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. Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety taaft Tool-using LLM agents extend security risks beyond generated text to actions that affect external s… 2026-08-26 published
  2. RecalibrateGPT: AI Fatigue Resilient Conversational Interfaces taaft Large language models are powerful, but their interfaces often devolve into a type $\rightarrow$ re… 2026-09-01 published
  3. RECAST: Recent & Context-Aware Sampling for Test-Time Adaptation in Streaming Biosignals taaft Streaming biosignals vary across subjects and drift over time, so population-trained models lose ac… 2026-08-28 published
  4. ReCAST: Restoration-aware Cascaded Stage-wise Training for Obfuscated SMS Risk Classification taaft Fraudulent messages sent via Short Message Service (SMS) are increasingly obfuscated to evade cost-… 2026-09-04 published
  5. RecKAN: Kolmogorov-Arnold Networks with a Learnable Recursive Polynomial Basis taaft Kolmogorov--Arnold Networks (KANs) replace the fixed scalar weights of a standard network with lear… 2026-09-01 published
  6. Reconciling Kinesthetic Mismatches: A Somatic Alignment Mindset for Musical Body Transformation taaft Mastering musical performance requires precise multisensory coordination, yet learners encounter a… 2026-09-02 published
  7. Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization taaft Outcome-based reinforcement learning provides verified feedback for language-model agents, but assi… 2026-08-31 published
  8. Reconstructing Humans and Objects in Interaction using Large Reconstruction Models taaft Estimation of Human-Object Interactions in 3D (3D HOI) is a fundamental problem in 3D computer visi… 2026-08-27 published
  9. Reconstructing Quantum Dot Charge Stability Diagrams with Diffusion Models taaft Efficiently characterizing quantum dot (QD) devices is a critical bottleneck when scaling quantum p… 2026-03-27 published
  10. Reconstructing the Right Episode: Evaluating Interleaved Conversational Memory Beyond Long Context taaft Conversations with chat assistants increasingly span many topics in a single long-running thread, c… 2026-08-26 published
  11. Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning taaft Video Object-Centric Learning seeks to decompose raw videos into a small set of object slots, but e… 2026-03-24 published
  12. Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach taaft Music recommendation relies primarily on two signals: user-item interactions, which fail in the col… 2026-08-27 published
  13. Recurrence Is Not Enough: Causally Validating Multilingual SAE Translation Features in Gemma 2 and 3 taaft Sparse autoencoder (SAE) features are increasingly used to explain and steer language-model behavio… 2026-09-04 published
  14. RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges taaft LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving… 2026-08-25 published
  15. Recursive Criticality of AI Self-Improvement taaft AI is increasingly used in the R\&D process that produces future AI systems. We study the condition… 2026-08-31 published
  16. Recursive Synthesis for Long-Horizon Terminal Tasks taaft High-quality long-horizon training data for terminal agents is expensive to produce, often costing… 2026-08-05 published
  17. Recursive Value Learning for Long-Horizon Offline Goal-Conditioned RL taaft Scaling offline goal-conditioned reinforcement learning (GCRL) to long-horizon tasks is difficult b… 2026-09-02 published
  18. ReCycle: Resilient Training of Large DNNs using Pipeline Adaptation taaft Training large Deep Neural Network (DNN) models requires thousands of GPUs over the course of sever… 2024-05-22 published
  19. ReDiffuse: Rotation Equivariant Diffusion Model for Multi-focus Image Fusion taaft Diffusion models have achieved impressive performance on multi-focus image fusion (MFIF). However,… 2026-03-22 published
  20. ReDiPrune: Relevance-Diversity Pre-Projection Token Pruning for Efficient Multimodal LLMs taaft Recent multimodal large language models are computationally expensive because Transformers must pro… 2026-03-25 published
  21. Reducing Catastrophic Risk from AI with Systematic Monitoring and Evaluation of Rogue AI Progression taaft This article presents a structured framework of behavioral indicators that may signal progression t… 2026-09-02 published
  22. REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation taaft As language-model compute continues to scale, high-quality training data is becoming an increasingl… 2026-08-31 published
  23. REFACTOR-VLA: Unsupervised Library Learning of Typed Motor Programs taaft Most vision-language-action (VLA) models -- OpenVLA, $π_0$, RT-2, RDT-1B -- are monolithic: they em… 2026-09-01 published
  24. RefactorPlatform: An Open-Source Harness for Controlled Evaluation of Repository-Scale Refactoring Agents taaft Repository-scale refactoring requires coding agents to propagate a single change across many interd… 2026-09-04 published
  25. RefDiT: Local Attribute Guidance in Reference-Based Image Generation taaft Personalization models generate new images guided by a few subject references, while style transfer… 2026-09-04 published
  26. RefineRank: Joint Box Refinement and Ranking for Surgical Spatio-Temporal Grounding taaft Surgical spatio-temporal grounding (STG) requires locating, at each video time specified by a proce… 2026-08-25 published
  27. Refining Heuristic-Based Bitcoin Address Clustering with Graph Neural Networks taaft Bitcoin's pseudonymous nature makes it challenging to analyze user-level activity, since a single u… 2026-09-01 published
  28. Reflect-SQL: A Self-Reflection Based Framework for Text-to-SQL taaft Democratizing data access through natural language is a crucial goal for modern enterprises, but th… 2026-09-01 published
  29. Reflexion: Language Agents with Verbal Reinforcement Learning Extropic Large language models (LLMs) have been increasingly used to interact with external environments (e.… 2023-03-20 published
  30. Refusal geometry reflects refusal training: diverse refusal prefixes can raise stable rank and weaken refusal vector ablation attacks taaft Refusal training protects AI models from jailbreaks by training models to decline unsafe queries, r… 2026-08-26 published
  31. Refuse without Refusal: A Structural Analysis of Safety-Tuning Responses for Reducing False Refusals in Language Models taaft Striking a balance between helpfulness and safety remains a fundamental challenge in aligning large… 2026-09-04 published
  32. Regime-Aware Portfolio Management via Retrieval-Augmented LLM-Guided Expert Switching taaft Financial markets are inherently non-stationary, making the effectiveness of individual portfolio-m… 2026-08-28 published
  33. RegionCache: Semantic-Aware Region Reuse for Efficient Multi-Turn Image Generation taaft Real-world image generation often involves multi-turn editing, where users iteratively modify small… 2026-08-30 published
  34. RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments taaft Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies,… 2026-09-04 published
  35. Regression Transformer enables concurrent sequence regression and generation for molecular language modelling IBM Introduced a "language model" that can perform both molecular property prediction and molecular gen… IBM
  36. REIGN: Refurbished Embeddings with Integrated Guidance Networks for Efficient Context-Length Scaling taaft Dense retrieval over long documents is expensive. Token-level encoders scale quadratically in seque… 2026-08-30 published