Starred repositories
An organized dissertation/thesis Latex template for UC San Diego (UCSD) students.
A curated list of papers and selected technical blogs on Loop Models.
A diagnostic tool and a guideline for advancing next-generation world models capable of robust understanding, forecasting, and purposeful action.
A unified framework for vision-language environments with Gymnasium-compatible interface
Create beautiful slides on the web using a coding agent's frontend skills
Minimalistic 4D-parallelism distributed training framework for education purpose
H-Net: Hierarchical Network with Dynamic Chunking
[ICLR 2026] An official implementation of "SIM-CoT: Supervised Implicit Chain-of-Thought"
[ACL 2026 Oral] Official Implementation of the paper "Deriving Character Logic from Storyline as Codified Decision Trees"
Life is too boring to have one personality, so let's have two
An agent framework for building and evaluating general digital agents.
An Open-Source Large-Scale Reinforcement Learning Project for Search Agents
Leantime is a goals focused project management system for non-project managers. Building with ADHD, Autism, and dyslexia in mind.
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
AgentOccam: A Simple Yet Strong Baseline for LLM-Based Web Agents
MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering
Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient
Building Open LLM Web Agents with Self-Evolving Online Curriculum RL
A benchmark for LLMs on complicated tasks in the terminal
Koishi's Day 2025 Paper (NeurIPS 2025): "Codifying Character Logic in Role-Playing"
coredumpy saves your crash site for post-mortem debugging
The RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
Search-R1: An Efficient, Scalable RL Training Framework for Reasoning & Search Engine Calling interleaved LLM based on veRL