AI News

Commentary: Virginia must put the brakes on data center development - Roanoke Times (roanoke.com)

Show HN: Proc-CLI – An agent-friendly CLI tool for process and port management (proc-cli.com)

Cognitive Mercantilism: AI panic resembles fears of early capitalism (contraptions.venkateshrao.com)

Exact Global Minimax Risk near Nonidentification (arxiv.org)

OmniSpectra: A Unified Foundation Model for Universal Spectra Representation Learning (arxiv.org)

Beyond the Monolithic Scheduler: Lightweight Adaptive Policy Switcher for Process Scheduling Optimization (arxiv.org)

The Role of Quantum in Hybrid Quantum-Classical Neural Networks: An Empirical Assessment (arxiv.org)

PAIR-SAFE: A Paired-Agent Approach for Runtime Auditing and Refining AI-Mediated Mental Health Support (arxiv.org)

EvalCards: A Framework for Standardized Evaluation Reporting (arxiv.org)

Towards robust long-context understanding of large language model via active recap learning (arxiv.org)

Score-Preserving Continual Lasso under Task Shift (arxiv.org)

Acquisition for Spherical-Linear Bayesian Optimization on the Cube (arxiv.org)

Batched NN 4D-Var: a performant hybrid model framework for the Integrated Forecasting System (arxiv.org)

Empirical concentration for chains with infinite memory (arxiv.org)

Combinatorial Characterizations of the Learnability of Conditional Distributions (arxiv.org)

Conditional Flow Models for Offline Maximum Entropy Reinforcement Learning (arxiv.org)

Implicit Neural Representations for Variational Problems on Graphons (arxiv.org)

Federated Nonparametric Regression with Heterogeneous Clients (arxiv.org)

Sparse Bayesian Neural Networks via Sticky Piecewise Deterministic Markov Processes (arxiv.org)

Autoregressive Physics-Informed Neural Operator Surrogates and Joint 4-D Seismic-Production Bayesian History Matching (arxiv.org)

Early learning in large residual networks (arxiv.org)

Mitigating the Likelihood Paradox in Flow-based OOD Detection: An Entropic Perspective (arxiv.org)

Beyond Pattern Matching in 3D MLLMs: Part-Level Functional Reasoning for Generalizable Recognition (arxiv.org)

Efficient Zero-Shot Video Anomaly Detection via Signal-Aware Adaptive Fusion (SAAF) (arxiv.org)

Representation Learning via Composite Subspace Flow Matching (arxiv.org)

EditJev: System One Routing for Image Editing Models (arxiv.org)

Training an MoE LLM in MXFP4: How We Closed the Gap to BF16 (arxiv.org)

Easy-3Dfy: Object-Level Geometric Composition for Single-Image 3D Scene Construction (arxiv.org)

Head Dimension Matters in Language Models for Long-Context Retrieval (arxiv.org)

Attractor Domain Theory: A Mathematical Framework for Cardiovascular Attractor Analysis with Wearable Photoplethysmography (PPG) Validation (arxiv.org)

Tokamak-SI: Interpreting Tokamak Discharges with Labeled Catalogs (arxiv.org)

Multiplicative vs. Additive State Coupling in Learned Optimizer Schedules (arxiv.org)

SOPO: Socratic Guided Policy Optimization for Span-Level Hallucination Detection (arxiv.org)

MedCaseAgent: From Multimodal Clinical Evidence to Rare Disease Case Reports (arxiv.org)

Dual-Adaptive Z-Score PPO: Dynamic Clipping Using Action Confidence and Normalized Advantage Magnitude (arxiv.org)

AI Alignment for Digital Democracy: Fairer Voters Representation against LLM Biases (arxiv.org)

"Not" is Not Lost in Translation: A Causal Analysis of Negation Representations in Multilingual LLMs (arxiv.org)

Searching with Sparse Histories: Cross-Task Architecture Search from Incomplete Search Logs and Zero-Cost Proxies (arxiv.org)

ChoreoStudio: Planning What, When, and Who in Music-Driven Group Choreography (arxiv.org)

Complementing DINO Features with Image Structure for Part Discovery (arxiv.org)

Tool-Calling LLM Agents Under Realistic MCP Faults: Scale Does Not Purchase Fault Tolerance (arxiv.org)

Watermarking Diffusion Language Models with Learned Foresight and Balanced Bands (arxiv.org)

Ontology-Guided Knowledge Graph Construction from Structured Metadata and Climate Science Publications (arxiv.org)

HyScale: Scaling Long-Context Training for Learned Sparse Attention (arxiv.org)

Beyond Data Schedule: Fast LLM Pretraining on Data Mixtures by Loss-Reweighting (arxiv.org)

ImageRSI: Verification-Driven Recursive Self-Improvement for Agentic Image Generation (arxiv.org)

Heterogeneous Space Data Centers: A Key Paradigm for Future Non-Terrestrial and In-Orbit Services (arxiv.org)

MG-REPA: Multi-Granularity Representation Alignment for Generative Target Speaker Extraction (arxiv.org)

FSVL: Taxonomic Fast-Slow Vision-to-Language Collaborative Framework for Interpretable Confusable Fish Species Identification and Knowledge Generation in the Middle Yangtze River (arxiv.org)

TGR-EvoDAG: A DAG-based Multi-Agent Code Evolution Framework for Generative Recommendation on Tencent (arxiv.org)