-
KAUST
- Thuwal, Saudi Arabia
- https://shaopengfu.me
Highlights
- Pro
Stars
Alipay DeepLink + JSBridge Security Research - 17 Verified Vulnerabilities | 支付宝DeepLink安全研究 | Full Report: innora.ai/zfb
这是一套专为 **懒猫微服 (LazyCat MicroServer)** 平台开发者打造的 AI 智能体技能包 (Agent Skills)。
this is the project Aegis. (Hopefully) The mile stone for AGI.
jordanzed13 / Projekt-Aegis
Forked from Totoro1121/Projekt-AegisThis is the Project Aegis Launcher. The simplify way for layman to use autonomous agentic AI.
Bash is all you need - A nano claude code–like 「agent harness」, built from 0 to 1
Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.
📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉
GLM-4.6V/4.5V/4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning
The official code for "Adversarially Pretrained Transformers May Be Universally Robust In-Context Learners" [S. Kumano et al., ICLR26].
A package of distributionally robust optimization (DRO) methods. Implemented via cvxpy and PyTorch
A PyTorch extension that facilitates decentralized data parallel training. [ICLR'25] From Promise to Practice: Realizing High-performance Decentralized Training.
No longer maintained, see pinned issues
ZO2 (Zeroth-Order Offloading): Full Parameter Fine-Tuning 175B LLMs with 18GB GPU Memory [COLM2025]
A Telegram bot to recommend arXiv papers
SASA: Semantics-Augmented Set Abstraction for Point-based 3D Object Detection
ArchLinuxARM for OrangePi 5 / 5B / 5 plus with vendor and mainline kernels to choose from