Highlights
- Pro
Lists (1)
Stars
Denoising Diffusion Probabilistic Models
PubMedQA: A Dataset for Biomedical Research Question Answering
Leaderboard Comparing LLM Performance at Producing Hallucinations when Summarizing Short Documents
RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.
MAGI-1: Autoregressive Video Generation at Scale
⚡FlashRAG: A Python Toolkit for Efficient RAG Research (WWW2025 Resource)
ReCall: Learning to Reason with Tool Call for LLMs via Reinforcement Learning
A general framework for bridging LLMs and recommendation systems via reinforcement learning. https://arxiv.org/pdf/2503.24289
An Open-source RL System from ByteDance Seed and Tsinghua AIR
A high-throughput and memory-efficient inference and serving engine for LLMs
A specialized LLM for study search, study screening, and data extraction from medical literature.
Pyserini is a Python toolkit for reproducible information retrieval research with sparse and dense representations.
ColBERT: state-of-the-art neural search (SIGIR'20, TACL'21, NeurIPS'21, NAACL'22, CIKM'22, ACL'23, EMNLP'23)
A large-scale information-rich web dataset, featuring millions of real clicked query-document labels
A Python model checking package
"Your Fully-Automated Personal AI Assistant, and Open-Source & Cost-Efficient Alternative to OpenAI's Deep Research"
A lightweight data processing framework built on DuckDB and 3FS.
DeepRetrieval - Hacking 🔥Real Search Engines and Retrievers with LLM via RL
verl: Volcano Engine Reinforcement Learning for LLMs
RAS: Retrieval-And-Structuring for Knowledge-Intensive LLM Generation
Bringing BERT into modernity via both architecture changes and scaling
Contriever: Unsupervised Dense Information Retrieval with Contrastive Learning
Code repository for supporting the paper "Atlas Few-shot Learning with Retrieval Augmented Language Models",(https//arxiv.org/abs/2208.03299)
Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question ans…