code repository for "OmniEvalKit: A Modular, Lightweight Toolbox for Evaluating Large Language Model and its Omni-Extensions"

The code repository for "Wings: Learning Multimodal LLMs without Text-only Forgetting" [NeurIPS 2024]

Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)

Narrative movie understanding benchmark

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation (NeurIPS 2023)

The agent engineering platform.

ZhiJian: A Unifying and Rapidly Deployable Toolbox for Pre-trained Model Reuse

Gradient Boosted Neural Network

The code repository for "A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning" (ICLR'23) in PyTorch

Let us control diffusion models!

Awesome Compatible Learning

Ultralytics YOLO 🚀

OpenMMLab YOLO series toolbox and benchmark. Implemented RTMDet, RTMDet-Rotated,YOLOv5, YOLOv6, YOLOv7, YOLOv8,YOLOX, PPYOLOE, etc.

PyTorch implementation of popular datasets and models in remote sensing

Reverse engineered ChatGPT API

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image