AI News

Bellman Error Minimization Via Linear Programming Normalization (arxiv.org)

Jumping up and down: Denoiser diffusion models for discrete ordinal data (arxiv.org)

A Two-Stage Cascade for Near-Real-Time Forest Anomaly Detection from Sentinel-1 SAR Time Series (arxiv.org)

A Controlled Audit of Personal AI Memory for Rating Prediction (arxiv.org)

Counterexample Generation via Per-Theorem Symbolic Verifiers: When Imitation Hurts and Reinforcement Repairs (arxiv.org)

FinDialogLens: Event Extraction over Multi-Party Dialogue for Missed-Trade Identification in Financial Chatrooms (arxiv.org)

SideKernel: A Usable microVM Sandbox for AI Coding Agents on macOS (arxiv.org)

APDMem: Agent-Controlled Progressive Disclosure for Query-Adaptive Long-Term Memory (arxiv.org)

From Retrieval to Typed Decisions: Calibrated System One Models from Biomedical Sentence Encoders (arxiv.org)

Exact Memory-Time Optimization for Prefix-Cached Language Model Serving (arxiv.org)

No-Free-Graph: Learning When Multimodal Data Should Be Graphified (arxiv.org)

LatticeSMC: Where to Spend Inference-Time Compute in Chunked Sequence Generators (arxiv.org)

Controlling Polar Exposure to Delay Memorization in Diffusion Models (arxiv.org)

From Fragments to Global Maps: Learning Vectorized Map Aggregation with Large Language Models (arxiv.org)

Out of Sync, Out of Sight: Phantom State Attacks against IIoT Intrusion Detection (arxiv.org)

Pincer: Resource Authorization for Agents using a Digital Twin (arxiv.org)

Improving the Energy-Efficiency of the Code Generated by LLMs through Effective Prompting (arxiv.org)

WebUIProof: Benchmarking WebUI Code Generators with UI-Agent Execution Harness (arxiv.org)

Equivariant Flow Matching for Electron Density Prediction (arxiv.org)

Efficient Memory Crystallization for Graph Learning under Non-Stationary Distribution Shifts (arxiv.org)

Gated Slot Attention-2: Two-Sided Associative Memory Correction in Linear Attention (arxiv.org)

All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR (arxiv.org)

To Explore The Strange New World Beyond Data Distribution: System Behavior, Causality Tax, and Non-causal Base Model (arxiv.org)

Understanding Enrichment in Reinforcement Learning (arxiv.org)

Counterfactual Action Evaluation, Observation Bottlenecks, and Representation Geometry in Joint-Embedding Predictive World Models (arxiv.org)

NeuroLens: Learning Latent Embeddings of Neural Semantics from Chronic Recordings (arxiv.org)

On Unlearning for Time-series Forecasting (arxiv.org)

DIVINE: Simple Cross-Market Stock Pretraining via Diverse Indicator Reconstruction (arxiv.org)

Peer Effects in Signed Networks: Separating Influence Through Positive and Negative Ties (arxiv.org)

Uncertainty as a Proxy for Semantic Correctness in Diffusion-Based Medical Image Synthesis (arxiv.org)

D2K-Bench: Can LLM Agents Turn Expert Designs into Efficient GPU Kernels? (arxiv.org)

WAMpy: Efficient Synthesis of Prolog Programs in Python (arxiv.org)

Mapping and Advancing the Scalability-Accuracy Frontier of Nonlinear Causal Discovery (arxiv.org)

Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures (arxiv.org)

Toward Omni Multimodal Graph Foundation Model: A Topology-Driven Binding Approach (arxiv.org)

Tangent Schr\"odinger Bridge Matching: Learning Stochastic Transport with Mechanistic Sensitivities (arxiv.org)

Do ResNets Route? Sparse Interaction Experts in Residual Networks (arxiv.org)

Neural Data Needs Semantic Tokenization: Behavioral Events as Boundaries of Session-Transferable Tokens (arxiv.org)

SPEAR: A Spectral-Disentangled MoE Neural Operator with Knowledge-Guided Expert Aggregation for Large-Scale PDE Pretraining (arxiv.org)

Information Limits of Low-Rank Approximation Certification (arxiv.org)

DriftTTS: Few-Step Text-to-Speech Without Distillation via Distribution-Matching Drift (arxiv.org)

ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation (arxiv.org)

Corrupted but Correct: Why Vision-Language Models Lie to Themselves Internally (arxiv.org)

Preserving Anatomical Continuity: Three-Stage Pipeline for Colon Segmentation in 3D Abdominal CT Scans (arxiv.org)

Signal Simplification Is Not Predictive Simplification: Diagnosing Residual Neural Forecasting in Short-Horizon Volatility (arxiv.org)

Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling (arxiv.org)

Dual Certified White-Box Inference for Input Convex Neural Networks (arxiv.org)

Learning from Evolving Errors: Adaptive Iterative Repair for On-Policy Distillation (arxiv.org)

Hop-Decayed Influence: New Vulnerabilities of Structural Auxiliary Indexing in GraphRAG Pipelines with LLM (arxiv.org)

RIPPLE in Still Water: Zero-Shot Clustering in Federated Learning with Wavelet Scattering Transform (arxiv.org)