AI News

The New Social Image: How AI Competency and AI Proactivity Influence Self- and Peer-Perceptions in the Workplace (arxiv.org)

SEMBridge: Tagless-Final Program Semantics with Weakest-Precondition and Bounded-Checking Interpretations (arxiv.org)

Continuous Reasoning for Vision-Language-Action (arxiv.org)

Short-form Text Rewriting with Phi Silica (arxiv.org)

ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems (arxiv.org)

Flow Matching for Convective-Scale Precipitation Downscaling (arxiv.org)

A combination of noise and bilateral filters achieve supralinear and scalable adversarial robustness in CNNs (arxiv.org)

CityTrajBench: A Unified Benchmark for City-Scale Vehicle Trajectory Generation (arxiv.org)

Self-Improving Small Object Grounding in LVLMs (arxiv.org)

Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization (arxiv.org)

Regularized Large Neighborhood Search (arxiv.org)

Measurement Geometry and Design for Trustworthy Generative Inverse Problems (arxiv.org)

Repurposing Adversarial Perturbations for Continual Learning: From Defense to Active Alignment (arxiv.org)

Riemannian Gradient Descent for Low-Rank Architectures (arxiv.org)

Civilizational Metamaterials: Engineering Coordination Under Capability Gradients and Structural Turbulence (arxiv.org)

Effects of Varying LLM Access on Essay Writing Behavior (arxiv.org)

StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement (arxiv.org)

Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models (arxiv.org)

Entropy Minimization without Model Collapse: Mitigating Prediction Bias in Medical Imaging (arxiv.org)

When Do Attention Circuits Form? Developmental Trajectories of Capability and Attention-Sink Emergence Across Three 1B-ClassArchitectures (arxiv.org)

TabPrep: Closing the Feature Engineering Gap in Tabular Benchmarks (arxiv.org)

Learning Implicit Bias in Generative Spaces for Accelerating Protein Dynamics Emulation (arxiv.org)

Synthetic Data from Cross-Domain Events for Large-Scale Recommendation Systems (arxiv.org)

Real2SAM2Real: Generative 3D Caches as Complementary Context for Video Diffusion (arxiv.org)

Bridging Reasoning Trajectories in On-Policy Distillation via Near-Future Guidance (arxiv.org)

DRL-Based Pose Control for Double-Ackermann Robots Under Actuation Uncertainties (arxiv.org)

LLMs Need Encoders for Semantic IDs Too (arxiv.org)

IntraShuffler: A Privacy Preserving Framework for Heterogeneous DP Federated Learning (arxiv.org)

Isolating LLM Lexical Bias: A Curation-Free Triangulated Metric for Preference-Stage Learning (arxiv.org)

A Local Perturbation Theory for Cross-Domain Interference and Recovery in Multi-Domain RL (arxiv.org)

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters (arxiv.org)

Drifting Preference Optimization for One-Step Generative Models (arxiv.org)

Guidance for Low-Level Perceptual Editing in Unconditional Diffusion Models (arxiv.org)

Agentic Authoring of Interactive Multiview Visualizations in Genomics (arxiv.org)

SUPREME: A Multi-GPU Framework for Reproducible Image Unlearning Method Evaluation (arxiv.org)

A Distribution-Free Framework for Rewrite-Based Human-text Detection via Knockoff Filtering (arxiv.org)

Masking Stale Observations Helps Search Agents -- Until It Doesn't: A Regime Map and Its Mechanism (arxiv.org)

AgentxGCore: Agentic AI for Next-Generation Mobile Core Network (arxiv.org)

Detect Before You Leap: Mirage Detection in Vision-Language Models (arxiv.org)

Machine Learning-Based Bitcoin Trading Under Transaction Costs: Evidence From Walk-Forward Forecasting (arxiv.org)

ChWDTA: Channel-wise Wavelet-Domain Transformer Attention and Entropy Modeling for Learned Image Compression (arxiv.org)

Positional Encodings Anchor Spatial Structure in Vision Transformers: A Geometric Perspective on Robustness (arxiv.org)

Modeling Robotics Dataset Construction as an Artifact-Based Build Process (arxiv.org)

CodeCytos: AI-assisted spatial molecular imaging analysis via code-augmented agent action space (arxiv.org)

Pre-Deployment Robustness Stress Testing for CT Segmentation Systems Using Clinically Motivated Multi-Corruption Augmentation (arxiv.org)

V-LynX: Token Interface Alignment for Video+X LLMs (arxiv.org)

Skill or Skip? Learning Selective Skill Invocation in Agentic Tasks via Dual-Granularity Preference Learning (arxiv.org)

PaCo-VLA: Passivity-Shielded Compliance Prior for Contact-Rich Vision-Language-Action Manipulation (arxiv.org)

CAFOSat: A Strongly Annotated Dataset for Infrastructure-Aware CAFO Mapping Using High-Resolution Imagery (arxiv.org)

Revisiting Parameter-Based Knowledge Editing in Large Language Models: Theoretical Limits and Empirical Evidence (arxiv.org)