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. Structured Frequency-Domain Evidence for LLM-Based Time-Series Anomaly Detection taaft Time-series anomalies can appear not only as pointwise deviations but also as changes in recurring… 2026-08-25 published
  2. Structured Packing in LLM Training Improves Long Context Utilization taaft Recent advancements in long-context large language models have attracted significant attention, yet… 2023-12-28 published
  3. Structured Semantic Cloaking for Jailbreak Attacks on Large Language Models Kuaishou Technology Modern LLMs employ safety mechanisms that extend beyond surface-level input filtering to latent sem… 2026-03-17 published
  4. Structured-Prior-Guided Diffusion Inpainting with Physical Consistency for Traffic Sign Augmentation taaft Traffic sign detection faces a long-tailed data distribution. Many rare signs matter as much as com… 2026-09-02 published
  5. StudentSim: Training LLM-based Student Simulators taaft AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred gu… 2026-09-01 published
  6. Subcellularly Resolved Single-Cell Embedding Learning with Transcriptomic data, Protein Structure and Localization Information taaft Existing cell embedding methods predominantly rely on transcriptomic or proteomic measurements and… 2026-09-02 published
  7. Subject-Specific Low-Field MRI Synthesis via a Neural Operator taaft Low-field (LF) magnetic resonance imaging (MRI) improves accessibility and reduces costs but genera… 2026-03-26 published
  8. Subspace Projection Methods for Fast Spectral Embeddings of Evolving Graphs taaft Several graph data mining, signal processing, and machine learning downstream tasks rely on informa… 2026-03-19 published
  9. Substrate-Aware AI Agents: Execution Context as a First-Class Input taaft Autonomous AI agents increasingly select actions in environments whose memory, execution-time, runt… 2026-09-04 published
  10. Subword Segmental BabyLMs: Learning to Tokenise for Sample-Efficient Pretraining taaft In the standard LM training pipeline, subword tokenisation is applied as a preprocessing step. Subw… 2026-09-01 published
  11. SUP-MIMIC: A Multi-Task Clinical Diagnosis Benchmark for Evaluating LLMs' Robustness to Contradictory Evidence taaft Current evaluations of large language models (LLMs) primarily focus on factual knowledge retrieval,… 2026-08-30 published
  12. Superfiltering: Weak-to-Strong Data Filtering for Fast Instruction-Tuning taaft Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant d… 2024-02-01 published
  13. Superposed Latent Autoencoder taaft Autoencoders typically meet tight latent-memory budgets by making each latent representation smalle… 2026-09-01 published
  14. Supraglacial Lake Fate Is Knowable Long Before the Season Ends taaft A supraglacial lake on the Greenland Ice Sheet ends its melt season in one of four ways: it drains… 2026-08-31 published
  15. SurfSpec: Enhancing Off-Target-Agnostic Specificity by Bounding Pocket-Ligand Geometric Mismatch taaft Lead optimization in structure-based drug design aims to improve target binding while avoiding unin… 2026-09-02 published
  16. SurgeGen: A Hybrid Generative Diffusion Framework for Storm Surge Scenario Synthesis taaft Predicting storm surge induced by landfalling tropical cyclones is crucial for flood mitigation and… 2026-09-03 published
  17. Surrogate-Assisted Genetic Programming with Rank-Based Phenotypic Characterisation for Dynamic Multi-Mode Project Scheduling taaft The dynamic multi-mode resource-constrained project scheduling problem (DMRCPSP) is of practical im… 2026-03-17 published
  18. Sustainability Is Not Linear: Quantifying Performance, Energy, and Privacy Trade-offs in On-Device Intelligence taaft The migration of Large Language Models (LLMs) from cloud clusters to edge devices promises enhanced… 2026-03-27 published
  19. Sustainable Edge Vision via Empirically Calibrated DVFS: Eliminating Thermal Throttling on Passively Cooled Hardware taaft Passive cooling eliminates the energy overhead and mechanical failure modes of fans, making it attr… 2026-09-04 published
  20. SVG-Score: Human-Aligned Evaluation of Text-to-SVG Generation taaft Scalable Vector Graphics (SVG) generation is attracting increasing attention as generative models i… 2026-09-03 published
  21. SwanTale: Unified Multi-Speaker Speech and Audio Generation for Instruct and Zero-Shot Tasks taaft Speech and audio generation is often needed in animation dubbing, audio drama, movies, advertising,… 2026-08-03 published
  22. SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering taaft Language model (LM) agents are increasingly being used to automate complicated tasks in digital env… 2024-05-06 published
  23. SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents taaft Repository-level software engineering benchmarks have significantly advanced the evaluation of codi… 2026-09-03 published
  24. SWE-PRBench: Benchmarking AI Code Review Quality Against Pull Request Feedback taaft We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for ev… 2026-03-27 published
  25. SWIM: Student Writing Simulation via Proficiency-Conditioned Generation taaft Writing proficiency manifests in how students develop content, organize ideas, choose words, and us… 2026-09-02 published
  26. Swin Meets EfficientNet: Lightweight Architectures for GAN-Based Face Forensics taaft Modern generative models, such as GANs, diffusion architectures, and autoregressive systems, now pr… 2026-09-01 published
  27. Swin Transformer: Hierarchical Vision Transformer using Shifted Windows Microsoft This paper presents a new vision Transformer, called Swin Transformer, that capably serves as a gen… 2021-03-25 published
  28. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity Google In deep learning, models typically reuse the same parameters for all inputs. Mixture of Experts (Mo… 2021-01-11 published
  29. Symbolic Chain-of-Thought Distillation: Small Models Can Also "Think" Step-by-Step taaft Chain-of-thought prompting (e.g., "Let's think step-by-step") primes large language models to verba… 2023-06-24 published
  30. SymFold: Synergizing Evolutionary and Structural Priors for Accurate Protein Inverse Folding taaft Protein inverse folding aims to recover amino acid sequences for a given 3D protein structure, unde… 2026-09-01 published
  31. Synchronized Video Storytelling: Generating Video Narrations with Structured Storyline taaft Video storytelling is engaging multimedia content that utilizes video and its accompanying narratio… 2024-05-22 published
  32. SynCrash: A Multi-Stage Pipeline for Zero-Shot Accident Detection and Localization in Traffic Surveillance Video taaft We present SynCrash, a multi-stage pipeline for zero-shot accident detection, spatial localization,… 2026-08-30 published
  33. Synergistic Event-SVE Imaging for Quantitative Propellant Combustion Diagnostics taaft Real-time monitoring of high-energy propellant combustion is difficult. Extreme high dynamic range… 2026-03-26 published
  34. Synergistic Information Disentanglement for Omni-modal Slide Representation Learning in Computational Pathology taaft In computational pathology (CPath), developing omni-modal self-supervised learning (SSL) models tha… 2026-09-02 published
  35. Synergizing Reasoning and Acting in Language Models Google Research While large language models (LLMs) have demonstrated impressive capabilities across tasks in langua… 2022-10-06 published
  36. Syntax-Directed Variational Autoencoder for Structured Data taaft Deep generative models have been enjoying success in modeling continuous data. However it remains c… 2018-02-24 published