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. ARIA - An Agentic Framework for Autonomous Testing of Infotainment Systems taaft Automotive infotainment validation still relies on manual testing, slow, costly, and incompatible w… 2026-09-04 published
  2. ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning taaft Training open-ended agents via reinforcement learning (RL) is hindered by the lack of verifiable go… 2026-09-01 published
  3. Arkios: An Open Bilingual English-Nepali Language Model Trained From Scratch, with a Devanagari-Aware Tokenizer taaft We present Arkios, a 1.04B-parameter dense transformer pretrained from scratch on 150B tokens of bi… 2026-08-30 published
  4. ARMOR: Manifold-Oriented Training for Adversarially Robust Aerial Object Detection under Data Scarcity taaft Aerial object detection is increasingly deployed in real-world applications, but models remain vuln… 2026-08-30 published
  5. ArtHOI: Taming Foundation Models for Monocular 4D Reconstruction of Hand-Articulated-Object Interactions taaft Existing hand-object interactions (HOI) methods are largely limited to rigid objects, while 4D reco… 2026-03-26 published
  6. Artificial Intelligence for Energy Optimization in Data Centers taaft Data centers are increasingly optimized by artificial intelligence and, at the same time, increasin… 2026-09-03 published
  7. Artificial Intelligence in Equity and Crypto Markets: Progress, Profitability Evidence, and the Limits of Automated Investing taaft Artificial intelligence (AI) now supports investment workflows from data and prediction through res… 2026-09-04 published
  8. Artificial Rosetta Stone: Constrained Maximum A Posteriori (MAP) Reconstruction of Symbolic Raga Sequences via Order-k Markov Models taaft Reconstructing a damaged musical fragment is an inverse problem: the observed sequence contains par… 2026-09-01 published
  9. ASCII Attack: Recontextualising Harmful Requests as Artistic Critique in Large Language Models taaft Safety alignment trains large language models to refuse harmful requests stated plainly, but that t… 2026-09-02 published
  10. Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization taaft Large language models (LLMs) are increasingly used to formulate optimization models from natural-la… 2026-09-04 published
  11. Ask, Don't Judge: Binary Questions for Interpretable LLM Evaluation and Self-Improvement taaft Evaluating LLM outputs remains a major bottleneck in NLP: human evaluation is expensive and slow, l… 2026-06-25 published
  12. ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents taaft Clarification-seeking behavior is widely regarded as a desirable property of LLM agents, enabling t… 2026-05-17 published
  13. Aspire: Can Models Self-Evolve from Vague Goals? taaft Many important forms of human learning begin with a vague goal, such as "become a better physicist"… 2026-08-31 published
  14. Assessing Alignment and Stability of Feature Importance Explanations via Weight of Evidence taaft Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions,… 2026-08-31 published
  15. Assessing the Safety of a New Clinical Decision Support System for a National Helpline Infermedica A safety evaluation of a new clinical decision support system for nurses on Australia's national co… Infermedica
  16. Associative Memory using Attribute-Specific Neuron Groups-2: Learning and Sequential Associative Recall between Cue Neurons for different Cue Balls taaft This paper introduces a neural network model that learns multiple attributes as images and performs… 2026-03-26 published
  17. Asymmetric Cross-Modal Fine-Grained Visual Categorization: ACF-Net and the BirdPro Benchmark taaft Audio-visual cross-modal Fine-Grained Visual Categorization (FGVC) aims to identify fine-grained ca… 2026-08-26 published
  18. Asymmetric Paired-Annotation Learning for Multi-Structure ULF Pediatric Brain MRI Segmentation taaft Portable ultra-low-field (ULF) MRI can expand access to pediatric neuroimaging, but segmentation at… 2026-09-02 published
  19. AsymSpec: Context-Asymmetric Speculative Decoding for Agentic LLMs taaft Agentic LLM pipelines face escalating inference costs as context accumulates across retrieval, tool… 2026-08-26 published
  20. Asynchronous Cooperative Online Learning for Multi-Robot Control under Computational Delays taaft Ensuring the safe operation of multi-agent systems (MASs) under uncertain environments is crucial f… 2026-08-30 published
  21. ATGS: Anchored Temporal Gaussian Splatting for Long Volumetric Video Representation taaft Volumetric video enables immersive free viewpoint rendering of dynamic real world scenes, yet exist… 2026-08-31 published
  22. Athena: Vulnerability-Affected Library Identification via Knowledge Graph Completion taaft A single vulnerability in a widely used library can cascade through millions of dependent applicati… 2026-09-01 published
  23. ATLAS: Dual-Horizon Diagnostic Evaluation for Industrial Tool-Use Agents taaft Large language model (LLM) agents are increasingly deployed in user-facing services that require it… 2026-08-31 published
  24. AtlasNLP: A Country-Aware Atlas of Dataset Representation in NLP taaft Understanding which countries are represented in NLP datasets is essential for identifying gaps, ta… 2026-08-31 published
  25. Attention Is All You Need Google Research The dominant sequence transduction models are based on complex recurrent or convolutional neural ne… 2017-06-12 published
  26. Attention-guided super-resolution of 4D flow MRI in carotid arteries taaft Four-dimensional (4D) flow magnetic resonance imaging (MRI) is a powerful non-invasive technique fo… 2026-09-04 published
  27. Audio-Driven Adversarial Defense for 3D Talking Face Generation with totally Visual Fidelity Preservation taaft The rapid development of generative portrait models has raised growing concerns about privacy leaka… 2026-08-31 published
  28. AudioLM: A Language Modeling Approach to Audio Generation Google Research We introduce AudioLM, a framework for high-quality audio generation with long-term consistency. Aud… 2022-09-07 published
  29. Auditing Patient Privacy in Medical Generative Models: Scalable Memorization Detection with DeepSSIM++ taaft While deep generative models offer new opportunities for medical image synthesis and data sharing,… 2026-09-03 published
  30. Auditory Illusion Benchmark for Large Audio Language Models taaft Perceptual illusions have long served as crucial probes into human cognition, revealing biases and… 2026-09-02 published
  31. Augmenting Human Performance with an XR Agent Learning from Online Behavior and BCI Evidence taaft We present OLIVE, a framework for adapting a foundation model to provide real-time assistance in te… 2026-08-31 published
  32. Augmenting Interviewer Judgments of Patient Experience with Automatic Language Analysis taaft Understanding how psychiatric patients subjectively experienced a clinical conversation is importan… 2026-08-31 published
  33. Augmenting Math Word Problems via Iterative Question Composing taaft Despite the advancements in large language models (LLMs) for mathematical reasoning, solving compet… 2024-01-17 published
  34. AutoCompass: Accurate Visual Localization on Public Maps by Learning from Weak Labels taaft Neural map matchers estimate an image's 3-DoF pose relative to a 2D map. These models are trained o… 2026-09-02 published
  35. Autodata: An agentic data scientist to create high quality synthetic data taaft We introduce Autodata, a general method that enables AI agents to act as data scientists who build… 2026-06-24 published
  36. AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation Microsoft AutoGen is an open-source framework that allows developers to build LLM applications via multiple a… 2023-08-16 published