AI News

Transfer Learning Architectures for Scalable Multi-Fidelity Bayesian Optimization (arxiv.org)

DocHRL: A Hierarchical Reinforcement Learning Framework for Cost-Optimised Document Classification (arxiv.org)

DAMamba-UNet3D: A Parameter-Efficient Mamba State Space U-Net with Dynamic Adaptive Scan for 3D Medical Image Segmentation (arxiv.org)

Reason Before You Retrieve: Agentic Planning for Multi-modal RAG (arxiv.org)

What do Reward Models Memorize? (arxiv.org)

Understanding Tone-Dependent Inference Cost in Large Language Models (arxiv.org)

WorldDiT: A Unified Diffusion Architecture for World and Action Modeling (arxiv.org)

On the post-hoc Evaluation of PDE Discovery: A Multifaceted Challenge of Scientific Advancement (arxiv.org)

Controllable Diversity in Normalization-Based Implicit Ensembles via Softmax-Temperature Modulation (arxiv.org)

Learned Interventions in Lean 4 grind (arxiv.org)

TopoFE: topology-aware LLM-guided Automated Feature Engineering (arxiv.org)

Multimodal Surface EMG Hand Gesture Recognition Using Query-Based Transformers for Prosthetic Control (arxiv.org)

An Interactive Vision Language Platform for Cognitive Remediation in Schizophrenia (arxiv.org)

Real-time Reconstruction of Human Visual Perception from fMRI (arxiv.org)

Not Forgotten: Implementation and Evaluation of a Personalized Episodic Memory for the Humanoid Robot Head Kim (arxiv.org)

Closed-Loop Validation-Repair for Healthcare Interoperability: A Multi-Model Study of Schema Compliance in Clinical LLMs (arxiv.org)

Limbomorphs (arxiv.org)

DeepFaith: Evidence-Grounded LLMs for Faithful Incident Reporting in Multi-Stage APT Defense (arxiv.org)

Learning from the Descent Direction: Adaptive Gradient Descent under One-Sided H\"older Regularity (arxiv.org)

Regulating for AI Legitimacy (arxiv.org)

The balance between compactness and forecast accuracy of data-driven latent-space reduced-order models in controlled wake flows (arxiv.org)

Do Language Models Converge to Themselves? Recursive Self-Refinement as Textual Relaxation (arxiv.org)

Bayesian Complete-Pooling in Cross-Subject Classification for Motor Imagery Electroencephalogram (arxiv.org)

Robustifying pathology foundation models via fine-tuning (arxiv.org)

KG2Code: Bridging Knowledge Graphs and Large Language Models via Executable Code for Question Answering (arxiv.org)

EchoBridge: Long-Tail-Aware ECG-Echocardiography Text Alignment for Echocardiography-Derived Cardiac Findings (arxiv.org)

The Cost of Knowing: A Resource-Aware Protocol for Benchmarking Hallucination Beyond Static Leaderboards (arxiv.org)

A Comparison of Data Augmentation Methods for Training Deep Neural Networks on Synthetic Aperture Sonar (arxiv.org)

Scale Weight Decay and Train Better (arxiv.org)

ESRVS: Extreme Semi-Supervised Retinal Vessel Segmentation with a Single Annotated Image (arxiv.org)

Earnings25: A Comprehensive 500-Hour Speech Benchmark for Finance (arxiv.org)

SMART: LLM-Augmented Hybrid Retrieval for Dynamic Product Ads (arxiv.org)

Does Graph Compression Preserve Signal Propagation? (arxiv.org)

Latent-LoRA: Compact Latent-Space Adapters with Gradient-Free Routing for Continual Learning (arxiv.org)

Where Is the Cost of Third-Party API Routers in Agentic Software Development? (arxiv.org)

Token-Region Guided Cross-Attention Fusion for Multimodal Affect Interpretation (arxiv.org)

Stress-Testing EEG Foundation Models for Clinical Decoding: Dataset Identity and Targeted Negative Controls (arxiv.org)

DraftExpert: Expansion-Aware Self-Speculative Decoding for End-Device MoE Inference (arxiv.org)

Learning to Optimize: Joint Routing and Flow Allocation on Sparse Non-Euclidean Networks (arxiv.org)

When Activation Oracles Learn Not to Read: Concept-Specific Blind Spots in Fine-Tuned Oracles (arxiv.org)

Multi-primitive in-memory computing for Monte Carlo tree search (arxiv.org)

Explaining BiomedCLIP with Weighted Banzhaf Interactions Supported by Tree-Gram Parsing (arxiv.org)

From Machine Learning to Large-Scale EO Products: Best Practices for Making Maps (arxiv.org)

Context Is King: How In-Context Specification Shapes the Geometry of Concepts (arxiv.org)

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation (arxiv.org)

Do Small Models Use the Law You Give Them? Context-Injected Fine-Tuning for Legal QA in Bangladesh (arxiv.org)

Post-Operative Glioma Segmentation via Loss Stabilization, Normalization and Subspace Attention (arxiv.org)

Variational Boosting for Physics-Informed Neural Networks (arxiv.org)

Optimizing Transformer Neural Network for Real-Time Outlier Detection on FPGAs (arxiv.org)

Parallel Swin Transformer-Enhanced 3D MRI-to-CT Synthesis for MRI-Only Radiotherapy Planning (arxiv.org)