Blog Promote Sign in Sign up

Catalogs

Papers

3,241 in the directory.

Browse AI research papers and methods. Search paper profiles, read recorded summaries and follow source links for the full research.

A–Z Recently synced
Explore other catalogs
Models Datasets Demos Devices Robots MCPs Papers Investors Fundraises Repositories News
How to choose papers

Use the summary to find relevant work, then read the original paper. Compare the method, evaluation setting, baselines and limitations with your own problem. Check whether code and datasets are available; a reported benchmark result may not transfer to your use case.

Understand our sources and data limits

  1. ManGo: Manga Active Narrative Grounding Optimization taaft Manga visual question answering requires models to answer questions over panel-based visual narrati… 2026-08-30 published
  2. Manifold Preserving Guided Diffusion taaft Despite the recent advancements, conditional image generation still faces challenges of cost, gener… 2023-11-28 published
  3. Manifold-Aware General Coded Computing for Straggler-Resilient Distributed Computing taaft Existing coded-computing designs do not explicitly exploit the intrinsic structure of the input dat… 2026-09-01 published
  4. Manifold4D: Denoising on Point Cloud Rendered Manifolds for Video Re-shooting taaft Video re-shooting re-renders a monocular video of a dynamic scene along a user-specified camera tra… 2026-08-28 published
  5. MAOL: Morphology-Aware Ordinal Learning for Fine-Grained Industrial Defect Severity Grading taaft Fine-grained defect severity grading is essential for industrial inspection, yet remains challengin… 2026-09-02 published
  6. MAP: A Benchmark on Multimodal Accessibility Planning for Real World Places taaft We introduce MAP, the first benchmark to evaluate multimodal AI systems as assistants for users wit… 2026-08-28 published
  7. MariSat: A Maritime Dataset for Instance Segmentation of Objects in Satellite and Aerial Images taaft Automated maritime surveillance from satellite and aerial imagery requires large, precisely annotat… 2026-08-30 published
  8. Markerless Pose Estimation for Resistance Training Technique Assessment taaft Resistance training can be a high risk activity, and safe form is essential to avoiding injury. Lab… 2026-08-25 published
  9. Markets, Not Planners: Decentralized Orchestration of LLM Agents with Private Information taaft As LLM agents proliferate, built by different parties and with different capabilities and costs, or… 2026-08-24 published
  10. MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding taaft Multimodal pre-training with text, layout, and image has made significant progress for Visually Ric… 2021-10-16 published
  11. MARS: What Retrieval Signals Are Hidden in Multimodal Large Language Models for Text-Video Retrieval? taaft Text-video retrieval requires representations that can distinguish videos with similar scenes, acti… 2026-09-02 published
  12. Mask R-CNN Meta Platforms We present a conceptually simple, flexible, and general framework for object instance segmentation.… 2017-03-20 published
  13. MASkills: Continual Skills Optimization for Multi-Agent LLM Systems taaft LLM-based multi-agent systems have shown strong performance on complex tasks, yet continual improve… 2026-09-02 published
  14. MASQ: Mask-Aware Spatiotemporal Quantization for Unsupervised Skeleton Action Segmentation taaft Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human… 2026-08-30 published
  15. MaST: Motion-aware Sparse Pipeline for Lightweight Object Tracking taaft Transformer-based object trackers are renowned for their strong performance, yet dense token proces… 2026-08-25 published
  16. MasterControl Seventeen Every Time taaft We study a governed approach to enterprise analytics: a language model interprets the question, whi… 2026-09-02 published
  17. Mastering Diverse Domains through World Models taaft Developing a general algorithm that learns to solve tasks across a wide range of applications has b… 2023-01-10 published
  18. Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs taaft Diffusion models have exhibit exceptional performance in text-to-image generation and editing. Howe… 2024-01-22 published
  19. Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models taaft Underlying data distributions of natural language, programming code, and mathematical symbols vary… 2024-03-13 published
  20. MathAdv: What Theorem Provers Know, Reason, Formalize, and Generalize taaft Formal theorem proving enables machine-verifiable evaluation of mathematical reasoning, yet existin… 2026-08-26 published
  21. MathForm: Scaling Mathematical Autoformalization with Knowledge Retrieval and Verification-Guided Refinement taaft Autoformalization is commonly framed as translating natural-language mathematical statements into m… 2026-08-14 published
  22. Matrix-Game 3.5: Enhancing Real-Time Streaming Interactive World Models with Patch Memory taaft Interactive world models extend video generation from offline clip synthesis toward persistent simu… 2026-08-30 published
  23. MC-CXR: A Multi-Context Chest X-ray Benchmark for Context-Induced Disruption in Vision-Language Models taaft Vision-language models (VLMs) are increasingly used in clinical pipelines where a chest X-ray is in… 2026-08-25 published
  24. MCC-KD: Multi-CoT Consistent Knowledge Distillation taaft Large language models (LLMs) have showcased remarkable capabilities in complex reasoning through ch… 2023-10-23 published
  25. MCLR: Improving Conditional Modeling in Visual Generative Models via Inter-Class Likelihood-Ratio Maximization and Establishing the Equivalence between Classifier-Free Guidance and Alignment Objectives taaft Diffusion models achieve strong performance in generative modeling, but their success often relies… 2026-03-23 published
  26. MCPO: Modality-Contrastive Preference Optimization for Multimodal Chain-of-Thought Compression taaft Recently, multimodal large-scale reasoning models have demonstrated remarkable capabilities in solv… 2026-09-04 published
  27. ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking taaft Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual… 2026-03-21 published
  28. MeanField Surrogate Modeling for Scalable Runtime Scheduling of Concurrent Heterogeneous AI Inference on Shared GPUs taaft Deploying heterogeneous AI models concurrently on a shared GPU introduces resource contention that… 2026-09-02 published
  29. Measured Sliders: Learning Continuous Controls from Differentiable Image Measurements taaft Continuous sliders are useful only when coefficient changes produce predictable image changes. Yet… 2026-09-04 published
  30. Measurement-Driven Sub-Network Selection for On-Premise Retrieval-Augmented Factory Agents taaft On-premise assistants can give factory workers conversational access to machine documentation, but… 2026-09-02 published
  31. Measuring AI Accountability Through Argumentation Analysis: Can Model Reasoning Withstand Scrutiny? taaft AI oversight methods rely on ground truth for validation, but what constitutes appropriate AI behav… 2026-09-04 published
  32. Measuring Persona Drift in Long-Horizon Agent Simulations MatrAIx Tests whether LLM agents (Qwen3-32B, Claude Haiku) maintain assigned identities/values over extende… MatrAIx
  33. Measuring the Novelty of Biomedical Papers Using the Latent Distances between Knowledge Units taaft Measuring the novelty of scientific papers is a central concern in research evaluation and scientom… 2026-09-04 published
  34. Mechanism Design for Alignment and Control taaft We develop a framework for mechanism design with AI agents whose alignment (preferences) and capabi… 2026-09-01 published
  35. MedCache: Efficient and Temporally Valid Memory for Longitudinal Clinical Agents taaft Longitudinal clinical agents must maintain an evolving patient state from evidence distributed acro… 2026-08-30 published
  36. MedFlow: Class-Aware Multi-Scale Generation for Medical Time-Series Synthesis taaft Synthetic medical time-series generation can alleviate data scarcity and support the development of… 2026-09-04 published