Lists (4)
Stars
OpenTinker is an RL-as-a-Service infrastructure for foundation models
A dynamic forecasting benchmark for LLMs
Official implementation of "Continuous Autoregressive Language Models"
[EMNLP 2025] DiagramEval: Evaluating LLM-Generated Diagrams via Graphs
LightMem: Lightweight and Efficient Memory-Augmented Generation
A Practitioner's Guide to M(eow)ti Turn Agentic ReinfOrcement learning
This is the github repo for our LM4SCI@COLM25 paper "The Ram\'{o}n Llull's Thinking Machine for Automated Ideation".
🌎💪 BrowserGym, a Gym environment for web task automation
A lightweight platform for realistic social simulations
Materials for course on language model programming (LMProgramming)
Sotopia-RL: Reward Design for Social Intelligence
Course resources for the ESSLLI 2024 class on language model programming
Time-R1: Framework and resources for endowing LLMs with comprehensive temporal reasoning (understanding, prediction, creative generation) using a novel three-stage RL curriculum. Includes the Time-…
[EMNLP 2025 Demo] TinyScientist: A Lightweight Framework for Building Research Agents
A Python package that evaluates Large Language Models (LLMs) through a novel tree-based approach
[ICLR 2025] DeFT: Decoding with Flash Tree-attention for Efficient Tree-structured LLM Inference
A platform to develop CTM-motivated AI architecture.
"MiniRAG: Making RAG Simpler with Small and Open-Sourced Language Models"
Collection of links and other miscellaneous data about Polymarket
[ACL'25 Main] Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs