AI News

The Zero Pattern of a Design Matrix Drives Multiple Descent in Over-parameterized Regression (arxiv.org)

When Should Active RAG Retrieve? A Budget-Aware Evaluation of Utility, Calibration, and Cost (arxiv.org)

DynaResize: Runtime GPU Reallocation for Disaggregated LLM Post-Training (arxiv.org)

Capacity-Aware Deep Learning for Generalizable Traffic Volume Estimation Across Links and Cities (arxiv.org)

Flick: Few Labels Text Classification using K-Aware Intermediate Learning in Multi-Task Low-Resource Languages (arxiv.org)

Subject-Level Heterogeneity in EEG Motor Imagery Decoding: A Large-Scale Benchmark and Portfolio-Based Reduction of the Search Space (arxiv.org)

An Agentic Orchestration of Atomistic Simulations (arxiv.org)

Adaptive Data Admission and Retention for Streaming Federated Learning (arxiv.org)

Exploration of the generative capabilities of Boltzmann machines applied to social systems under the majority rule (arxiv.org)

Structural Preservation Governs Data Augmentation in Deep Learning-Based Laser Speckle Material Classification (arxiv.org)

Constrained Reinforcement Learning Using Successor Representations (arxiv.org)

Learning Distributions from Multiple Data Providers (arxiv.org)

No Free Lunch in Flow Surrogates under Time-Varying Boundary Conditions: A Two-Regime Study (arxiv.org)

Finite-Time Analysis of the Natural Policy Gradient in Finite-Horizon Markov Decision Processes (arxiv.org)

LEDOM: Reverse Language Model (arxiv.org)

scMIR: a vision-language foundation model for single-cell light microscopy image representation (arxiv.org)

Metamorphic Testing for Clinical ML Models: A Framework Proposal and Pilot Study (arxiv.org)

Intent-Governed Tool Authorization for AI Agents (arxiv.org)

Like a Baby: Visually Situated Neural Language Acquisition (arxiv.org)

A didactical-driven teacher assistant for a dimensional modeling course (arxiv.org)

Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems (arxiv.org)

Group Preference Collapse in Personalized Multimodal Large Language Models (arxiv.org)

DICA: Dual-Indicator Guided Contrastive Alignment in Multimodal Large Language Models (arxiv.org)

Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning (arxiv.org)

HydroAgent: Formalizing Forecaster Expertise into Skill-Orchestrated Flood Forecasting Workflows (arxiv.org)

Fashion-3DLR: A Controllable 3D Garment Generation Using Pairwise Fashion Elements for Intelligent Design (arxiv.org)

X-Stage: An Overlooked Pipeline Stage for Communication-Computation Overlap in DiT Inference (arxiv.org)

Foundation Models and Fine-Tuning: Toward a New Generation of Models for Time Series Forecasting (arxiv.org)

In-Context Learning as Implicit Policy Gradient (arxiv.org)

Where Quality Breaks in Compressed Short-Text Generation: Staged Bottleneck Localization (arxiv.org)

EXE-Bench: Ranking the Tradeoffs of AI-based Windows Malware Detectors for Real-World Usability (arxiv.org)

Catalyst Diffusion Transformer: Generative Inverse Design of Heterogeneous Catalysts (arxiv.org)

Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning (arxiv.org)

Grokking on the Weight-Decay Clock: A Rate Hierarchy from Softly Broken Symmetries (arxiv.org)

When Less Is More: A Controlled Benchmark of Lightweight CNNs for Satellite Land-Cover Segmentation on DeepGlobe (arxiv.org)

xMIx: High-Performance Serving-Time Platform for Mechanistic Interpretability Apps (arxiv.org)

Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model (arxiv.org)

Variance-Preserving Orthogonal Selection (VPOS): Greedy Feature Selection via Orthogonal Deflation in PCA Loading Space (arxiv.org)

ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits (arxiv.org)

Differencing the Diffusion Trajectory toward Uncertain Components for Time Series Forecasting (arxiv.org)

Topological Data Analysis and Graph-Theoretic Approaches for Tennis Match Prediction (arxiv.org)

What CLIP Knows but Cannot Say: Recovering Negation from Frozen Intermediate Features (arxiv.org)

Speed Reading Tool Powered by Artificial Intelligence for Students with ADHD, Dyslexia, and Short Attention Span (arxiv.org)

MolCryst-MLIPs: A Machine-Learned Interatomic Potentials Database for Molecular Crystals (arxiv.org)

Trustworthy Medical Segmentation: Uncertainty-Aware U-Net Evaluation Under Clinical Image Degradation (arxiv.org)

Steerable Chatbots: Exploring Personalization Control Interfaces via LLM Activation Steering (arxiv.org)

LU-500: A Logo Benchmark for Concept Unlearning (arxiv.org)

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning (arxiv.org)

LazyMem: Retrieve Broadly, Construct Selectively for Efficient Long-Term Agent Memory (arxiv.org)

Towards simultaneous decoding of kinetic and kinematic movement parameters during grasp and lift task by noninvasive brain imaging (arxiv.org)