🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

[COLM 2025] Official implementation of μKE - edit LLM knowledge while preserving memory dependencies via Matryoshka-style objectives.

Epistemic Context Learning: Building Trust the Right Way in LLM-Based Multi-Agent Systems

Towards a Mechanistic Understanding of Large Reasoning Models: A Survey of Training, Inference, and Failures

Papers of Neural Topic Models (NTMs)

[ACL 2025] RuleArena: A Benchmark for Rule-Guided Reasoning with LLMs in Real-World Scenarios

[ECCV’24 Main] MAMA: A Meta-optimized Angular Margin Contrastive Framework for Video-Language Representation Learning

Unlearning backdoor

Detecting Harmful Memes with Decoupled Understanding and Guided CoT Reasoning

A Fast, Adaptive, Stable, and Transferable Topic Model (NeurIPS 2024)

A comrephensive collection of learning from rewards in the post-training and test-time scaling of LLMs, with a focus on both reward models and learning strategies across training, inference, and po…

[ICML 2026] Official resources of "Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning".

[NeurIPS 2025] Official resources of "HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation".

[ICML 2025] Official resources of "KBQA-o1: Agentic Knowledge Base Question Answering with Monte Carlo Tree Search".

Comparison of two cutting-edge dynamic topic models solving consumer complaints classification exercise

Code for "Can Group Decision-Making Mitigates Social Bias in Large Language Models?"

This repository contains code and models for the paper: Semantic Graphs for Generating Deep Questions (ACL 2020).

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

This repository contains the source code for COrAL, an Order-Agnostic Language Modeling framework for Efficient Iterative Refinement.

Official Implementation of EMNLP 2024 Are LLMs Good Zero-Shot Fallacy Classifiers?

[EMNLP’24 Main] Encoding and Controlling Global Semantics for Long-form Video Question Answering

[ACL’24 Findings] Video-Language Understanding: A Survey from Model Architecture, Model Training, and Data Perspectives

EMNLP2024 - AKEW: Assessing Knowledge Editing in the Wild

Code and data for "Lost in the Middle: How Language Models Use Long Contexts"

Aligned Neural Topic Model (ANTM) for Exploring Evolving Topics: a dynamic neural topic model that uses document embeddings (data2vec) to compute clusters of semantically similar documents at diffe…