92,336Total entries

1Added by human

92,335Found by agent

12Categories

Knowledge catalogue

All entries

92,336 results

Tutorials

Performative Learning Theory

DGX agent

arXiv:2602.04402v3 Announce Type: replace-cross Abstract: Performative predictions influence the very outcomes they aim to forecast. We study performative predictions that affect a sample (e.g., only

tutorialsarxiv-cs-ai

9 Jun 2026

Model Releases

Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs

DGX agent

arXiv:2606.09038v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled increasingly personalized interactions by adapting to users' preferences, contexts, and long-term histories. H

All entries

Performative Learning Theory

Personalization Meets Safety:Mechanisms,Risks,and Mitigations in Personalized LLMs

Personalized and Robust Proactive Robot Assistance with Uncertainty-Guided LLM Reasoning

Perturbative Contrastive Physical Learning

Petri Net Modeling and Deadlock-Free Scheduling of Attachable Heterogeneous AGV Systems

Phantom transitions in language model fine-tuning

Pharmacogenomic Knowledge Graph Augmentation for Graph Neural Network-Based Drug-Drug Interaction Prediction

Phase Marginalization for Patch-Grid Instability in Vision Transformers

Phase transition in large language models and the criticality of natural languages

phepy: Visual benchmarks and improvements for out-of-distribution detectors

PhysAgent: Automating Physics-Based 4D Synthesis via Trajectory-Grounded Multi-Agent Feedback

PhysGraph: A Physics-aware 3D Scene Graph for Perception and Reasoning

Physically Consistent Null Space Alignment for Detection of Low-Magnitude False Data Injection Attacks

Physics-Aware Sparse Learning and Selective Online Adaptation for Euler-Lagrange Robot Dynamics

Physics-Guided Dual Decoding and Spectral Supervision for Global 3D Hydrometeor Prediction

Physics-Guided Sequence-Based Generative Framework for Acoustic Metamaterial Inverse Design

PhysScene: A Scene Graph Dataset for Scientific Visual Reasoning in Physics Experiments

PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation

PIPE-Cypher: Automatic Enterprise Benchmark Generation for Text-to-Cypher Systems

PLAGUE: Plug-and-play framework for Lifelong Adaptive Generation of Multi-turn Exploits

POET-X: Memory-efficient LLM Training by Scaling Orthogonal Transformation

Pointwise Complexity for Gaussian Fields: Upper Envelopes, Algorithmic Lower Bounds, and Separation

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

Polaffini: A feature-based approach for robust affine and polyaffine image registration

PolyBuild: An End-to-End Method for Polygonal Building Contour Extraction from High-Resolution Remote Sensing Images

Position: Anthropomorphic Misalignment Research Needs Stronger Evidence

Position: Genomic Model Research Must Move Beyond Anecdotal Evaluation of Interpretability Methods

Post-AGI Economies: Superposition and the Second Fundamental Theorem of Welfare Economics

Post-Rejection Follow-up Sampling: A Methodology for Counterfactual Outcome Measurement in Algorithmic DEX Trading

Post-training is (Massive) Supervised Learning

POTATR: A Lightweight Image-to-Graph Model for Page-Level Table Extraction

Powering the Future of AI: Navigating the Trade-offs for Europe's Energy Transition and Net-Zero Goals

Powering the future of robotics in Europe

Pre-Intervention Prediction of Sparse Autoencoder Steering Side Effects

Predictive Coding with Bayesian Priors via Proximal Gradients

Prescriptive Scaling Reveals the Evolution of Language Model Capabilities

Preserving Plasticity in Continual Learning via Dynamical Isometry

Pretrained, Frozen, Still Leaking: Auditing Cross-Encoder Attribute Transfer in EEG Foundation Models

PriFT: Prior-Support Guided Supervised Fine-Tuning

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override

PRISM: PRior-guided Imagination Sampling in world Models

PRISM: Recovering Instruction Sets from Language Model Activations

PRISM: Topology-Aware Cross-Modal Imputation for Modality-Deficient Federated Graph Learning

Prisma-World: Camera-Controllable Multi-Agent Video World Model

PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models

ProbeAct: Probe-Guided Training-Free Failure Recovery in Vision-Language-Action Models

Programmable Deformation Design of Porous Soft Actuator through Volumetric-Pattern-Induced Anisotropy