Stars
Paper2Agent is a multi-agent AI system that automatically transforms research papers into interactive AI agents.
Paper2Code: Automating Code Generation from Scientific Papers in Machine Learning
Best practices & guides on how to write distributed pytorch training code
🧠 Train a 64M-parameter LLM from scratch in just 2h!
SkillsBench evaluates how well skills work and how effective agents are at using them.
Research Artifact Protocol for Rigorous and Trustworthy AI Scientists
AI agents running research on single-GPU nanochat training automatically
BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent (ACL 2026 Main)
A game theoretic approach to explain the output of any machine learning model.
Application and blog explaining my interpretations of In-run Data Shapley
Source Code of Arena Leaderboard Methodology
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Improving Your Model Ranking on Chatbot Arena by Vote Rigging (ICML 2025)
Unbiased Learning To Rank Algorithms (ULTRA)
This repository implements a fast method for auditing the robustness of LLM ranking systems, such as Chatbot Arena, to dropping very small number of preferences.
ChatArena (or Chat Arena) is a Multi-Agent Language Game Environments for LLMs. The goal is to develop communication and collaboration capabilities of AIs.
Connect AI models like Claude & GPT with robots using MCP and ROS.
Dense Passage Retriever - is a set of tools and models for open domain Q&A task.
A high-throughput and memory-efficient inference and serving engine for LLMs
A Python Toolkit for Explainable IR methods
Code for visualizing the loss landscape of neural nets
[ICCV 2021- Oral] Official PyTorch implementation for Generic Attention-model Explainability for Interpreting Bi-Modal and Encoder-Decoder Transformers, a novel method to visualize any Transformer-…
[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.
A large-scale face dataset for hair segmentation, hair recognition, and GANs for hair generation and editing.