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. Consistency as Regularization for Unsupervised Shadow Removal taaft Shadow removal is an important preprocessing step for many vision tasks, yet existing supervised me… 2026-09-01 published
  2. Consistency Beyond Contrast: Enhancing Open-Vocabulary Object Detection Robustness via Contextual Consistency Learning taaft Recent advances in open-vocabulary object detection focus primarily on two aspects: scaling up data… 2026-03-27 published
  3. Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion taaft Consistency Models (CM) (Song et al., 2023) accelerate score-based diffusion model sampling at the… 2023-10-01 published
  4. ConsRoute:Consistency-Aware Adaptive Query Routing for Cloud-Edge-Device Large Language Models taaft Large language models (LLMs) deliver impressive capabilities but incur substantial inference latenc… 2026-03-22 published
  5. Constant Individual Regret in General Games taaft Uncoupled no-regret dynamics provide a decentralized route to equilibrium, but prior guarantees for… 2026-08-31 published
  6. Constant regret in general games via higher-order optimism taaft We introduce an uncoupled learning algorithm which, when employed by all players of an arbitrary $N… 2026-09-03 published
  7. Constitutional AI: Harmlessness from AI Feedback Anthropic As AI systems become more capable, we would like to enlist their help to supervise other AIs. We ex… 2022-12-15 published
  8. Constrained Entity Selection under Partial Knowledge for LLM-Based Knowledge Graph QA taaft Large language models are increasingly used for knowledge graph question answering (KGQA), but can… 2026-08-25 published
  9. Constrained Hyperparameter Optimization for Streaming Data taaft Optimization of hyperparameters is a critical factor to obtain optimal model performance. While exi… 2026-08-25 published
  10. Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent taaft Evaluation of medical artificial intelligence agents remains predominantly answer-centric, assessin… 2026-09-04 published
  11. Context as an Environment: Programmatic Context Management for Long-Horizon Agents taaft LLM agents increasingly take on long-running tasks whose history grows far beyond a single model co… 2026-08-21 published
  12. Context Inference Attacks Without Jailbreaks taaft Agentic AI systems are increasingly deployed to process sensitive data at inference time, such as h… 2026-08-31 published
  13. Context Window Failures in Relational Foundation Models taaft Recent Relational Deep Learning architectures have been proposed as foundation models for multi-tab… 2026-08-31 published
  14. ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models taaft Text-to-image models learn associations between concepts - in the case of this paper, people's prof… 2026-08-30 published
  15. ContextLeak: Exfiltrating LLM Agent Context via Malicious Tools taaft Exfiltrating an LLM agent's runtime context -- such as the user prompt, execution trajectory, and t… 2026-08-28 published
  16. ContextPilot: Teaching Agents for Proactive Context Management via Fine-grained RL taaft Long-horizon agentic tasks require large language models (LLMs) to iteratively retrieve, integrate,… 2026-08-28 published
  17. Continual Field-Adaptive Models (CFAMs) for Post-Deployment Physical AI taaft Unattended interactive autonomy - machines that step into danger in place of humans and complete ta… 2026-09-03 published
  18. Continual Graph Memory for Adaptive Recommendation under Intent Drift taaft This paper studies adaptive recommendation under intent drift, where feedback from each recommendat… 2026-09-04 published
  19. CONTINUITY: Security-Context Contracts for Composable LLM Agent Controls taaft LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, prot… 2026-09-04 published
  20. Continuous Actions from Discrete Minds: Latent-Aligned Planning for End-to-End Autonomous Driving taaft Bridging the gap between the discrete reasoning of Vision-Language Models and the continuous, physi… 2026-09-03 published
  21. Contrastive Branch Policy Optimization taaft Reinforcement learning with verifiable rewards (RLVR) enables language models to learn multi-turn i… 2026-08-25 published
  22. Contrastive Explanations in Quantitative Bipolar Argumentation Frameworks taaft Argumentation frameworks are useful tools for representing and reasoning with information in a vari… 2026-09-02 published
  23. Control-Data Flow Separation: Stable Prompt Optimization in Multi-Agent LLMs taaft Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serv… 2026-09-01 published
  24. Controlling and Assessing Appropriate Persona Use in LLM-based Dialogue Generation taaft In persona-based dialogue generation (PDG), LLMs often overuse persona attributes by incorporating… 2026-09-04 published
  25. Convergence rates for the RMSprop optimizer with full control of the hyperparameters taaft Popular adaptive stochastic gradient descent (SGD) methods to train artificial intelligence (AI) sy… 2026-08-31 published
  26. Convergence Theory of Knowledge Distillation in Asynchronous P2P Gossip Learning Network taaft Decentralized, serverless learning increasingly connects devices running different architectures, w… 2026-09-01 published
  27. Conversation Coach: A Voice-enabled AI System that Helps Practice Difficult Workplace Conversations taaft Effective manager-employee communication is critical for retaining high performers and developing u… 2026-08-31 published
  28. Converse and Collision-Based Achievability for Node Localization with Hybrid Distance-Spectral Graph Positional Encodings taaft Graph positional encodings are widely used in graph neural networks and graph Transformers, yet it… 2026-08-31 published
  29. Cooperative Multi-Task Semantic Communication for Joint Classification and Regression Tasks taaft Multi-Task semantic communication (SemCom) prioritizes simultaneous execution of multiple tasks ove… 2026-09-03 published
  30. Coordinating the Unknown Lipschitz Constant in Multiplayer Bandits taaft Motivated by decentralized applications, we study cooperative multi-agent bandits in continuous (Li… 2026-08-11 published
  31. CopyShield: A Cross-Level Benchmark of Copyright Defenses in LLMs taaft Large language models can reproduce memorized text verbatim, yet copyright defenses are usually eva… 2026-09-01 published
  32. CORAL: An LLM-Native Harness for Production Recommender Systems taaft Production recommender systems shape what billions of people see, and sustaining their performance… 2026-09-02 published
  33. CordisBench: Can Language Models Reason About Component Lifecycles in Dynamic Agent Harnesses? taaft Dynamic agent harnesses let language models change the software that shapes their own execution. Th… 2026-09-01 published
  34. CoRe-MoE: Compact Reusable MoE for Continual Multimodal Instruction Tuning taaft Continual multimodal instruction tuning requires multimodal large language models to acquire new ta… 2026-08-28 published
  35. CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation taaft MLLM-based embedding models remain limited in compositional retrieval, often failing to distinguish… 2026-09-03 published
  36. CoRe: Joint Optimization with Contrastive Learning for Medical Image Registration taaft Medical image registration is a fundamental task in medical image analysis, enabling the alignment… 2026-03-24 published