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. SMG: Semantic Motion Graph for Monocular Dynamic Gaussian Splatting taaft We study dynamic Gaussian Splatting from monocular videos. While recent advancements in dynamic Gau… 2026-08-31 published
  2. SMILE: Bridging Continuous Optimization and Discrete Symbolic Recovery taaft Symbolic regression (SR) discovers closed-form mathematical expressions from data, offering interpr… 2026-09-04 published
  3. SMILE: Self-Explainable Multimodal Information Bottleneck for Medical Diagnosis taaft Explainability is increasingly seen as a crucial requirement in AI-based medical diagnosis, particu… 2026-09-04 published
  4. SMOTE-VAR: An Uncertainty-Aware Oversampling Method for Predicting Depression Remission in University Students taaft University students experience disproportionately high rates of common mental health conditions, su… 2026-08-31 published
  5. Snap Video: Scaled Spatiotemporal Transformers for Text-to-Video Synthesis Snap Contemporary models for generating images show remarkable quality and versatility. Swayed by these… 2024-02-22 published
  6. SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection taaft Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech… 2026-03-21 published
  7. SnapBench: Benchmarking Snap-and-Ask Multimodal Retrieval for Mobile Interactions taaft Mobile AI acts as a visual oracle, empowering users to snap a picture of something and ask for info… 2026-08-30 published
  8. SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds Snap Text-to-image diffusion models can create stunning images from natural language descriptions that r… 2023-06-01 published
  9. Socialized Detector Learning: Trajectory-Guided and Reciprocal Distillation for Heterogeneous Object Detectors taaft Object detection knowledge is fragmented across independently trained, heterogeneous detectors with… 2026-08-26 published
  10. SocioGesture: Real-Time and Adaptive Social Gesture Perception for Human-Robot Interaction taaft Robots interacting with people must recognize not only explicit commands, but also social cues such… 2026-09-03 published
  11. Soft-Argmax for the Projective Plane via the Veronese Embedding taaft From horizon detection to fibre structures in X-ray imaging, many vision tasks recover lines via pe… 2026-09-01 published
  12. Softmax Linear Units Anthropic Proposed a new neural network architecture (SoLU) that makes models more "interpretable" by design… Anthropic
  13. SoK: Where Do Flow Labels Come From? Auditing Label Provenance in Encrypted Traffic Benchmarks taaft Encrypted traffic classification infers semantics beyond the flow record from transport-layer obser… 2026-09-02 published
  14. Solaris: Towards Interfaces That Are Generated, Not Coded taaft Digital interfaces are traditionally implemented through intermediate representations such as code,… 2026-09-01 published
  15. SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models taaft We introduce SolarWM, a fully open foundation for building interactive video world models from data… 2026-09-02 published
  16. Solution-space heterogeneity shapes federated learning dynamics across partial differential equations taaft Federated scientific machine learning enables institutions to train neural surrogates without centr… 2026-09-04 published
  17. Solving Hard XAI Queries Based on a Compiled Dual-Rail Encoding taaft The widespread adoption of artificial intelligence (AI) within real-world applications has raised a… 2026-09-04 published
  18. Solving In-Table Prediction Problems by Deep Neural Networks with Performance Evaluation Using Synthetic Data taaft Tabular deep learning (TDL) leverages neural networks (NN) to extract patterns from tabular data. T… 2026-09-01 published
  19. Solving Olympiad Geometry without Human Demonstrations (AlphaGeometry) Google Combined a neural language model with a symbolic deduction engine to solve 25/30 IMO geometry probl… Google
  20. Solving the Needle-in-a-Haystack Problem in Mammography Vision-Language Model with Differentiable Subset Sampling taaft There is growing interest in adopting CLIP-style vision--language model (VLM) pretraining for mammo… 2026-09-02 published
  21. SOMTab: Set-Order Mamba for Efficient Tabular In-Context Learning taaft Tabular foundation models based on in-context learning have recently emerged as strong alternatives… 2026-08-28 published
  22. SonicCaps: Large-Scale Diverse and Fine-Grained Captioning for Improved Audio-Retrieval taaft Recent advances in audio-language modeling have been driven by large-scale audio captioning dataset… 2026-09-02 published
  23. Sound-based Multi-Person 3D Pose Estimation taaft Can we recover the 3D poses of multiple people using only sound? This paper presents the first atte… 2026-09-04 published
  24. SoundCTM: Unifying Score-based and Consistency Models for Full-band Text-to-Sound Generation taaft Sound content creation, essential for multimedia works such as video games and films, often involve… 2024-05-28 published
  25. Soundify: Matching Sound Effects to Video taaft In the art of video editing, sound helps add character to an object and immerse the viewer within a… 2021-12-17 published
  26. Source Distribution Estimation by Posterior Averaging taaft Simulation-based science often requires a distribution over simulator parameters whose push-forward… 2026-09-02 published
  27. Source-Free Class Relearning: Diagnosing Forgetting in Class Unlearning taaft Class unlearning aims to remove a model's ability to recognize designated forget classes while pres… 2026-09-02 published
  28. Sources of Truth: A Multi-Platform, Multilingual Audit of Citations in AI Mental Health Information Queries taaft Online health information seeking is shifting from keyword search, where users consider a ranked li… 2026-08-31 published
  29. SPA: A Simple but Tough-to-Beat Baseline for Knowledge Injection taaft While large language models (LLMs) are pretrained on massive amounts of data, their knowledge cover… 2026-03-23 published
  30. Space Generative AI with Solar Energy Harvesting taaft Satellites are emerging as promising platforms to extend generative \emph{artificial intelligence}… 2026-09-01 published
  31. SPADE: SPaT Attack Detection from the Connected Vehicle's Perspective taaft Signal Phase and Timing (SPaT) messages are a cornerstone of connected vehicle (CV) safety, enablin… 2026-09-02 published
  32. SPAR: Enhancing Industrial-Scale Generative POI Recommendation via Real-World Spatial Perception taaft Generative Point-of-Interest (POI) recommendation, autoregressively generating a target POI's seman… 2026-09-02 published
  33. SPARK: Input-Conditioned Sparse Activation Modulation for Frozen DiT-based Super-Resolution taaft Real-world image super-resolution (SR) increasingly relies on Diffusion Transformer (DiT) backbones… 2026-09-03 published
  34. SPARK: Skeleton-Guided Reasoning Synthesis from Large-Scale Scientific Literature taaft Scientific reasoning remains challenging for open-source models, largely due to the lack of high-qu… 2026-08-31 published
  35. Sparks of Artificial General Intelligence: Early experiments with GPT-4 Microsoft Artificial intelligence (AI) researchers have been developing and refining large language models (L… 2023-03-22 published
  36. Sparse Competition during Training For the Emergence of Specialized Modules taaft Modularity in deep neural networks has been proposed as a means of improving both interpretability… 2026-08-31 published