Papersby Glyph

Notable data and AI papers

Papers627 Labs45

627 papers · 45 labs

From Local to Global: A Graph RAG Approach to Query-Focused Summarization research paper by Microsoft, 2024

Microsoft · Retrieval and data · Apr 24, 2024 · 2,561 citations · 7 upvotes

GraphRAG builds a knowledge graph of a document set so a model can answer questions about the whole collection.

By Darren Edge, Ha Trinh, Newman Cheng and 5 more · arXiv 2404.16130 · PDF

Summarised by hand from the abstract.

More from Microsoft

Agents and evaluationUnverifiedNov 2, 2026WebHarbor: Docking Real Websites for Evolving GUI Agent EnvironmentsWebHarbor provides realistic, containerized website environments for training and testing computer-using web agents across complex online tasks.

Microsoft28 upvotesRead →Agents and evaluationUnverifiedOct 19, 2026Agent World Model in the Wild: Computer-Use Agent Environment SynthesisThis pipeline creates controllable, open-source environments to safely train and test AI agents on complex, long-horizon computer-use tasks.

Microsoft69 upvotesRead →Training and scalingUnverifiedOct 16, 2026Self-Evolving Coding Agents via Harness-Policy OptimizationThis framework improves coding agents by recursively alternating between optimizing the agent's policy and the environment harness it uses to interact with code.

Microsoft48 upvotesRead →Multimodal and roboticsUnverifiedOct 13, 2026AesCode: Aesthetic Code Generation with Decoupled Cross-Modal RewardsThis paper introduces a method to improve code-based visual generation by using image-based aesthetic guidance and decoupled rewards to ensure quality and correctness.

Microsoft137 upvotesRead →Training and scalingUnverifiedOct 13, 2026APT: Feedback-Driven Agentic Post-Training for Text-to-Image GenerationThis paper introduces an automated post-training framework that uses a feedback loop of evaluation and diagnosis to improve text-to-image models.

Microsoft23 upvotesRead →Multimodal and roboticsUnverifiedOct 13, 2026LensErase: A Foundation Model for Erase AnythingThis paper introduces a foundation model designed for versatile image editing and object removal using mask-based inputs and efficient positional encoding.

Microsoft52 upvotesRead →Inference and efficiencyUnverifiedOct 13, 2026Simplifying and Improving On-Policy Distillation for Few-Step DiffusionThis paper introduces a simplified regression-based method for distilling diffusion models that improves generation speed without requiring complex training techniques.

Microsoft27 upvotesRead →Applied AIUnverifiedOct 5, 2026MiniCorp: The Last Mile of the AI Agent FirmMiniCorp is an office simulator that allows researchers to study how agents run companies and generate enterprise data for training.

Microsoft39 upvotesRead →

Retrieval and dataUnverifiedNov 9, 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language ModelBLOOM, a 176B-parameter open-access language model, achieves competitive performance on various benchmarks and is released publicly with a Responsible AI License.

Hugging Face3,165 citations41 upvotesRead →Retrieval and dataUnverifiedAug 13, 2025DINOv3DINOv3, a self-supervised learning model, achieves superior performance across various vision tasks by scaling datasets and models, addressing dense feature degradation, and enhancing flexibility with post-hoc strategies.

Meta1,932 citations320 upvotesRead →Retrieval and dataUnverifiedJan 8, 2026Qwen3-VL-Embedding and Qwen3-VL-Reranker: A Unified Framework for State-of-the-Art Multimodal Retrieval and RankingThe Qwen3-VL-Embedding and Qwen3-VL-Reranker models form an end-to-end multimodal search pipeline, leveraging multi-stage training and cross-attention mechanisms to achieve high-precision retrieval across diverse modalities.

Alibaba (Qwen)315 citations59 upvotesRead →Retrieval and dataUnverifiedMay 23, 2024DeepSeek-Prover: Advancing Theorem Proving in LLMs through Large-Scale Synthetic DataGenerating extensive Lean 4 proof data from mathematical competition problems improved DeepSeekMath 7B's theorem-proving capabilities over GPT-4 and other methods.

DeepSeek284 citations47 upvotesRead →Retrieval and dataFeb 9, 2024Aya Dataset: An Open-Access Collection for Multilingual Instruction TuningThe initiative builds a human-curated instruction-following dataset spanning 65 languages and creates the largest multilingual collection of instruction-following instances through templating and translating existing datasets across 114 languages, contributing datasets and platforms for participatory research.

Cohere253 citations57 upvotesRead →Retrieval and dataUnverifiedAug 15, 2024DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree SearchDeepSeek-Prover-V1.5 improves theorem proving by optimizing training and inference, utilizing reinforcement learning, and proposing RMaxTS for diverse proof paths, achieving state-of-the-art results on miniF2F and ProofNet benchmarks.

DeepSeek229 citations64 upvotesRead →

About this paper

Venue: arXiv.org
Citations: 2,561, 351 influential · Semantic Scholar
Upvotes: 7 · Hugging Face
Lab: Microsoft · on Companies · on Acquisitions · on Quarterly · on Paydays · on Releases · on TechConf

Changes

CitationsNov 9, 2026Influential citations rose from 346 to 351.

CitationsNov 9, 2026Citations rose from 2,488 to 2,561.

CitationsNov 2, 2026Influential citations rose from 323 to 346.

CitationsNov 2, 2026Citations rose from 2,328 to 2,488.

CitationsOct 12, 2026Influential citations rose from 314 to 323.

CitationsOct 12, 2026Citations rose from 2,267 to 2,328.

CitationsOct 5, 2026Influential citations rose from 307 to 314.

CitationsOct 5, 2026Citations rose from 2,214 to 2,267.

CitationsSep 28, 2026Influential citations rose from 304 to 307.

CitationsSep 28, 2026Citations rose from 2,198 to 2,214.

CitationsSep 25, 2026Influential citations rose from 302 to 304.

CitationsSep 25, 2026Citations rose from 2,191 to 2,198.

New paperSep 24, 2026Added to the list.