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. Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens taaft A language model's prediction of its next token develops across layers, and lens methods track this… 2026-09-01 published
  2. Sparse3DTrack: Monocular 3D Object Tracking Using Sparse Supervision taaft Monocular 3D object tracking aims to estimate temporally consistent 3D object poses across video fr… 2026-03-18 published
  3. Spatial Matryoshka Training for Multi-Granularity Visual Document Retrieval taaft Multi-modal late-interaction retrievers achieve strong retrieval on visually rich documents by repr… 2026-08-30 published
  4. Spatial-Semantic Reasoning using Large Language Models for Efficient UAV Search Operations taaft We present a real-time semantic navigation framework for Unmanned Aerial Vehicles (UAVs) focused on… 2026-08-28 published
  5. SpatialCrafter: Single Image World Modeling with Generative 3D Proxies taaft Explorable image-to-scene generation is essential for applications in gaming, robotics, and virtual… 2026-08-27 published
  6. SpatialGuard: Harness-Guided Verifiable Spatial Reasoning for Text-to-Image Generation taaft Complex 3D spatial text to image generation requires models to convert natural language into stable… 2026-09-01 published
  7. Spatially Aware World Action Model via Geometric Latent Diffusion taaft World Action Models (WAMs) leverage the capabilities of large-scale pretrained video diffusion mode… 2026-09-02 published
  8. SpatialTrust: A Benchmark for Environmental Risk Recognition in Secure Authentication taaft Visual environmental risk recognition plays an important role in secure authentication, where a use… 2026-08-30 published
  9. Spawn Freely, Act Sparingly: Progressive Risk Vesting for Recursive LLM-Agent Trees taaft Recursive LLM agents can broaden their search by spawning specialists. Some branches later request… 2026-09-01 published
  10. SPD: Single Pass Decoding for Generative Reranking taaft Large language models (LLMs) achieve state-of-the-art generative ranking quality, but the ranking t… 2026-09-01 published
  11. SpeakPay: Domain-Adaptive LoRA Fine-Tuning of Whisper for Low-Resource Nepali Financial Speech Recognition taaft Mobile payment applications in Nepal are graphically mediated and largely inaccessible to visually… 2026-09-01 published
  12. Spec2Twin-Chain: Orchestrating Bi-Level Optimization with LLMs for Blockchain Digital Twin Construction taaft Building a blockchain digital twin largely requires translating domain knowledge and specific syste… 2026-08-30 published
  13. Spectral Coherence Index: A Model-Free Metric for Protein Structural Ensemble Quality Assessment taaft Protein structural ensembles from NMR spectroscopy capture biologically important conformational he… 2026-03-26 published
  14. Spectral Initialization and Scheduled Graph Smoothness for Uncertain Knowledge Graph Completion taaft Uncertain knowledge graphs (UKGs) extend knowledge graphs by assigning each triple a continuous con… 2026-09-02 published
  15. Spectral methods: crucial for machine learning, natural for quantum computers? taaft This article presents an argument for why quantum computers could unlock new methods for machine le… 2026-03-25 published
  16. Spectral Scalpel: Amplifying Adjacent Action Discrepancy via Frequency-Selective Filtering for Skeleton-Based Action Segmentation taaft Skeleton-based Temporal Action Segmentation (STAS) seeks to densely segment and classify diverse ac… 2026-03-25 published
  17. Speculative Probing: LLM Monitoring at Speculative-Decoding Cost taaft Real-time classification during language model inference is valuable for safety filtering, behavior… 2026-08-28 published
  18. Speech Translation with Large Language Models: An Industrial Practice ByteDance Given the great success of large language models (LLMs) across various tasks, in this paper, we int… 2023-12-21 published
  19. Speech-to-SOAP: End-to-End Summarization of Medical Dialogues: KIT@BeTraC 2026 taaft With the advent of Large Language Models and its instruction following capabilities a promising app… 2026-08-25 published
  20. Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task taaft We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-SQL dataset… 2018-09-24 published
  21. SpikeOPD: Stable On-Policy Distillation for Autoregressive Spiking Language Models taaft Spiking neural networks (SNNs) offer a path to energy-efficient language modeling through sparse en… 2026-08-28 published
  22. SpinGQE: A Generative Quantum Eigensolver for Spin Hamiltonians taaft The ground state search problem is central to quantum computing, with applications spanning quantum… 2026-03-25 published
  23. SPLG-Mamba: Structure-Preserving Local-Global Mamba Network for Salient Object Detection in Optical Remote Sensing Images taaft Salient object detection in optical remote sensing images (ORSI-SOD) requires dense predictions tha… 2026-08-30 published
  24. SPO++: Stream-Aligned Policy Optimization for Asynchronous Agentic RL taaft Group-relative reinforcement learning waits for sibling rollouts of the same prompt, which is costl… 2026-08-25 published
  25. Spruce: Scalable Private Outsourced Retrieval Using Compact Embeddings taaft Retrieval-Augmented Generation (RAG) has made dense retrieval over large document collections a sta… 2026-09-03 published
  26. SPUQ: Perturbation-Based Uncertainty Quantification for Large Language Models Intuit In recent years, large language models (LLMs) have become increasingly prevalent, offering remarkab… 2024-03-04 published
  27. Spurious Advantage Hidden in GRPO taaft Group Relative Policy Optimization (GRPO) is widely studied for reinforcement learning with verifia… 2026-09-03 published
  28. SQ-VAE: Variational Bayes on Discrete Representation with Self-annealed Stochastic Quantization taaft One noted issue of vector-quantized variational autoencoder (VQ-VAE) is that the learned discrete r… 2022-05-16 published
  29. SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation INFLY Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly… 2026-03-17 published
  30. SQL-Zero: Self-Evolving Text-to-SQL taaft Training a competitive Text-to-SQL agent usually depends on human-annotated natural-language/SQL pa… 2026-09-04 published
  31. SQuaT: Self-Supervised Knowledge Distillation via Student-Aware Quantized Teacher Features taaft Quantization-Aware Training (QAT) enables the deployment of quantized models with minimal accuracy… 2026-08-11 published
  32. Squeeze Evolve: Unified Multi-Model Orchestration for Verifier-Free Evolution taaft We show that verifier-free evolution is bottlenecked by both diversity and efficiency: without exte… 2026-04-09 published
  33. SqueezeComposer: Temporal Speed-up is A Simple Trick for Long-form Music Composing taaft Composing coherent long-form music remains a significant challenge due to the complexity of modelin… 2026-03-22 published
  34. Squeezing More from Limited Data with Recursive Transformers taaft Pre-training under limited data requires a different view of scaling than web-scale language modeli… 2026-08-27 published
  35. Squish and Release: Exposing Hidden Hallucinations by Making Them Surface as Safety Signals taaft Language models detect false premises when asked directly but absorb them under conversational pres… 2026-03-27 published
  36. SR-Edit: Region-Aware Image Editing via Self-Refinement taaft With the recent rapid progress in generative models, image editing has made remarkable advances, ye… 2026-09-02 published