AI News

Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems (arxiv.org)

Verbalized Particle Posterior: Bayesian Inference over Natural Language Hypotheses (arxiv.org)

Towards High-Level Semantic Intelligence (arxiv.org)

Sampling Decisions: Exact Path-Space Correction, Prior Cancellation and Local-Boltzmann Guidance (arxiv.org)

Fisher Information based Stochastic Gradient Ascent for Online Learning of Dirichlet Process Mixture and Theory (arxiv.org)

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

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

Commitment To Cooperation With Self-Negotiated Contracts (arxiv.org)

MarineEVT: Advancing Event-Centric Marine Video Understanding via Visual Tool Reasoning (arxiv.org)

Retrieval-Augmented Generation of Ontologies from Relational Databases (arxiv.org)

LOCKS: Page-Local Compact Key Summaries for Efficient Long-Context Decoding (arxiv.org)

VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference (arxiv.org)

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

SeT-Diff: Towards Semantic Foundation Models for HPC Telemetry and Time-Series (arxiv.org)

RMS@CC-MMD 2026: Multimodal Misogyny Detection via Geometric Interaction and Multi-View Consensus (arxiv.org)

Not All LLM Reasoning is Visible in the Chain-of-Thought (arxiv.org)

Imprompt: A Language Framework for Prompt Programming (arxiv.org)

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

All in One: Generative Modeling as Mean-Field Game Design (arxiv.org)

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

Photonic reservoir computing with complex networks (arxiv.org)

WISERouter: LLM Routing with Workload Budget Constraint (arxiv.org)

Outcome-Confounded Local Supervision in On-Policy Distillation (arxiv.org)

CausAdv: A Causal-based Framework for Detecting Adversarial Examples (arxiv.org)

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

MINT-V2X: A Mobility-Integrated Network Trajectory Dataset for Predictive Resource Management (arxiv.org)

Extreme Volatility Warning under Label Scarcity via Multi-Source Anomaly Fusion (arxiv.org)

AI-generated Images Challenge Visual Trust in High-risk Scenarios (arxiv.org)

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

A scalable online machine learning approach for Stock Recommendation (arxiv.org)

Anytime-Valid Confirmation of Covariate Balance for Prespecified Corrections (arxiv.org)

Towards Nexus-Score: Metadata Gaps Limit Scholarly AI Attribution (arxiv.org)

DynaCalKV: Key-Value Cache Compression via Head Grouping and Adaptive Rank Allocation (arxiv.org)

DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification (arxiv.org)

A Coulomb Particle Model for Learning Kernel Attention in Transformers (arxiv.org)

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

Language-Routed RAG and Direct Option Scoring for Multilingual Financial QA: DS@GT at FinMMEval (arxiv.org)

Cheap Probes Predict Expensive Training in 3D-CT Vision--Language Models (arxiv.org)

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

Mini-batch Noise Lowers Sharpness via Dominant-Subspace Fluctuations (arxiv.org)

VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing (arxiv.org)

MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning (arxiv.org)

CallBench: A Benchmark for Dual-Goal Coordination in Phone Call Assistants (arxiv.org)

Gleam: Adaptive Network-Efficient CUDA API Remoting for Cross-Device GPU Sharing over LANs (arxiv.org)

Beyond a Global Norm: Personalizing Toxicity Sensitivity in Language Models Without Retraining (arxiv.org)

EventOD: Event-Aware OD Flow Generation via LLM-Guided Semantic Modulation (arxiv.org)

Order in Desbordante: Techniques for Efficient Implementation of Order Dependency Discovery Algorithms (arxiv.org)

LEDOM: Reverse Language Model (arxiv.org)

Compute Globally, Materialize Locally: The Memory Contract of Sparse Event-KV (arxiv.org)

SpecAHD: Localize to Specialize for Automated Heuristic Design in Large-Scale Routing Problems (arxiv.org)