AI News

$\alpha$-Graph: Attention-Infused Normalizing Flow Approach to Tractable Graph Modeling (arxiv.org)

Flawed but Memorable: Student Critical Reception of Interest-Personalized GenAI Analogies in Computing Education (arxiv.org)

MetaKV: Adaptive KV Cache Compression for Constrained LLM Inference (arxiv.org)

Heat Field Signatures: From Point Clouds to Smooth Geometry (arxiv.org)

Semi-Supervised Learning under Spatially Biased Sampling (arxiv.org)

Solving the Elastic Wave Equation with Physics-Informed Neural Networks: A Robust and Critical Assessment (arxiv.org)

Automated Chest CT Protocol Selection via Large Language Model Derived Text Embeddings from Imaging Request Text (arxiv.org)

HyCO: A Hybrid Neural Solver for Combinatorial Optimization (arxiv.org)

Sharp Structure-Agnostic Minimax Risk for Partial Linear Models (arxiv.org)

Two-Scale Localized PCA-Net: Coarse-Global and Local-Residual Representations for Artifact-Reduced PDE Operator Learning (arxiv.org)

Risk-Conditioned Fine-Tuning of Large Language Models (arxiv.org)

Nystr\"om Attention Matches Full Attention for Cross-Sectional Stock Prediction (arxiv.org)

A Machine Learning Framework for Predicting Restaurant Food Waste to Support Sustainable Food Management (arxiv.org)

Proactive Context-Forecasted Safety Constraints for Nonstationary Reinforcement Learning (arxiv.org)

FALCON-S: Fixed-wing ground-effect Aerodynamics Simulator and Flight Control Learning Suite (arxiv.org)

Learning Metamaterial Eigenmodes with Wavelet-Encoded Fourier Neural Operators (arxiv.org)

Comparative Study of Anatomical and Learned Features in AI Models for Structural Brain MRI (arxiv.org)

Sparse Data Augmentation for Optimization with Provable Guarantees (arxiv.org)

KBBQ: A Predictive Noise Law and the Limits of Spectrum Flattening in FP4 Quantization (arxiv.org)

GPU-Enabled Large-Scale Optimization Using Randomized Linear Algebra (arxiv.org)

Topology-induced Operators Reveal Complementary Graph Representations without Training (arxiv.org)

Geodesic-informed Generative Diffusion Model For Topology-preserved Image Video Generation (arxiv.org)

Typed Federated Artifacts for the Agentic Web:Sharing Tool-Routing Knowledge Across Frozen,Heterogeneous LLM Agents (arxiv.org)

SIM: Subspace Interaction-based Method for Token-Level Text Anomaly Detection (arxiv.org)

CUNO: Curriculum and Preference Optimization for Stable Graph Unlearning under Mass Deletion (arxiv.org)

Revisiting Spectral Representations in Generative Diffusion Models (arxiv.org)

Explainable Deep Learning for Price-Trade Dynamics: From Black-Box Forecasts to Effective Parametric Models (arxiv.org)

Programmable Cellular Automata (arxiv.org)

PAGR: Proof-Carrying Algebraic-Geometric Retrieval: A Quiver-, Provenance-, and Sheaf-Theoretic Framework for Grounded LLM Retrieval (arxiv.org)

What the Window Does Not Contain: Auditing Provenance in a Document-Grounded Instability Benchmark (arxiv.org)

SCRIPTIOC-BENCH: A Benchmark for Recognizing Actionable Threat Intelligence from Script-Based Malware using LLMs (arxiv.org)

ExpertLens: Visualizing Embedding Spaces for Post-Hoc Explainability in MoE Enhanced Retrievers (arxiv.org)

From Splats to Silicon: Rethinking Computational Efficiency of 3DGS (arxiv.org)

Multiple Myeloma Lesion Segmentation on Whole-Body Diffusion-Weighted Imaging via Efficient Anatomical Anticipation and Multimodal Confirmation (arxiv.org)

Diamond Agent: Agentic Control of Federated HPC Resources as a Service (arxiv.org)

Scratchy: Visual-Scratchpad Multimodal Reasoning for Cryptographic Proof Generation in EasyCrypt (arxiv.org)

SWE-Test: Benchmarking LLM Vulnerability Discovery via Input Prediction (arxiv.org)

VDiff-Bench: A Challenging Benchmark for Fine-Grained Image Difference Identification (arxiv.org)

It is Not Yet Another Tool: Creating and Deploying an Agentic AI Companion in a Security Operations Center (arxiv.org)

SIDE: Sensor Impersonation Detection at the Edge via Sequence Prediction (arxiv.org)

Collision Snapshot Guided Time-Reversed Safety-Critical Scenario Generation (arxiv.org)

One MLLM, One Call: Efficient Zero-Shot Vision-and-Language Navigation via Spatial-Aware Waypoints (arxiv.org)

ProcArena: A Multi-Scenario Benchmark for LLMs on Direct and Interactive PL/SQL Development from Natural Language (arxiv.org)

SRD-GUARD: A Defense Framework of LLMs via Semantic Rewriting and Joint Multi-Model Scoring for Latent Intent Exposure (arxiv.org)

Recovering topological information of light by topological learning (arxiv.org)

A TTP by TTP Approach: Precise Malware Detection via Malicious TTP Recognition (arxiv.org)

Reading Decoder Trajectories: Training-Free Counterfactual Query-Trajectory Reliability for Small-Object Detection (arxiv.org)

When Does a Laugh Begin? Structured Annotator Disagreement in Temporal Laughter Localization (arxiv.org)

SAGE: A Hierarchical Framework for Evaluating Interpretive Literary Quality in Narratives (arxiv.org)

Mind the Approximation: Fisher-Weighted SVD Compression for ViTs (arxiv.org)