Lists (2)
Stars
contains the list of papers of agent skills
GigaWorld-Policy: An Efficient Action-Centered World–Action Model
Edge server, user dataset for Edge Computing research
MemoryBear Equip AI with human-like memory capability
Drop-in pytest plugin for regression-testing AI agents — snapshot baselines, semantic comparison, mock LLMs
🤖🧠👾 Graph VLA with Control Barrier Function in Dual-Arm Robotics Manipulation
AI interview coach for behavioral questions with FAANG-caliber feedback
System Level Intelligent Router for Mixture-of-Models at Cloud, Data Center and Edge
RL-based Legged-Wheeled Robot locomotion sim-to-real based on NVIDIA Isaac Lab
news collection--classification--storage--push
The official code of [ICLR 2026] TFPI: Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners
Security guard for AI agents — blocks malicious skills, prevents data leaks, protects secrets. 24 detection rules, runtime action evaluation, trust registry.
Synthetic Data Generation Platform By DataArcTech
A lightweight, efficient auto key press tool for Windows.
A python platform for Data-Driven Multitask Optimization.
Official code of the paper "Rethinking Infrared Small Target Detection: A Foundation- Driven Efficient Paradigm"
[CVPR 2025 Highlight] Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis
Hybrid-tier key-value storage engine built on object storage & local SSDs. Engineered for batch-write efficiency and read optimization with ultra-low tail latency.
EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.
[ICRA2024] The official implementation of Robot Trajectron
正方教务系统自动抢课脚本：并发抢课、时间/教师筛选、换课、定时执行，内置图形界面。 | Auto course grabber with concurrent enrollment, filtering & scheduling.
A multi-agent AI trading system using LLMs to optimize strategies and adapt to market conditions in real-time.
High-Performance Perpetual Futures Exchange Matching Engine
This is the code for Visual Reasoning Sequential Attack, which is a method to jailbreak Multimodal Large Language Models Based on their visual reasoning capability
High Performance Redis-API Compatible Distributed Database with Persistency, Scalability, Full ACID Transactions, and Tiered S3 Storage Cost Efficiency
GigaBrain-0: A World Model-Powered Vision-Language-Action Model