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. Monocular Depth Estimation from a Single Image: Progress and Opportunities taaft Monocular depth estimation has long stood as a fundamental challenge in computer vision, enabling a… 2026-09-01 published
  2. Monolith: Real Time Recommendation System With Collisionless Embedding Table ByteDance Building a scalable and real-time recommendation system is vital for many businesses driven by time… 2022-09-16 published
  3. Moral Competence Before Moral Content: Why LLM Agents Lack the Prerequisites for Coherent Alignment taaft AI alignment requires AI systems to adhere to human norms, values, or intentions. Under value plura… 2026-09-04 published
  4. More Capable, Less Faithful: A Multilingual Analysis of Mathematical (Un)Solvability Detection in LLMs taaft Solvability detection is one of the most challenging aspects of mathematical reasoning for Large La… 2026-08-31 published
  5. More, better or different? Trade-offs between group size and competence development in jury theorems taaft In many circumstances there is a trade off between the number of voters and the time they can be gi… 2024-04-15 published
  6. Morphology signal in whole slide image foundation models can automatically triage slides taaft Patient exams in the cancer diagnosis and staging process typically generate several whole slide im… 2026-09-02 published
  7. MOSAIC: Multi-Objective Slice-Aware Iterative Curation for Alignment taaft We study how to allocate a fixed supervised fine-tuning budget when three objectives must be balanc… 2026-03-19 published
  8. Motion Transfer Across Subjects at Inference StepFun Motion4Motion, also called M4M, is a training free framework for transferring motion from a source… StepFun
  9. Motion-o: Trajectory-Grounded Video Reasoning taaft Recent video reasoning models increasingly produce spatio-temporal evidence chains that localize ob… 2026-03-19 published
  10. Motion-Saliency Complementary Masked Modeling for Point Cloud Video Understanding taaft Point cloud video representation learning is crucial for 3D dynamic scene understanding. In this pa… 2026-08-31 published
  11. MotionSync: Non-Causal Refinement of Causal Tracker for Label-Efficient 3D Perception taaft Three-dimensional box-and-track annotation is the cost bottleneck in autonomous-driving data engine… 2026-08-30 published
  12. Motus2: A Self-Evolving General World Model for Dexterous Manipulation taaft General embodied agents should perceive, predict, act, evaluate, and improve within a unified syste… 2026-08-31 published
  13. Moving Beyond More Views: Redundancy-Aware Ego-Exo Fusion for Proficiency Estimation taaft EgoExo proficiency estimation aims to assess action quality by integrating fine-grained motion cues… 2026-08-26 published
  14. mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video Alibaba Recent years have witnessed a big convergence of language, vision, and multi-modal pretraining. In… 2023-02-01 published
  15. mPLUG-Owl : Modularization Empowers Large Language Models with Multimodality Alibaba Large language models (LLMs) have demonstrated impressive zero-shot abilities on a variety of open-… 2023-04-27 published
  16. mPLUG-Owl2: Revolutionizing Multi-modal Large Language Model with Modality Collaboration Alibaba Multi-modal Large Language Models (MLLMs) have demonstrated impressive instruction abilities across… 2023-11-07 published
  17. mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections Alibaba Large-scale pretrained foundation models have been an emerging paradigm for building artificial int… 2022-05-24 published
  18. MRI-based Deep Radiomic Phenotyping of Neuromuscular Disorders: A Topology-driven Characterization taaft Quantitative assessment of muscle MRI is crucial for monitoring neuromuscular disorders (NMD). This… 2026-08-25 published
  19. mRNAutilus: Multi-Objective-Guided Discrete Generation of mRNA with Optimized Therapeutic Properties taaft Therapeutic mRNA design requires coordinating multiple interacting sequence features across the ful… 2026-05-29 published
  20. MS-CustomNet: Controllable Multi-Subject Customization with Hierarchical Relational Semantics taaft Diffusion-based text-to-image generation has advanced significantly, yet customizing scenes with mu… 2026-03-22 published
  21. MTEB: Massive Text Embedding Benchmark taaft Text embeddings are commonly evaluated on a small set of datasets from a single task not covering t… 2022-10-13 published
  22. MTVQA: Benchmarking Multilingual Text-Centric Visual Question Answering taaft Text-Centric Visual Question Answering (TEC-VQA) in its proper format not only facilitates human-ma… 2024-05-20 published
  23. MUDDLE: Measuring Understanding of Documents under Distractor and Length Effects taaft Document question-answering systems increasingly answer questions over collections of retrieved doc… 2026-08-30 published
  24. Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training taaft Sound event localization and detection (SELD) involves identifying the direction-of-arrival (DOA) a… 2021-10-14 published
  25. Multi-Agent Reasoning with Consistency Verification Improves Uncertainty Calibration in Medical MCQA taaft Miscalibrated confidence scores are a practical obstacle to deploying AI in clinical settings. A mo… 2026-03-25 published
  26. Multi-Granularity Context-Enhanced RAG over Multimodal Knowledge Graphs taaft Retrieval-augmented generation (RAG) is widely used to mitigate hallucination issues in large langu… 2026-08-26 published
  27. Multi-LLM Query Optimization taaft Deploying multiple large language models (LLMs) in parallel to classify an unknown ground-truth lab… 2026-03-24 published
  28. Multi-News+: Cost-efficient Dataset Cleansing via LLM-based Data Annotation taaft The quality of the dataset is crucial for ensuring optimal performance and reliability of downstrea… 2024-04-15 published
  29. Multi-output Gaussian process prediction of physical fields under linear equality constraints taaft We address the simultaneous prediction of multiple high-dimensional physical fields governed by lin… 2026-08-26 published
  30. Multi-Person Human Motion Forecasting in Complex Scenes taaft Accurately forecasting the movement of people in complex scenes requires reasoning over the past an… 2026-08-27 published
  31. Multi-Perspective LLM Annotations for Valid Analyses in Subjective Tasks taaft Large language models are increasingly used to annotate texts, but their outputs reflect some human… 2026-03-22 published
  32. Multi-step Proximal Policy Improvement in Offline Reinforcement Learning taaft Offline reinforcement learning (RL) must reconcile two competing requirements: policy updates shoul… 2026-09-03 published
  33. Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe taaft Data-sovereignty regulations increasingly require public institutions to deploy open-source, on-pre… 2026-09-04 published
  34. Multi-Tool Image Editing Attribution in Facial Forgery taaft As generative AI tools become increasingly powerful and easy to use, people can easily edit portrai… 2026-09-02 published
  35. Multi-View Reflective Surface Inspection via Semantic-Saliency Cross-Verification taaft Reflective smartphone cover glass is challenging to inspect from a single fixed viewpoint because d… 2026-08-31 published
  36. Multi2AV-Safety: Benchmarking Safety in Multimodal-to-Audio-Video Generation taaft Audio-video generation is rapidly moving from prompt-driven synthesis toward multimodal conditionin… 2026-08-27 published