All entries

PAFO: Pareto Fairness Optimization for Personalized Reward Modeling

arXiv:2606.07988v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on reward models to align their outputs with diverse user preferences. While personalized reward models a

Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing

DGX agent

arXiv:2606.07558v1 Announce Type: cross Abstract: Purpose: Digitization projects in the humanities produce vast, heterogeneous archives of historical documents, making manual sorting impractical at sc

researcharxiv-cs-ai

9 Jun 2026

PAI: Preserving Amplitude Information in Representation-Based Time-Series Anomaly Detection

arXiv:2606.08935v1 Announce Type: cross Abstract: Representation-based time-series anomaly detection algorithms significantly outperform other methods on diverse anomaly detection tasks. However, we n

local-aiarxiv-cs-ai

PairAlign: A Framework for Sequence Tokenization via Self-Alignment with Applications to Audio Tokenization

arXiv:2605.06582v2 Announce Type: replace Abstract: Many operations on sensory data -- comparison, memory, retrieval, and reasoning -- are naturally expressed over discrete symbolic structures. In lan

safetyarxiv-cs-lg

PairWise Image Finder: An Open-source Tool for Finding Visually Aligned Street-Level Image Pairs for Urban Perception Studies

arXiv:2606.08795v1 Announce Type: new Abstract: Change detection and scene recognition techniques have been widely applied to Street View Imagery (SVI) to understand changes in scenes across the years

safetyarxiv-cs-cv

Pantheon360: Taming Digital Twin Generation via 3D-Aware 360{eg} Video Diffusion

arXiv:2605.25449v2 Announce Type: replace Abstract: Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constr

researcharxiv-cs-cv

Parameter Tuning with Generalization Guarantees for GPU-Accelerated Linear Programming

model-releasesarxiv-cs-lg

arXiv:2606.08638v1 Announce Type: cross Abstract: Recent research has developed practical, parallelizable first-order methods for large scale linear programming, but performance is highly dependent on

Industry

Paramount accuses Netflix of 'scorched-earth campaign' against WBD merger

Paramount's chief legal officer accused Netflix of conducting a 'scorched-earth campaign' to derail the merger in a letter to the Department of Justice . The letter claimed Netflix is trying to 'poiso

industryars-technica

Agents

Parsing a document accurately is one thing. Proving where every value came from is another. When a compliance team reviews an AI extraction,…

Parsing a document accurately is one thing. Proving where every value came from is another. When a compliance team reviews an AI extraction, or an auditor needs to sign off on a figure pulled from a f

agentsjerry-liu--x

Partial Identification under Missing Data Using Weak Shadow Variables from Pretrained Models

arXiv:2602.16061v2 Announce Type: replace-cross Abstract: Estimating population quantities such as mean outcomes from user feedback is fundamental to platform evaluation and social science, yet feedba

Partially Performative Prediction

arXiv:2606.07890v1 Announce Type: new Abstract: Performative prediction studies feedback loops that arise when predictive models are deployed in consequential domains. In these settings, deploying a m

Path Planning Using Deep Deterministic Policy Gradient: A Reinforcement Learning Approach

arXiv:2606.07855v1 Announce Type: new Abstract: Path-planning for autonomous vehicles in threat-laden environments is a fundamental challenge because the problem is nonlinear and nonconvex even in sim

safetyarxiv-cs-ro

PathoSage: Towards Multi-Source Evidence Adjudication in Pathology via Experience-Aware Agentic Workflow

arXiv:2606.07549v1 Announce Type: new Abstract: Recent advances in Multimodal Large Language Models (MLLMs) and agent workflows have shown strong promise for computational pathology, yet reliable patc

Payoff scaling shapes cooperation in LLM agents across languages

arXiv:2601.19082v2 Announce Type: replace Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, coordinate, and act on behalf of users. Whether they coo

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

arXiv:2606.09348v1 Announce Type: new Abstract: Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final

safetyarxiv-cs-lg

PEDRA: Evaluating the Realism of Pedestrian Dynamics in Video Generation

model-releasesarxiv-cs-cv

arXiv:2510.20182v2 Announce Type: replace Abstract: Pedestrian simulation traditionally relies on expert-tuned, hand-crafted models that limit scalability and generalization. Meanwhile, large-scale vi

Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain

arXiv:2606.08059v1 Announce Type: new Abstract: Humanoid behavior foundation models aim to acquire reusable whole-body control policies from broad human motion priors, enabling a single controller to

local-aiarxiv-cs-ro

PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing

model-releasesarxiv-cs-cv

arXiv:2606.07661v1 Announce Type: new Abstract: Parsing historical documents with complex, non-standard layouts remains a fundamental bottleneck in large-scale archival digitization. Unlike modern typ

Tutorials

Performative Learning Theory

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

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

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

Applications

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

arXiv:2606.08458v1 Announce Type: new Abstract: Proactive robot assistance in household environments requires accurate prediction of human activities and object usage under dynamic and noisy condition

applicationsarxiv-cs-ro

Agents

Perturbative Contrastive Physical Learning

arXiv:2606.09756v1 Announce Type: new Abstract: Responses to perturbations are key to understanding physical systems. The ability to contrast such responses by comparing how a system reacts under slig

agentsarxiv-cs-lg

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

arXiv:2508.00724v2 Announce Type: replace-cross Abstract: The increasing demand for flexible automation has accelerated the adoption of heterogeneous automated guided vehicles (AGVs). This work invest

safetyarxiv-cs-ro

Phantom transitions in language model fine-tuning

arXiv:2606.07559v1 Announce Type: cross Abstract: Fine-tuning a language model on contexts whose correct completion has a near-synonym competitor often fails silently. The cross-entropy loss decreases

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

arXiv:2606.07698v1 Announce Type: cross Abstract: Graph neural networks (GNNs) applied to drug-drug interaction (DDI) prediction rely exclusively on molecular structure encoded as SMILES-derived graph

Phase Marginalization for Patch-Grid Instability in Vision Transformers

arXiv:2606.08132v1 Announce Type: new Abstract: Vision Transformers operate on fixed patch grids, which can introduce phase-dependent instability for dense prediction: changing the patch partition can

researcharxiv-cs-cv

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

model-releasesarxiv-cs-lg

arXiv:2406.05335v3 Announce Type: replace-cross Abstract: Generation of text and speech in natural languages can be modeled as a stochastic process. This idea dates back to the seminal work of Markov

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

model-releasesarxiv-cs-lg

arXiv:2503.05169v2 Announce Type: replace Abstract: Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on i

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

arXiv:2606.08688v1 Announce Type: cross Abstract: Achieving fully automated, physically plausible 3D motion synthesis is a core objective in graphics and generative AI. However, configuring complex en

local-aiarxiv-cs-cv

Applications

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

arXiv:2606.08655v1 Announce Type: cross Abstract: To perform a wide range of daily tasks, robots need to construct a 3D representation that is semantically rich, physically grounded, and structured en

applicationsarxiv-cs-cv

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

arXiv:2606.08473v1 Announce Type: new Abstract: False data injection attacks (FDIAs) introducing small measurement perturbations can still cause large deviations in power system state estimation when

safetyarxiv-cs-lg

Applications

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

arXiv:2606.09640v1 Announce Type: new Abstract: Accurate dynamics models are essential for model-based robotic control, yet nominal Euler--Lagrange models often become inaccurate in the presence of pa

applicationsarxiv-cs-ro

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

arXiv:2606.08563v1 Announce Type: new Abstract: While global data-driven models excel at predicting continuous atmospheric variables, three-dimensional hydrometeor forecasting remains challenging due

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

arXiv:2606.09266v1 Announce Type: cross Abstract: Acoustic metamaterial (AMM) inverse design is particularly challenging for broadband target responses due to acoustic dispersion: a structure that mat

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

arXiv:2606.09368v1 Announce Type: cross Abstract: Scene Graphs (SGs) provide structured representations of visual scenes by modeling objects and their pairwise relationships. Despite recent progress,

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

arXiv:2603.11917v2 Announce Type: replace Abstract: Real-time, on-device segmentation is critical for latency-sensitive and privacy-aware applications such as smart glasses and Internet-of-Things devi

local-aiarxiv-cs-cv

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

arXiv:2606.08481v1 Announce Type: cross Abstract: Enterprise property graphs vary widely in schema structure, internal terminology, domain assumptions, governance constraints, and user interaction pat

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

arXiv:2510.17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate. With the advent of agentic workflows, multi-turn dialogue has become the de

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

arXiv:2603.05500v2 Announce Type: replace-cross Abstract: Efficient and stable training of large language models (LLMs) remains a core challenge in modern machine learning systems. To address this cha

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

arXiv:2606.07931v1 Announce Type: cross Abstract: We prove a variance-aware pointwise majorizing-measure theorem for centered Gaussian processes. Classical generic chaining characterizes the scalar qu

POISE: Position-Aware Undetectable Skill Injection on LLM Agents

arXiv:2606.07943v1 Announce Type: cross Abstract: Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A pr

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

arXiv:2602.17337v2 Announce Type: replace Abstract: In this work we present Polaffini, a robust and versatile framework for anatomically grounded registration. Medical image registration is dominated

safetyarxiv-cs-cv

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

arXiv:2606.08920v1 Announce Type: cross Abstract: Extracting building polygon contours from high-resolution remote sensing images is a fundamental task for various mapping applications. However, the p

Position: Anthropomorphic Misalignment Research Needs Stronger Evidence

arXiv:2606.07612v1 Announce Type: cross Abstract: We argue that many Anthropomorphic Misalignment Research (AMR) studies need stronger evidence to ensure that they can provide a robust foundation for

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

arXiv:2606.07607v1 Announce Type: new Abstract: Advances in machine learning and computational power have unlocked the predictive potential of the human genome, yet biologists now demand that these mo

local-aiarxiv-cs-lg

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

arXiv:2606.08267v1 Announce Type: cross Abstract: The classical Second Welfare Theorem decentralizes any Pareto efficient allocation through prices and transfers under convexity and regularity. In pos

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

arXiv:2606.08228v1 Announce Type: cross Abstract: Algorithmic trading systems on decentralised exchanges (DEXs) reject most candidate tokens they evaluate. The counterfactual outcome of rejected candi

Tutorials

Post-training is (Massive) Supervised Learning

arXiv:2606.07527v1 Announce Type: cross Abstract: The prevailing paradigm for training LLMs has evolved to rely on a massive post-training phase consisting of SFT and RL. In this position paper, we ar

tutorialsarxiv-cs-ai