🟣 Pytorch interview questions and answers to help you prepare for your next machine learning and data science interview in 2025.

A Gym for Agentic LLMs

Code repository for the VLDB2023 paper "Zebra: When Temporal Graph Neural Networks Meet Temporal Personalized PageRank".

SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

Comprehensive Benchmark Dataset for Dynamic Text-Attributed Graphs

official repository for the TGTalker paper

Official Implementation for the paper "Discovering Knowledge Deficiencies of Language Models on Massive Knowledge Base"

ZeroGUI: Automating Online GUI Learning at Zero Human Cost

Tina: Tiny Reasoning Models via LoRA

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-…

🐉 Loong: Synthesize Long CoTs at Scale through Verifiers.

Simple RL training for reasoning

Code and dataset repo for ICML-2024 paper Graph-enhanced Large Language Models in Asynchronous Plan Reasoning.

Code and data for "Timo: Towards Better Temporal Reasoning for Language Models" (COLM 2024)

TRAM: Benchmarking Temporal Reasoning for Large Language Models (Findings of ACL 2024)

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

s1: Simple test-time scaling

Forecastbench Datasets, updated nightly

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]

Fully open reproduction of DeepSeek-R1

Sparsify transformers with SAEs and transcoders

[NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering