Lists (18)
Starred repositories
The world's first open-source multimodal creative assistant This is a substitute for Canva and Manus that prioritizes privacy and is usable locally.
Official implementation of "See Less, See Right: Bi-directional Perceptual Shaping For Multimodal Reasoning"
5
Updated Dec 29, 2025
AgentScope: Agent-Oriented Programming for Building LLM Applications
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]
A simple, decentralized mesh VPN with WireGuard support.
cuTile is a programming model for writing parallel kernels for NVIDIA GPUs
Bimanual Dexterous Teleoperation with Real-Time Retargeting using VisionPro
The best way to get AI coding agents to solve hard problems in complex codebases.
A curated list of state-of-the-art research in embodied AI, focusing on vision-language-action (VLA) models, vision-language navigation (VLN), and related multimodal learning approaches.
[CoRL 2025] ManiFlow: A General Robot Manipulation Policy via Consistency Flow Training
Sharp Monocular View Synthesis in Less Than a Second
Learning Deep Representations of Data Distributions
Build effective agents using Model Context Protocol and simple workflow patterns
Magnificent app which corrects your previous console command.
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
A framework for few-shot evaluation of language models.
Inspect: A framework for large language model evaluations
PyTorch Lightning Optical Flow models, scripts, and pretrained weights.
Open-source release accompanying Gao et al. 2025
Implementation of popular deep learning networks with TensorRT network definition API
Base on tensorrt version 8.2.4, compare inference speed for different tensorrt api.
ding113 / claude-code-hub
Forked from zsio/claude-code-hub一个现代化的 Claude Code & Codex API 代理服务，提供智能负载均衡、用户管理和使用统计功能。
[ICCV 2025] 💐 Dense Policy: Bidirectional Autoregressive Learning of Actions #DSP
Official implementation of "S²M²: Scalable Stereo Matching Model for Reliable Depth Estimation, ICCV 2025"
Paper Survey for Transformer-based SLAM