AI News

The Violation Situation Pattern: A Knowledge-Graph Pattern for Compliance Violations (arxiv.org)

Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning (arxiv.org)

Plan2Map: A Multimodal Benchmark for Document-Grounded Geospatial Boundary Reconstruction from Planning Records (arxiv.org)

Do Neural Retrievers Prefer Certain Documents? Evidence of Learned Relevance Priors (arxiv.org)

ScoreStop: Gradient-based early stopping using functional score tests (arxiv.org)

CoralBay: A Self-Supervised CT Foundation Model (arxiv.org)

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking (arxiv.org)

Names Don't Matter: Symbol-Invariant Transformer for Open-Vocabulary Learning (arxiv.org)

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation (arxiv.org)

Expert-Aware Causal Tracing of Factual Recall in Sparse MoE Language Models (arxiv.org)

Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning (arxiv.org)

Qwen-Image-Flash: Beyond Objective Design (arxiv.org)

See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs (arxiv.org)

HiSE: A Lightweight Hierarchical Semantic Explainer for Heterogeneous Graph Neural Networks (arxiv.org)

GFFMERGE: Efficient Merging of Graph Neural Force Fields and Beyond (arxiv.org)

VidMsg: A Benchmark for Implicit Message Inference in Short Videos (arxiv.org)

Tool-Aware Optimization with Entropy Guidance for Efficient Agentic Reinforcement Learning (arxiv.org)

Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs (arxiv.org)

Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic (arxiv.org)

Fast Organic Crystal Structure Prediction with Unit Cell Flow Matching (arxiv.org)

Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning (arxiv.org)

$\Psi$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues (arxiv.org)

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models (arxiv.org)

Geometry-Aware Tabular Diffusion (arxiv.org)

AURA: Action-Gated Memory for Robot Policies at Constant VRAM (arxiv.org)

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs (arxiv.org)

Social Caption: Evaluating Social Understanding in Multimodal Models (arxiv.org)

Echo-POSED: Geometric Self-Distillation for Echocardiography Guidance (arxiv.org)

EvoDrive: Pareto Evolution for Safety-Critical Autonomous Driving via Self-Improving LLM Agents (arxiv.org)

Beyond Gradient Descent: Adam for Analog Ising Machines (arxiv.org)

CL-DMDF:Dynamic Multimodal Data Fusion Model Based on Contrastive Learning (arxiv.org)

\textsc{CR-Seg}: Attention-Guided and CoT-Enhanced Coarse-to-Refined Reasoning Segmentation (arxiv.org)

Bayesian Tensor Decomposition with Diffusion Model Prior (arxiv.org)

Efficient Transformer-Based Localized Patch Sampling for Choroid Plexus Segmentation in Multiple Sclerosis (arxiv.org)

Economy of Minds: Emerging Multi-Agent Intelligence with Economic Interactions (arxiv.org)

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)

PHASER: Phase-Aware and Semantic Experience Replay for Vision-Language-Action Models (arxiv.org)

DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting (arxiv.org)

Spectral Asymptotics of Neural Network Loss Landscapes: An Exact Decomposition of the Curvature Exponent (arxiv.org)

Toward a Modular Architecture for Embedded AI Agent Systems at the Edge (arxiv.org)

Attention Calibration for Position-Fair Dense Information Retrieval (arxiv.org)

SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction (arxiv.org)

Limit Analysis of Graph Neural Networks with Wireless Conflict Graphs (arxiv.org)

Building Better Activation Oracles (arxiv.org)

Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation (arxiv.org)

EntangleCodec: A Unified Discrete Audio Tokenizer via Semantic-Acoustic Entanglement (arxiv.org)

Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent (arxiv.org)

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring (arxiv.org)

Formalizing the Binding Problem (arxiv.org)

Forgetting is Not Erasure: Recovering Latent Knowledge via Transport Keys (arxiv.org)