MiroThinker is a deep research agent optimized for complex research and prediction tasks. Our latest models, MiroThinker-1.7, achieves 74.0 and 75.3 on the BrowseComp and BrowseComp Zh, respectively.

[CVPR'26] LEAD: Minimizing Learner–Expert Asymmetry in End-to-End Driving

This repository collects papers for "A Survey on Knowledge Distillation of Large Language Models". We break down KD into Knowledge Elicitation and Distillation Algorithms, and explore the Skill & V…

Awesome In-Context RL: A curated list of In-Context Reinforcement Learning - - —

[Survey] A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems

A high-throughput and memory-efficient inference and serving engine for LLMs

[REALM25 @ ACL25] - "StateAct" Official Paper Repo (SOTA LLM Agent)

A benchmark for evaluating learning agents based on just language feedback

NVIDIA Linux open GPU kernel module source

Official PyTorch implementation for "Large Language Diffusion Models"

An open-source library for GPU-accelerated robot learning and sim-to-real transfer.

[ICLR 2023 Oral] The official implementation of SQL and EQL in "Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization"

OpenDILab Decision AI Engine. The Most Comprehensive Reinforcement Learning Framework B.P.

Machine Learning Interviews from FAANG, Snapchat, LinkedIn. I have offers from Snapchat, Coupang, Stitchfix etc. Blog: mlengineer.io.

《代码随想录》LeetCode 刷题攻略：200道经典题目刷题顺序，共60w字的详细图解，视频难点剖析，50余张思维导图，支持C++，Java，Python，Go，JavaScript等多语言版本，从此算法学习不再迷茫！🔥🔥 来看看，你会发现相见恨晚！🚀

List of Tech Company OAs. Save your time from finding them all over the internet.

Hopfield Networks is All You Need

Collections of robotics environments geared towards benchmarking multi-task and meta reinforcement learning

Continual reinforcement learning baselines: experiment specifications, implementation of existing methods, and common metrics. Easily extensible to new methods.

The Research Tree - A playground for research at the intersection of Continual, Reinforcement, and Self-Supervised Learning.

Author's PyTorch implementation of BCQ for continuous and discrete actions

A library for generative social simulation

Implementation of TWOSOME

official implementation for our paper Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning (NeurIPS 2023)

RAG (Retrieval Augmented Generation) Framework for building modular, open source applications for production by TrueFoundry