Papers

An ACL paper's official code for a logical data-poisoning attack on GraphRAG systems, which swaps entities of the same type to corrupt a corpus's implicit reasoning graph while keeping the poisoned text locally plausible.

• Security
• Papers

A PyTorch implementation, from an ACL paper, of knowledge-graph retrieval-augmented generation for LLM-based recommendation, evaluated on MovieLens and Amazon Book datasets.

• RAG
• Papers

A four-stage multi-agent pipeline, presented at AAAI 2026, that classifies lung adenocarcinoma nodules from CT images and reports through nodule detection, sizing, report generation and a multi-agent clinical debate.

• Models
• Papers

A two-stage benchmark comparing more than twenty optimizers for large language model pre-training at scale, first screening them broadly on a shared architecture and then testing the strongest ones for generalization across several model architectures.

• Models
• Papers

Research code and the WildGUI dataset for a pipeline that extracts grounded GUI interaction trajectories from unlabeled internet videos to pretrain generalized graphical interface agents.

• Agent frameworks
• Papers

A research framework that evolves a single meta-skill file describing how an LLM should design and run a multi-agent system, refining it over rounds using contrastive reflection on past attempts.

• Agent skills
• Papers

A reinforcement-learning framework for repository-level code completion that trains a retriever to select reference code snippets that actually help generation, rather than merely similar ones.

• Models
• Papers

A Python implementation of a published method for simulating physical particle dynamics with a transformer, aimed at building a unified model of how particles move under Lagrangian dynamics.

• Libraries
• Papers

The source code for a paper on a token-efficient, agentic retrieval-augmented generation framework that compresses both retrieved content and reasoning steps to answer complex queries with fewer tokens and faster reasoning.

• RAG
• Papers

The official code for an ECCV 2026 paper that generates realistic human motion sequences from text descriptions by combining retrieval of similar existing motions with a masked transformer generation model.

• Generative media
• Papers

The official implementation of a paper on retrieval-augmented generation that decides when to retrieve based on statistics from the model's pre-training corpus, rather than relying on the model's own, often miscalibrated, internal confidence signals.

• RAG
• Papers

A Python implementation of a published method that learns the Kalman gain of a Kalman filter directly from data using a transformer, rather than computing it from a hand-derived model of the system.

• Libraries
• Papers

The official research code for an ECCV 2026 paper on quantizing every part of a multi-agent cooperative perception system for autonomous vehicles, aimed at cutting inference and communication cost with minimal loss of perception accuracy.

• Models
• Papers

A PyTorch implementation of a published method for image classification using multi-agent reinforcement learning, where several agents move across an image and their policy is trained to classify it.

• Models
• Papers

A research implementation of retrieval-augmented generation for relation extraction, providing an end-to-end pipeline that runs with and without retrieval across several standard relation-extraction datasets.

• RAG
• Papers

An unofficial, paper-aligned implementation of DeepSeek's Engram architecture that injects a large, sparsely retrieved conditional memory into a transformer model without increasing inference compute.

• Models
• Papers

An open, developer-friendly implementation of a research paper's approach to turning timestamped banking event histories, such as transactions and app sessions, into embeddings for fraud detection, anti-money-laundering graph analysis, and credit scoring.

• Papers

The reference implementation of a research paper on collaborative self-evolution for LLM-based multi-agent systems, where a team of agents reflects together after each task at the level of individual agents, their interactions, and the team's own organization.

• Agent frameworks
• Papers

A learnable memory framework for LLM-powered multi-agent systems, accepted to EMNLP 2026, that trains a memory composer to distill an experience bank of raw interaction trajectories into compact, role-aware latent memories for each agent.

• Agent memory
• Papers

An independent research branch of llama.cpp implementing DualDeadline, a component-staged expert-prefetching technique for offloaded mixture-of-experts inference, letting a GPU claim only router-selected expert tensor slices while routing and outputs stay exact.

• Inference
• Papers

A research framework, released with its NeurIPS 2026 paper, that pairs a vision-language reasoning model with a JEPA-based world model, so high-level semantic reasoning guides low-level physical prediction for embodied, robotic tasks.

• Models
• Papers

A minimal keyword-based tool that queries arXiv, OpenAlex and PubMed for new academic papers, deduplicates results across sources, and can translate and summarize them with a language model.

• Papers

An evaluation framework and reference implementation for a multi-agent, graph-based retrieval-augmented generation method aimed at legal judgment prediction.

• RAG
• Papers

An open, AI-reviewed marketplace where researchers share the plotting scripts behind their published figures, so others can find a template, its rendered output and its source paper side by side.

• Papers