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. A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping taaft Upcoming stage-IV surveys such as Euclid and Rubin will deliver vast amounts of high-precision data… 2026-03-23 published
  2. A Probabilistic Interpretation of KV Cache Eviction taaft The premise and promise of KV (cache) eviction is simple: higher throughput can be achieved by evic… 2026-08-28 published
  3. A Progressive Visual-Logic-Aligned Framework for Ride-Hailing Adjudication DiDi Global The efficient adjudication of responsibility disputes is pivotal for maintaining marketplace fairne… 2026-03-18 published
  4. A Quantum Roadmap for Softmax Attention: Exact Born-Rule Analogs for Softmax Attention on the Probability Simplex taaft The attention mechanism forms the foundation of many modern AI models such as the Transformer. In o… 2026-08-11 published
  5. A Robust Watermark-based Fingerprint Framework for GNNs Ownership Verification taaft The high training cost of Graph Neural Networks (GNNs) has raised growing concerns regarding model… 2026-09-04 published
  6. A Self-Evolving Multi-Agent Framework Defense against LLM Jailbreak Attacks taaft Large language models (LLMs) remain vulnerable to jailbreak attacks that exploit techniques such as… 2026-08-26 published
  7. A Shaky Voice Is Not Always a Dodge: Benchmarking Textual and Vocal Evasion Detection in Earnings Calls taaft Existing approaches to evasion detection in earnings calls focus on textual transcripts, treating e… 2026-08-28 published
  8. A Sim-to-Real Study of Surface-Code Decoder Benchmarking taaft Quantum error-correction decoders are typically benchmarked against synthetic circuit-level noise,… 2026-09-03 published
  9. A Simple Transformer Pipeline for Full-Key Side-Channel Attacks on Uncropped Datasets taaft Deep learning-based side-channel analysis has historically focused on single-byte targets and manua… 2026-08-31 published
  10. A Single Suffix to Break Them All: Basin-Aware Jailbreaks for Merged Model Families taaft Model merging enables combining multiple fine-tuned models without additional training, but its saf… 2026-08-27 published
  11. A Structural FHMM for Interpretable Disease Trajectories in T2DM taaft In this work, we propose a structural variant of the Factorial Hidden Markov Model (FHMM) for the a… 2026-08-25 published
  12. A Structured Debate-Mixture-of-Agents Framework for Complex Clinical Diagnostic Decision Support taaft Large language models (LLMs) show potential for medical tasks, but their single-turn question-answe… 2026-09-04 published
  13. A Survey of Deep Learning Approaches for OCR and Document Understanding taaft Documents are a core part of many businesses in many fields such as law, finance, and technology am… 2020-11-27 published
  14. A Survey on Data Selection for Language Models taaft A major factor in the recent success of large language models is the use of enormous and ever-growi… 2024-02-26 published
  15. A Survey on Data Selection for LLM Instruction Tuning taaft Instruction tuning is a vital step of training large language models (LLMs), so how to enhance the… 2024-02-04 published
  16. A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference taaft The ability of AI systems to improve their behavior during deployment is becoming increasingly impo… 2026-09-01 published
  17. A systematic Approach to constructing a Chance-and-Risk Matrix for Semiconductor Supply Chains taaft Semiconductor supply chains face escalating risks from geopolitical tensions, geographic concentrat… 2026-09-01 published
  18. A Systematic Comparison of Multilingual Interpretability Methods Reveals Anisotropy-Driven Failures taaft Multilingual language models develop shared cross-lingual representations, and various interpretabi… 2026-09-04 published
  19. A Table Is Worth 64 Tokens: Pixel-level Compression for Multi-Table Document Question Answering taaft Answering questions over real-world documents requires processing long inputs that interleave text… 2026-08-27 published
  20. A tale of perfect fit and phantom optima: how data-driven models can fail in real-time optimization taaft Real-time optimization (RTO) relies on process models to locate economically optimal operating cond… 2026-08-24 published
  21. A Target-Centric Survey of Quantization-Aware Training taaft The rapid development of LLMs incurs prohibitive memory footprints and intensive computational dema… 2026-08-30 published
  22. A Taxonomy of Construction Task Activities for Robot Workers taaft Recent vision-language-action models offer a path toward robots with broader capabilities than conv… 2026-08-26 published
  23. A Tendon-Driven Five-Fingered Hand with Distributed Tactile Perception for Dexterous Manipulation taaft To apply the techniques of embodied artificial intelligence to human-oid robots for complex manipul… 2026-08-26 published
  24. A Theory of Finite-Noise Optima and Generalization in Quantum Machine Learning taaft Quantum noise is expected to degrade quantum machine learning by driving circuits away from their n… 2026-08-25 published
  25. A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation taaft On-policy distillation (OPD) supervises a student on its own trajectories with token-level signals… 2026-08-26 published
  26. A Top-Down Framework for Metric-Scale Athlete Localization from Single Broadcast Frames taaft Accurate world-coordinate localization of athletes from single-frame broadcast footage is inherentl… 2026-09-02 published
  27. A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models taaft Large Language Models (LLMs) are increasingly deployed in interactive systems where understanding u… 2026-09-02 published
  28. A Two-Stage Forecasting System for CPU Workload Prediction in Private Clouds taaft Accurate cloud resource forecasting is essential for proactive resource provisioning, maintaining Q… 2026-09-03 published
  29. A Unified Model for Personalization: Language-SteerableGenerative Recommendation, Search, and User Understanding Spotify This DOI corresponds to a brief report paper at KDD '26 (32nd ACM SIGKDD Conference on Knowledge Di… Spotify
  30. A Unified Particle Filter LSTM for Data-Driven Process Simulation taaft Data-driven process simulation aims to generate realistic case trajectories from historical event l… 2026-09-02 published
  31. A Unified Perspective on Conformal Prediction and Wasserstein Distributionally Robust Optimization for Uncertainty Quantification taaft Uncertainty quantification from finite data is central to machine learning, optimization, and autom… 2026-08-30 published
  32. A Unified Physics-Aware Quantum Machine Learning Framework across Power GaN HEMTs and Logic Nanowire FETs: Predicting Unseen Process Splits and Held-Out Geometry Combinations with Lower Error and Tighter Split-to-Split Variability taaft We present a unified reinforcement-learning (RL) framework that discovers compact parametrized quan… 2026-09-04 published
  33. A Unified Rate-Distortion Perspective on Vector, Product, and Scalar Quantization taaft Discrete visual tokenization, predominantly driven by vector, scalar, and product quantization, lac… 2026-09-02 published
  34. A Universal Context-Reuse Layer for Cross-Model KV Sharing taaft Modern large language model (LLM) serving systems increasingly operate over repeated or shared cont… 2026-08-31 published
  35. A Verifier-Guided Explainable Reasoning Framework with Gold-Anchored QLoRA, Task-Aware Mixture-of-Experts, and Group-Relative RLVR taaft Large language models (LLMs) show strong reasoning ability, but their explanations can remain incon… 2026-09-04 published
  36. A visual observation on the geometry of UMAP projections of the difference vectors of antonym and synonym word pair embeddings taaft Antonyms, or opposites, are sometimes defined as \emph{word pairs that have all of the same context… 2026-03-25 published