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. SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation taaft Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities,… 2026-08-31 published
  2. SemTrace: Source-Grounded Semantic Signatures for Tracing LLM Exposure to Protected Documents taaft Large language models are increasingly used to read documents and produce downstream text, creating… 2026-08-30 published
  3. Sensing Which Modality Matters: Evidence-Gated Regularization for Robust VLA Policies taaft Vision-Language-Action (VLA) policies fuse multimodal sensory inputs, but training on limited and h… 2026-09-02 published
  4. Sensitivity-Constrained Neural Operators for Data-Efficient Forward and Inverse Modeling of Partial Differential Equation Systems taaft Neural operators provide fast surrogates for partial differential equation (PDE) solvers, but their… 2026-08-30 published
  5. Separating Disclosure from Authorization: Field-Tier Minimization for Agent Action Mediation taaft A system that authorizes an action must see enough of it to decide, and a system that attests to it… 2026-08-26 published
  6. Separating perception from reasoning in vision-language models: a model-free render ceiling for crystal structures taaft Multimodal evaluations cannot say whether a vision-language model misread an image or misreasoned a… 2026-09-01 published
  7. SEPO: Evidence-Grounded Prompt Optimization via Structural Editing taaft Existing API-only prompt optimisers are often described as interpretable, but in practice, this usu… 2026-08-28 published
  8. Sequential Attention: Making AI Models Leaner and Faster Without Sacrificing Accuracy Google Feature selection is the problem of selecting a subset of features for a machine learning model tha… 2022-09-29 published
  9. Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR taaft Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged… 2026-09-03 published
  10. Serving Masked Diffusion LLMs: Characterization and Design Principles from Real Hardware taaft Masked diffusion language models (dLLMs) can in principle generate text faster than autoregressive… 2026-08-24 published
  11. SeVeR: Selective Visual Exposure and Retrieval for 3D Medical Image Question Answering taaft Volumetric medical VQA requires reasoning over long and redundant 3D visual token sequences, especi… 2026-08-26 published
  12. SFAD: Speculative Factuality-Aware Decoding taaft As one of the most critical challenges in large language models, contextual faithfulness directly d… 2026-09-01 published
  13. SGAD-SLAM: Splatting Gaussians at Adjusted Depth for Better Radiance Fields in RGBD SLAM taaft 3D Gaussian Splatting (3DGS) has made remarkable progress in RGBD SLAM. Current methods usually use… 2026-03-22 published
  14. SGD-KV: Summarization Guided KV Cache Compression taaft Large language models (LLMs) face severe memory bottlenecks in long-context inference due to the li… 2026-09-03 published
  15. Shadow Queries for Private Retrieval in Vector Databases taaft Large language models (LLMs) increasingly rely on information retrieval (IR) systems, such as Retri… 2026-09-04 published
  16. Shallow neural network approximation in mixed Sobolev spaces taaft We investigate the best $L_2$ approximation of mixed Sobolev spaces by shallow neural networks with… 2026-09-04 published
  17. ShallowStream: Index Shallow then Answer Deep for Streaming Video Understanding taaft Streaming video understanding is a critical capability for real-world applications, including embod… 2026-09-02 published
  18. SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning taaft The pre-trained Large Language Models (LLMs) can be adapted for many downstream tasks and tailored… 2024-04-23 published
  19. SHELF: A Synthetic Harness for Multi-Task Bibliographic Benchmarking taaft Libraries and archives manage large collections with limited staff and computing budgets, yet commo… 2026-09-02 published
  20. Shopping with a Platform AI Assistant: Who Adopts, When in the Journey, and What For taaft This paper provides some of the first large-scale descriptive evidence on how consumers adopt and u… 2026-03-26 published
  21. Short Horizons and Sparse Concepts: a Mathematical View of the Readout in the J-lens taaft The Jacobian lens (J-lens) has been proposed as a way to read verbalizable representations from lan… 2026-08-26 published
  22. Shortcut Before Circuit: Document Statistics Time In-Context Conflict Resolution taaft When a context asserts two values for one fact, a model commits to a cue -- recency, repetition, po… 2026-08-25 published
  23. Shot2Story: A New Benchmark for Comprehensive Understanding of Multi-shot Videos taaft A short clip of video may contain progression of multiple events and an interesting story line. A h… 2023-12-16 published
  24. Should I Use This Synthetic Dataset for Training? How to Test with Minimal Real Data taaft Digital twins (DTs) and learned world models are increasingly used to generate synthetic data that… 2026-08-28 published
  25. SHSP: Structure-Aware Hierarchical Solution Prediction for Mixed-Integer Linear Programming taaft Mixed-Integer Linear Programming (MILP) is a fundamental optimization paradigm in combinatorial opt… 2026-08-26 published
  26. SIA: A Synthesize-Inject-Align Framework for Knowledge-Grounded and Secure E-commerce Search LLMs with Industrial Deployment JD.com Large language models offer transformative potential for e-commerce search by enabling intent-aware… 2026-03-17 published
  27. SIC-Agents: Benchmarking and Building an Adaptive Simulator for Pediatric Serious Illness Communication Training taaft Pediatric serious illness communication (SIC) is critically important, yet scalable communication t… 2026-08-30 published
  28. Sierpiński--Knopp Wasserstein Distance for Persistence Diagrams and Applications to 2-Wasserstein Approximation taaft This paper introduces the Sierpiński-Knopp (SK) Wasserstein distance, a fast metric between persist… 2026-09-01 published
  29. Signal or Noise? Auditing Rotation-Induced Saliency Drift in Medical and Aerial Imaging taaft Post-hoc saliency maps such as Grad-CAM are increasingly used to audit why a deployed vision model… 2026-09-02 published
  30. Signals: Trajectory Sampling and Triage for Agentic Interactions taaft Agentic applications based on large language models increasingly rely on multi-step interaction loo… 2026-04-01 published
  31. SignMatch: Matching Dictionary Signs to Continuous Sign Language Video taaft The objective of this paper is to match dictionary sign videos to corresponding signs in continuous… 2026-09-01 published
  32. SignRR: Retrieve and Refine Real Motion for Sign Language Production taaft Sign language production (SLP) aims to generate continuous signing motion from spoken language, oft… 2026-08-28 published
  33. SiLR: Structure-Preserving Admission and Process Reward for LLM Tool Agents taaft A runtime gate for an LLM tool agent is usually cast as a filter. In a ReAct loop a rejected propos… 2026-09-04 published
  34. Sim-to-Real of Humanoid Locomotion Policies via Joint Torque Space Perturbation Injection taaft This paper proposes a novel alternative to existing sim-to-real methods for training control polici… 2026-03-23 published
  35. Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control taaft Reinforcement learning achieves strong traffic signal control performance in simulation, yet polici… 2026-09-01 published
  36. SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning taaft The unprecedented surge in Earth observation data volume and diversity has exposed a critical bottl… 2026-08-31 published