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. Scalable Kronecker-Fisher Approximation: Efficient Hessian Analysis for Billion-Parameter Language Models Compression taaft In this paper, we propose a scalable Kronecker-based approximation that captures cross-layer intera… 2026-09-02 published
  2. Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models taaft Spatial reasoning focuses on locating target objects based on spatial relations in 3D scenes, which… 2026-03-25 published
  3. Scalable Question-Centric Text-to-Image Evaluation: Reliable Ranking, Fine-Grained Diagnosis, and Cost-Aware Routing taaft Modern text-to-image (T2I) models often have similar total scores but different strengths, making p… 2026-08-25 published
  4. Scale-based Approach for Active Wildfire Segmentation on Satellite Imagery taaft Active wildfire mapping from satellite imagery is challenging due to the sparse and highly imbalanc… 2026-09-01 published
  5. Scaled Idempotence in Transformer Attention: Paired OV Geometry and Shared-Value Algebras taaft We identify a recurrent algebraic regularity in Transformer attention: a sparse subset of effective… 2026-09-01 published
  6. Scaling Autoregressive Models for Content-Rich Text-to-Image Generation Google Research We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity p… 2022-06-22 published
  7. Scaling Language Models: Methods, Analysis & Insights from Training Gopher taaft Language modelling provides a step towards intelligent communication systems by harnessing large re… 2021-12-08 published
  8. Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence taaft Recent advances in large reasoning models (LRMs) have shown that reinforcement learning with verifi… 2026-08-31 published
  9. Scaling Laws and Interpretability of Learning from Repeated Data taaft Recent large language models have been trained on vast datasets, but also often on repeated data, e… 2022-05-21 published
  10. Scaling Laws for Neural Language Models OpenAI We study empirical scaling laws for language model performance on the cross-entropy loss. The loss… 2020-01-23 published
  11. Scaling Laws, Tabular Data and Actuarial Ratemaking Models taaft Scaling laws in modern deep learning describe how held-out loss improves as model capacity, trainin… 2026-09-02 published
  12. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet Anthropic Used Sparse Autoencoders (SAEs) to "de-mix" the activations of Claude 3 Sonnet, identifying million… Anthropic
  13. Scaling Near-Optimal SFT-RL Annotation Budget Allocation from Small to Large LLMs taaft How to divide a fixed annotation budget between supervised fine-tuning (SFT) and reinforcement lear… 2026-09-01 published
  14. SCAPES: Semantically Conditioned Autoregressive Prior for Environmental Sounds taaft As generative audio models grow in complexity, the computational and ecological costs of synthesizi… 2026-09-04 published
  15. ScenePilot: Grow-and-Repair Policy for Text-Driven 3D Indoor Scene Generation taaft Text-driven 3D indoor scene generation has advanced from dataset-bound layout modeling to open-voca… 2026-08-31 published
  16. ScentEcho: Exploring Adsorbent Materials for Accurate Odor Collection and Playback taaft Delivering odors that feel realistic and recognizable remains a core challenge for olfactory intera… 2026-08-26 published
  17. Schema on the Inside: A Two-Phase Fine-Tuning Method for High-Efficiency Text-to-SQL at Scale taaft Applying large, proprietary API-based language models to text-to-SQL tasks poses a significant indu… 2026-03-25 published
  18. Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation taaft Generative modeling directly on geometric manifolds can avoid errors introduced by flattening non-E… 2026-09-02 published
  19. Schrödinger Bridges over Kinetic Swarming Models taaft Paradigmatic interaction models explain how collective behaviors can emerge in complex systems from… 2026-08-26 published
  20. SchurVINS: Schur Complement-Based Lightweight Visual Inertial Navigation System taaft Accuracy and computational efficiency are the most important metrics to Visual Inertial Navigation… 2023-12-04 published
  21. Science sandboxes measure the scientific capability of AI agents taaft Scientific progress depends not only on finding solutions, but on learning the rules that explain w… 2026-08-31 published
  22. ScienceFlow: A long-horizon agent for ML research, scientific discovery and beyond taaft Enabling LLM agents to sustain productive, stable, and goal-aligned research over extended horizons… 2026-08-14 published
  23. SciToolAgent-Evo: An Ontology-Aware Self-Evolving Agent for Open-World Scientific Tool Acquisition taaft Large language model (LLM) agents have been increasingly adopted in scientific research for organiz… 2026-07-30 published
  24. SCLA: Automated Smart Contract Summarization via LLMs and Control Flow Prompt taaft Smart contract code summarization is crucial for efficient maintenance and vulnerability mitigation… 2024-02-07 published
  25. SCOTT: Self-Consistent Chain-of-Thought Distillation taaft Large language models (LMs) beyond a certain scale, demonstrate the emergent capability of generati… 2023-05-03 published
  26. SCULPT: Training Edge Vision Models for Post-Training Quantization Readiness taaft Edge vision models are difficult to deploy on resource-constrained hardware, making low-bit post-tr… 2026-09-01 published
  27. SCX Router: Streaming Zero-Shot Model Selection with a Decoder-KV Classifier and a Real-World Task Ontology taaft The rapid proliferation of large language models (LLMs) and the growing diversity of their applicat… 2026-09-02 published
  28. SDARE-Bench: Evaluating Large Language Models on Conversational Stigma Detection and Response in Dyadic and Group Dialogue taaft Large Language Models (LLMs) are increasingly used in advice seeking and decision making that may a… 2026-09-01 published
  29. SDDF: Specificity-Driven Dynamic Focusing for Open-Vocabulary Camouflaged Object Detection taaft Open-vocabulary object detection (OVOD) aims to detect known and unknown objects in the open world… 2026-03-27 published
  30. SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis taaft We present SDXL, a latent diffusion model for text-to-image synthesis. Compared to previous version… 2023-07-04 published
  31. SEAL: Reinforcing Global Safety in Mixture-of-Experts through Shared Expert ALignment taaft Mixture-of-Experts (MoE) is a scaling architecture for large language models that activates only a… 2026-09-02 published
  32. SeamFlow: Structure-Aware Flow Matching on Edge Probabilities for Artist-Like UV Unwrapping taaft 3D surface cutting and UV unwrapping are fundamental problems in computer graphics. Traditional geo… 2026-09-04 published
  33. Search2Motion: Training-Free Object-Level Motion Control via Attention-Consensus Search Intel We present Search2Motion, a training-free framework for object-level motion editing in image-to-vid… 2026-03-17 published
  34. Searching For Music Mixing Graphs: A Pruning Approach taaft Music mixing is compositional -- experts combine multiple audio processors to achieve a cohesive mi… 2024-06-03 published
  35. SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking taaft Flat retrieval-augmented generation treats a corpus as a bag of chunks, discarding document hierarc… 2026-08-30 published
  36. SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring taaft Federated Learning (FL) enables privacy-aware distributed training, yet gradient updates remain exp… 2026-08-27 published