AtlasKV: A scalable, effective, and general way to augment LLMs with billion-scale knowledge graphs using very little GPU memory cost.

[EMNLP'25 main] This is the official repo for the paper, Can LLMs be Good Graph Judge for Knowledge Graph Construction?

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

Benchmarking Chat Assistants on Long-Term Interactive Memory (ICLR 2025)

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

LightMem: Lightweight and Efficient Memory-Augmented Generation

A relation-free graph constrcution method for efficient GraphRAG.

AnyEdit: Edit Any Knowledge Encoded in Language Models, ICML 2025

[NeurIPS'25] Neuro-symbolic Entity Alignment via Variational Inference

[ICML'23] RSC: Accelerate Graph Neural Networks Training via Randomized Sparse Computations

[NeurIPS 2025] OmniSVG is the first family of end-to-end multimodal SVG generators that leverage pre-trained Vision-Language Models (VLMs), capable of generating complex and detailed SVGs, from sim…

[Up-to-date] A curated list of resources on graph-empowered agents and agent-facilitated graph learning (Graphs Meet Agents).

Code repo for CLERC: A Legal Precedent Dataset for Case Retrieval and Retrieval-Augmented Analysis Generation (NAACL 2025)

Official repository of the MIRAGE benchmark

gpt-oss-120b and gpt-oss-20b are two open-weight language models by OpenAI

Official repository for paper "Automating Expert-Level Medical Reasoning Evaluation of Large Language Models"

Code for the MedRAG toolkit

NeurIPS‘24: Entity Alignment with Noisy Annotations from Large Language Models

Build resilient language agents as graphs.

User Profile-Based Long-Term Memory for AI Chatbot Applications.

Nano vLLM

Paper list for Efficient Reasoning.

A list of AI autonomous agents

GraphRAG-Bench, the official repo of comprehensive benchmark and dataset for evaluating GraphRAG models.

Python tool for converting files and office documents to Markdown.

[arXiv 2025] Materials Generation in the Era of Artificial Intelligence: A Comprehensive Survey