research

💡✨ Zotero, RAG, MCP, and deep research

Local text-driven editing of 3D shapes with Cascaded Score Distillation

🎓 Claude Code skill — AI prompt library for academic paper writing, polishing, reviewing, translating and submitting to SCI/IEEE/Nature/TRO journals

Research framework that quantifies how steganographic obfuscation of embeddings defeats off-the-shelf statistical detection in RAG pipelines, paired with the VectorPin cryptographic-provenance defense

MCP Deep Research Server using Gemini creating a Research AI Agent

Research experiments exploring uncommon quant techniques.

Code repository dedicated to experimenting and research with tiny reasoning language model

Prove My Point is a web-based AI assistant designed to help users back their arguments with credible, research-backed information. It allows users to ask complex or controversial questions and instantly receive answers supported by real research papers from academic sources like arXiv, PubMed, and Semantic Scholar.

Practical guide and toolkit for physicists and mathematicians using Claude Code — built from months on a real research project

329 agent skills (Cursor, Claude Code & Codex), 5,380 OpenClaw skills, 201 ML notebooks, 9 textbooks, 82 research papers, 85 curated projects, 18 industry reports for PMs, Designers & Developers.

Distributed Networks Institute

A clean, single-file PyTorch implementation of Attention Residuals (Kimi Team, MoonshotAI, 2026), integrated with Grouped Query Attention (GQA), SwiGLU feed-forward networks, and Rotary Position Embeddings (RoPE).

让AI Agent 做真正会思考，有判断的深度调研，而不是会摆信息的汇总报告。一个即插即用的 skill 文件。

VAAS is an inference-first, research-driven library for image integrity analysis. It integrates Vision Transformer Attention Mechanisms with patch-level self-consistency analysis to enable fine-grained localization and detection of visual inconsistencies across diverse image analysis tasks.

A reasoning assistant for your STEM education

Fast dataset format and loader

Implementation of TSDS: Data Selection for Task-Specific Model Finetuning. An optimal-transport framework for selecting domain-specific and task-specific training data to improve LLM finetuning and instruction tuning.

Unsupervised specificity-guided optimization of Image Captioning models to encourage meaningful diversity in the generated captions. Code for the paper Generating Diverse and Meaningful Captions: Unsupervised Specificity Optimization for Image Captioning (Lindh et al., 2018).

Multimodal document QA: vision + retrieval over PDFs (LLaVA + LlamaIndex)

Tracking exactly what happens to the internal "circuitry" (induction heads) of a 2-layer attention-only Transformer when forced to undergo domain adaptation from prose to structured Python code.