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. Triple-Bottom-Line Sustainability of Language Models for Edge AI: A Comparison Between SLMs and Quantized LLMs taaft Edge-AI model selection is commonly driven by one isolated metric - accuracy, latency, memory, ener… 2026-09-01 published
  2. TRIS: A Tri-Layer Retrieval Integrity Sieve Against Knowledge Poisoning taaft Retrieval-Augmented Generation (RAG) grounds large language models in external corpora, but implici… 2026-08-31 published
  3. Trojan horse hunt in deep forecasting models: Insights from the European Space Agency competition taaft Forecasting plays a crucial role in modern safety-critical applications, such as space operations.… 2026-03-20 published
  4. Trojan's Whisper: Stealthy Manipulation of OpenClaw through Injected Bootstrapped Guidance taaft Autonomous coding agents are increasingly integrated into software development workflows, offering… 2026-03-20 published
  5. Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learning taaft The Meteosat Third Generation (MTG) Flexible Combined Imager (FCI) offers new opportunities for tro… 2026-08-26 published
  6. TROVE: Adaptive Agent Skill Orchestration via Trace-Grounded Route Validation and Editing taaft Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes… 2026-09-04 published
  7. TruncGradGS: Improved 3D Gaussian Splatting via Truncated Gradient Updates taaft 3D Gaussian Splatting has become a de facto scene representation for novel view synthesis, yet robu… 2026-09-03 published
  8. Trust Your Guide Only When Certain: Uncertainty-Aware Sparse Alignment at Inference Time taaft A prominent paradigm in inference-time alignment employs lightweight supervisors to steer Large Lan… 2026-09-01 published
  9. Trust-Aware Sequential Decision Making and Rollout Planning for Resilient Multi-Robot Systems taaft Sequential decision-making in multi-robot systems typically assumes that planning information is re… 2026-08-26 published
  10. TRUST: Threshold-Recalibrated Uncertainty-Safe Training for Certified Dismissal in Breast Cancer Screening taaft Reducing the review of clearly cancer-negative screening mammograms could lower radiologist workloa… 2026-08-31 published
  11. TrustShiftProbe: Characterizing, Benchmarking, and Defending Staged Trust Attacks on MCP Servers taaft The Model Context Protocol (MCP) has emerged as the standard layer connecting Large Language Model… 2026-08-24 published
  12. Trustworthy Machine Learning through the Lens of Combinatorial Optimization: Survey and Research Perspectives taaft Modern machine learning (ML) increasingly relies on complex models whose behavior is difficult to c… 2026-07-08 published
  13. TruthInsightBench: An Evidence-Grounded Benchmark for Automated Evaluation of Open-Ended Scientific Discovery Agents taaft Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses an… 2026-09-04 published
  14. TSExplorer: An interactive data annotation and exploration tool for time-series data taaft We present TSExplorer, a cross-platform tool for interactive annotation and exploration of time-ser… 2026-08-31 published
  15. TSPFN: A Temporal Tabular Foundation Model for Physiological Time Series Classification taaft Designing models that generalize effectively in low- to medium-data regimes remains a primary chall… 2026-08-31 published
  16. TTPO: Test-Time Policy Optimization taaft Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Dist… 2026-08-27 published
  17. Tunable Soft Equivariance with Guarantees taaft Equivariance is a fundamental property in computer vision models, yet strict equivariance is rarely… 2026-03-27 published
  18. TurboT2VA: Fast Large-Scale Text-to-Video-Audio Generation via Score-Regularized Consistency Distillation taaft Joint text-to-video-audio generation produces synchronized visual and acoustic content, but the lon… 2026-08-25 published
  19. TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM taaft Vision-language-action (VLA) models commonly adopt an LLM-centric $V \to L \to A$ pathway, processi… 2026-07-29 published
  20. TuringLLM: Efficiently Scaling Foundation Models Toward Physical AI taaft We present Turing-20B-A2B, a 20B-parameter Mixture-of-Experts language model that activates approxi… 2026-08-31 published
  21. TUTTI: Toward generalizable audio-to-score transcription via fully synthesized data taaft Generalizable Audio-to-Score (A2S) transcription is fundamentally constrained by the severe scarcit… 2026-09-01 published
  22. Twin Worlds: Equivariance-Based Abstention for Evidence-Grounded Reasoning taaft Knowledge-intensive reasoning requires Large Language Models (LLMs) to ground answers in provided e… 2026-08-28 published
  23. Two locked tests of phase-structure features for transition prediction taaft Following arXiv:2607.25507, this report examines whether phase-derived features improve endpoint pr… 2026-08-31 published
  24. Two-Stage Reinforcement Learning for Sound and Adversarial Test Generation in Code LLMs taaft Reinforcement learning (RL) has substantially advanced code generation with large language models (… 2026-09-03 published
  25. Typological Feature Prediction with Large Language Models: An In-Context Learning Approach taaft Typological features are widely used in multilingual NLP, and the prediction of such features holds… 2026-09-03 published
  26. UAV Thermal Imagery for Inert Ordnance Screening: Multi Campaign Dataset Development,Object Detection, and Practical Recommendations taaft Unexploded ordnance (UXO) continues to restrict civilian access, agricultural activity, infrastruct… 2026-09-01 published
  27. UE5M3 FP4 Block Scaling for Stable Language Model Pretraining taaft Stable 4-bit floating-point (FP4) pretraining is difficult because the E2M1 payload represents only… 2026-09-02 published
  28. UI-VISA: U-Net Initialized Vascular Image Segmentation Architecture taaft Accurate segmentation of vascular structures in digital subtraction angiography (DSA) images remain… 2026-09-01 published
  29. UltraFeedback: Boosting Language Models with Scaled AI Feedback taaft Learning from human feedback has become a pivot technique in aligning large language models (LLMs)… 2023-10-02 published
  30. UnCapsTSR: An Unsupervised Transformer-based Image Super-Resolution Approach for Capsule Endoscopy Images taaft Wireless Capsule Endoscopy (WCE) captures and streams video while passing through a patient's Gastr… 2026-09-02 published
  31. Uncensored Open-weight Models: Redistribution as the Persistence Layer taaft A rapidly expanding ecosystem of actors is removing built-in safety guardrails from open-weight AI… 2026-09-04 published
  32. Uncertainty of Vision Medical Foundation Models taaft Accurate uncertainty estimation is essential for machine learning systems de- ployed in high-stakes… 2026-08-31 published
  33. Uncertainty Quantification for Distribution-to-Distribution Flow Matching in Scientific Imaging taaft Distribution-to-distribution generative models support scientific imaging tasks ranging from modeli… 2026-03-23 published
  34. Uncertainty Quantification for Quantum Computing taaft This review is designed to introduce mathematicians and computational scientists to quantum computi… 2026-03-26 published
  35. Uncertainty-Aware Trajectory Forecasting from Imperfect Tracking taaft Most trajectory forecasting models are trained on clean annotated histories, and are often evaluate… 2026-08-31 published
  36. Uncertainty-Driven Replay Memory for Reinforcement Learning taaft Uncertainty estimation provides promising capabilities for reinforcement learning (RL) agents. Nota… 2026-08-30 published