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. Parameterized Complexity of $L_p$-Lipschitz Constants for Input Convex Neural Networks and $L_p$-Norm Maximization over Zonotopes taaft Lipschitz constants are a standard way to quantify the sensitivity of neural networks to small inpu… 2026-08-25 published
  2. Parametric Social Identity Injection and Diversification in Public Opinion Simulation StepFun Large language models (LLMs) have recently been adopted as synthetic agents for public opinion simu… 2026-03-17 published
  3. Paritok-4B: Intent-Conditioned Context Compression for Coding Agents taaft Coding agents re-send large file reads and tool outputs to a frontier LLM every turn, and this cont… 2026-08-25 published
  4. Partially Observable Learning for Multi-Platform Dispatch Optimization taaft Instant delivery platforms have become a critical component of urban logistics, increasingly relyin… 2026-08-11 published
  5. ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild taaft Estimating the pose of a moving camera from monocular video is a challenging problem, especially du… 2022-07-19 published
  6. PAS3R: Pose-Adaptive Streaming 3D Reconstruction for Long Video Sequences taaft Online monocular 3D reconstruction enables dense scene recovery from streaming video but remains fu… 2026-03-22 published
  7. PASDiff: Physics-Aware Semantic Guidance for Joint Real-world Low-Light Face Enhancement and Restoration taaft Face images captured in real-world low light suffer multiple degradations-low illumination, blur, n… 2026-03-26 published
  8. PatchBench: Evaluating AI Agents for Vulnerability Patching taaft AI agents have recently demonstrated strong performance in automated vulnerability patching. Howeve… 2026-09-03 published
  9. Pattern Over-Generalization of Knowledge Graph Embedding taaft Knowledge graph embedding (KGE) demonstrates its effectiveness for predicting missing links in know… 2026-09-03 published
  10. PAVE: Predictive Alignment and Value-Guided Evolution for World-Action Policies taaft Direct vision-language-action policies generate continuous robot actions efficiently, but standard… 2026-08-31 published
  11. PAWBench: How Far Are We from Probabilistically Aligned World Modeling? taaft Recent video generation models are increasingly framed as world models. Many physical processes can… 2026-08-27 published
  12. PCoMoE: Shifting MoE Inference from Monolithic Expert Selection to Fine-Grained Path Composition taaft Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by act… 2026-09-01 published
  13. PeaCoK: Persona Commonsense Knowledge for Consistent and Engaging Narratives taaft Sustaining coherent and engaging narratives requires dialogue or storytelling agents to understand… 2023-05-03 published
  14. PEARL: Path-Entity Aligned Relational Learning with Contextual Subgraphs for Inductive Knowledge Graph Completion taaft Inductive knowledge graph completion (IKGC) aims to predict missing links involving entities unseen… 2026-09-02 published
  15. Pelican-VLA 0.5: Attending Before Acting Benefits Generalization taaft In this report, we present Pelican-VLA 0.5, a unified VLA model that integrates vision-language und… 2026-07-07 published
  16. Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization taaft Open-world geo-localization requires models to reason over ambiguous visual cues through multi-step… 2026-08-30 published
  17. Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? taaft Multimodal Large Language Models (MLLMs) are increasingly deployed in human-facing roles where pers… 2026-05-21 published
  18. Perceptually Regularized Diffusion Model for Image Super-Resolution taaft Image super-resolution, which aims to reconstruct high-resolution images from their low-resolution… 2026-09-02 published
  19. Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance taaft We study the dynamics of Stochastic Gradient Descent (SGD), which is known to steer deep neural net… 2026-09-02 published
  20. Performative Privacy: When Differential Privacy Maximizes Utility taaft Privacy-preserving learning is often motivated by the idea that protecting users' data can preserve… 2026-08-28 published
  21. Permutation-Consensus Listwise Judging for Robust Factuality Evaluation Ryquo Large language models (LLMs) are now widely used as judges, yet their decisions can change under pr… 2026-03-20 published
  22. Persona-Execution Separation: An Architecture Pattern for Evolving LLM Agents under Execution Audit taaft Large language model (LLM) agents in governed organizations must let the persona (instructions, ton… 2026-08-27 published
  23. PersonaEdit: Representative Sample Selection for Personalized Model Editing taaft Personalization has attracted growing interest in LLM applications, yet existing retrieval-based ap… 2026-08-28 published
  24. PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems taaft Large language models are increasingly used as agentic workflow executors, yet existing training da… 2026-08-28 published
  25. Personalized and Multi-View Representation for Federated Cold-Start Recommendation taaft Federated recommendation (FedRec) enables personalized modeling without centralizing users' interac… 2026-08-28 published
  26. PersonalQ: Select, Quantize, and Serve Personalized Diffusion Models for Efficient Inference taaft Personalized text-to-image generation lets users fine-tune diffusion models into repositories of co… 2026-03-24 published
  27. PersuaRL: Reinforcement Learning-Driven Multi-Expert Selection for Persuasive Dialogue Generation in Insurance taaft Large Language Models (LLMs) are revolutionizing digital communication by powering conversational a… 2026-09-01 published
  28. PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistency taaft Recent advancements in Text-to-SQL (Text2SQL) emphasize stimulating the large language models (LLM)… 2024-03-13 published
  29. PetQA: Benchmarking Veterinary Knowledge and Clinical Reasoning taaft We introduce PetQA, a Korean long-form question-answering (QA) benchmark for evaluating veterinary… 2026-09-04 published
  30. PGPO: Potential-Guided Policy Optimization for Multi-Turn Agentic Tasks taaft Group-based reinforcement learning (RL) has become an effective paradigm for LLM post-training, but… 2026-09-02 published
  31. Phase Transition Frequency as a Training Time Predictor of Test Accuracy in ResNets taaft The number of discrete class-separability jumps observed during ResNet finetuning is examined empir… 2026-09-04 published
  32. PhaseShift: Topology-Aware Data Harmonization and Model Consolidation Across Signalized Intersections taaft Learned traffic-behavior models are commonly trained separately for each intersection, creating mod… 2026-08-26 published
  33. PhasorNet: Learning Structure from Frequency for Real-Time Stereo Matching taaft Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflecti… 2026-08-30 published
  34. Phi-2: A Small Language Model with Reasoning Capability Microsoft We continue the investigation into the power of smaller Transformer-based language models as initia… 2023-09-11 published
  35. PhiZero: A World Model Built Around Physical Language taaft We introduce PhiZero, a physical world model built around physical language, a compact discrete rep… 2026-07-30 published
  36. PhoenixNest-Video: Evidence-Grounded Multimodal Agent Framework for Automated Video Interview Assessment taaft Interview assessment requires per-criterion judgments grounded in behavioral evidence, yet surging… 2026-09-02 published