Stars
Code for the paper "Practical estimation of the optimal classification error with soft labels and calibration"
Official PyTorch implementation for "Large Language Diffusion Models"
Fully open reproduction of DeepSeek-R1
Expertise modeling for the OpenReview matching system
Mass-editing thousands of facts into a transformer memory (ICLR 2023)
Official repo for paper: "Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't"
Textbook on reinforcement learning from human feedback
Lightweight coding agent that runs in your terminal
An open protocol enabling communication and interoperability between opaque agentic applications.
Python SDK, Proxy Server (LLM Gateway) to call 100+ LLM APIs in OpenAI format - [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, Replicate, Groq]
Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator.
Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way.
[ICML 2024] Learning with Complementary Labels Revisited: The Selected-Completely-at-Random Setting Is More Practical
Code for the paper "Rethinking Importance Weighting for Deep Learning under Distribution Shift".
The software toolkits we developed for our paper in ACM CHI 2024.
Official Pytorch implementation of PULSE: Positive–Unlabelled Learning for audio Signal Enhancement (Best Paper Award at ICASSP 2023)
A powerful indexing & referencing system for theorems & equations in your Obsidian vault.
Code for the paper: On Symmetric Losses for Learning from Corrupted Labels
Cross-platform, customizable ML solutions for live and streaming media.