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. BioKERN: Biological Kernel Regularization for Histology-to-Transcriptomics Neighborhood Retrieval taaft Spatially resolved biology requires representations that preserve biological neighborhood structure… 2026-08-25 published
  2. Biomechanical 3D Body: Self-Supervised Distillation of Biomechanical Pose from a 3D Body Foundation Model taaft State-of-the-art monocular body recovery methods predict mesh vertices and angles on the correspond… 2026-08-30 published
  3. Births are difficult to predict even with rich survey and full-population register data taaft Major life events have proven difficult to predict. Does this reflect limits of theory, data, and a… 2026-09-01 published
  4. BIT.UA at BioASQ 14B: Modular Retrieval with pg_textsearch and Qdrant, and Agent-Based Answer Generation taaft This paper describes the participation of the BIT.UA team from the University of Aveiro in the 14th… 2026-09-04 published
  5. BitNet: Scaling 1-bit Transformers for Large Language Models Microsoft The increasing size of large language models has posed challenges for deployment and raised concern… 2023-10-17 published
  6. BixBench3: Benchmarking AI agents on research-study-scale computational biology tasks taaft Artificial intelligence (AI) promises to accelerate biological research by automating computational… 2026-08-26 published
  7. BLARM: Animating 3D Objects from Video via Blending Latent Rigid Motion Primitives taaft We introduce BLARM, a feed-forward method for video-driven 3D mesh animation. Given a monocular vid… 2026-08-31 published
  8. Blending Concepts: Benchmarking Visual Metaphor Generation in Text-to-Image Models taaft Text-to-image (T2I) models have achieved remarkable success at faithfully rendering specified objec… 2026-09-02 published
  9. Blind Men and the Elephant: Probing the Epistemic Myopia of LLMs under Long-Tail Divergent Knowledge taaft Factual question answering (QA) typically assumes a single canonical answer, obscuring whether larg… 2026-08-28 published
  10. BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models Salesforce The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end… 2023-01-30 published
  11. Blog: Survey of Optimizers taaft Neural-network optimization in 2025-2026 is no longer well described as a succession of new Adam va… 2026-08-28 published
  12. Bonded Recourse for Smart-Contract Settlement of Compensable Agent Side Effects taaft Autonomous agent runtimes execute tool actions that mutate databases, repositories, and cloud servi… 2026-09-01 published
  13. Boost Like a (Var)Pro: Trust-Region Gradient Boosting via Variable Projection taaft Gradient boosting, a method of building additive ensembles from weak learners, has established itse… 2026-03-24 published
  14. BOOST-RPF: Boosted Sequential Trees for Radial Power Flow taaft Accurate power flow analysis is critical for modern distribution systems, yet classical solvers fac… 2026-03-23 published
  15. Boosting Quantitive and Spatial Awareness for Zero-Shot Object Counting Miguo AI Zero-shot object counting (ZSOC) aims to enumerate objects of arbitrary categories specified by tex… 2026-03-17 published
  16. Boot-and-Feedback Framework for Generalist-Expert Model Collaboration in Breast Ultrasound Diagnosis taaft Breast ultrasound (BUS) is widely used for breast cancer diagnosis yet remains operator-dependent.… 2026-08-25 published
  17. BPG: Balancing Plasticity and Generalization for Domain Incremental Learning taaft Deep neural networks excel in various tasks but struggle to generalize across evolving data distrib… 2026-08-11 published
  18. BPMN4CAI: A BPMN Extension for Modeling Dynamic Conversational AI taaft Conversational AI systems, such as chatbots and virtual assistants, are becoming increasingly impor… 2026-08-27 published
  19. BrainDiff: Longitudinal Report Generation for Multimodal Brain MRI taaft Neuroradiologists rarely read a brain MRI in isolation, yet automated brain-MRI report generation h… 2026-09-01 published
  20. Breadth Beats Depth: Improving GCG-Based Jailbreak Optimization with Breadth-Oriented Suffix Search taaft Optimization-based jailbreak attacks such as Greedy Coordinate Gradient (GCG) achieve strong effect… 2026-09-02 published
  21. Breaking Entropy Bounds: Accelerating RL Training via MTP with Rejection Sampling taaft Reinforcement learning (RL) has become a key component in modern large language models, yet the rol… 2026-06-10 published
  22. BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI taaft Developing humanoid robots capable of leveraging human behavioral data is essential for general-pur… 2026-09-03 published
  23. Bridging Adversarial and Collaborative Learning for AI-Generated Image Quality Assessment taaft AI-generated image quality assessment (AIGIQA) requires jointly reasoning about perceptual fidelity… 2026-08-25 published
  24. Bridging Modalities and Tasks: A Unified Hierarchical ViT for SAR-to-Optical Translation and Semantic Segmentation taaft Synthetic Aperture Radar (SAR) images have all-weather, day-and-night observation capabilities. How… 2026-09-04 published
  25. Bridging the Evaluation Gap: Standardized Benchmarks for Multi-Objective Search taaft Empirical evaluation in multi-objective search (MOS) has historically suffered from fragmentation,… 2026-03-25 published
  26. BS: Take the Hint - Interactive Multitracer PET/CT Lesion Segmentation with a Scribble-Conditioned ResEnc U-Net taaft Automated lesion segmentation in whole-body PET/CT is complicated by the variety of physiological t… 2026-09-01 published
  27. Building Pretraining Data for World Models: An Unreal Engine-Based Pipeline for Action-Conditioned Video Generation taaft Action-conditioned video models require large-scale visual data paired with control signals that ar… 2026-09-03 published
  28. BuildOcc: A Large Language Model Occupant Agent Platform for Building Energy Research taaft Occupants are a primary source of uncertainty in building energy consumption and management, yet ex… 2026-09-02 published
  29. BUSSARD: Normalizing Flows for Bijective Universal Scene-Specific Anomalous Relationship Detection taaft We propose Bijective Universal Scene-Specific Anomalous Relationship Detection (BUSSARD), a normali… 2026-03-17 published
  30. ButterMamba: Butterworth-Enhanced Spatial-Temporal Mamba for Efficient Traffic Flow Prediction taaft Accurate traffic flow prediction is fundamental to intelligent transportation systems, playing a pi… 2026-08-30 published
  31. C$^{3}$T: Counterfactual Causal Reasoning for Sentiment Shifts in Social-Media Conversation Trees taaft Sentiment in social-media threads does not only vary across posts; it shifts as users react to clai… 2026-09-02 published
  32. CA-OPD: Confidence-Aware On-Policy Distillation for Structured Visual Prediction taaft Autoregressive vision language models unify heterogeneous perception tasks but are highly susceptib… 2026-09-02 published
  33. CABAL: Multi-Agent Simulacra for Tracing the Effects of Collusive Bidding in Peer Review taaft Recent reports during the AAAI-27 review cycle highlight the risk of reviewers coordinating bids fo… 2026-09-04 published
  34. CABINET: Content Relevance based Noise Reduction for Table Question Answering taaft Table understanding capability of Large Language Models (LLMs) has been extensively studied through… 2024-02-02 published
  35. Cache-Aware Joint Router Adaptation for Memory-Efficient MoE Inference taaft Mixture-of-Experts (MoE) models activate few experts per token, yet their full expert sets can exce… 2026-09-04 published
  36. CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning taaft Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sa… 2026-09-02 published