AI News

To Manipulate or Not: Opinion Dynamics in LLM Interactions (arxiv.org)

Speedrunning Relational Foundation Model Pretraining (arxiv.org)

Decision language models as affordable and rapid alternatives to LLM judges of clinical generative AI (arxiv.org)

Forging More Tasks into Better Harnesses: Agentic Harness Evolution via Successive Scale Racing (arxiv.org)

Bridging Number-Theoretic Primality Testing And Algorithmic Optimization: An Adaptive Cryptographic Framework (arxiv.org)

MIG-COW: Transferable Adversarial Attacks on Deepfake Detectors via Gradient Decomposition (arxiv.org)

SpecEvo: Speculative Evolution with Large Language Models for Cost-Efficient Scientific Discovery (arxiv.org)

Parameter Learning in Active Inference via Variational Message Passing (arxiv.org)

Evolving Federated Density Peak Clustering with Shuffler-Based Anonymization (arxiv.org)

QuaNAS: Uncertainty-Aware Reuse of Earlier Searches for Query-Efficient Neural Architecture Search (arxiv.org)

Data-Driven Vision-Language Models for Remote Sensing: A Survey (arxiv.org)

Beyond Accuracy: Disentangling Decomposition from Typed-State Quality Assurance in Multi-Agent LLM Pipelines (arxiv.org)

Learning Robot Behavior Priors from Non-Robotic Synthetic Data (arxiv.org)

Can Entanglement-Induced Feature-Map Designs Improve Projected Quantum Kernels? (arxiv.org)

ChronoSynth: Constraint-Aware Question Synthesis over Temporal Knowledge Graphs (arxiv.org)

OpenMAP-HIE: Pathology Informed Score-based Diffusion Model for Unsupervised Neonatal Hypoxic-Ischemic Encephalopathy Lesion Segmentation (arxiv.org)

When Are We Near Nash? Certifying Solutions in General-Sum Games (arxiv.org)

Latent space configuration for neural network finetuning, fast ranking, and embedding dimensionality reduction (arxiv.org)

CRAB: Cuboid-based Representation for As-built BIM from Point Clouds (arxiv.org)

Muting Tokens: Exploring Token Sparsification for Efficient Audio Transformers (arxiv.org)

When More Metadata Misleads: Probing Field-Level Grounding in LLM-Generated Museum Descriptions (arxiv.org)

RaSFNet: Ray-aligned and Scan-aware Fusion Network for LiDAR Semantic Segmentation (arxiv.org)

Track finding and particle identification performance with particle physics foundation models (arxiv.org)

Prompting Strategy Effects Depend on the Judge: A Multilingual Study of LLM-as-a-Judge Robustness (arxiv.org)

Hierarchical Masked Diffusion Language Models (arxiv.org)

MOSAIC: An Omni-Modal Benchmark for Long-Term Memory and Cross-Modal Reasoning in Conversational Agents (arxiv.org)

Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics (arxiv.org)

Huayu-Global: Skillful real-time quasi-global precipitation retrieval (arxiv.org)

LTEM: LLM-Friendly Table-Enhanced Markdown for Table Understanding and Generation (arxiv.org)

Decision Making and Ride Comfort Evaluation Based on Lane-Change Prediction for Autonomous Vehicles (arxiv.org)

FIGFLEX: A Mixed-Precision FP-INT GEMM Accelerator Co-Designed with Low-Bit LLM Quantization (arxiv.org)

Learning to Incentivise: Using Reinforcement Learning for Sustainable Urban Mobility (arxiv.org)

Soft Ontology Priors over Latent Concept Posteriors for Weakly Supervised Neuro-Symbolic Learning (arxiv.org)

Black-Box Red-Teaming of Multi-Agent Systems via Reinforcement Learning (arxiv.org)

Resuming Vision-Language Inference across Onboard Interruptions (arxiv.org)

Correlated Failures of AI Approval Monitors (arxiv.org)

TrainBridge: Agentic NPU Training Optimization Guided by GPU Compilation Evidence (arxiv.org)

How Representational Priors Shape Generalization in World Action Models (arxiv.org)

A Transformer-based Approach for Real-time Multi-agent Path Planning with Varying Initial/Final Conditions (arxiv.org)

Route-and-Generate: KL-Regularized Router Improvement for Reasoning Routing in LLMs (arxiv.org)

Consistency Is Not Validity: Self-Rewarded Moral Argumentation Makes Language Models Decisive but Pliable (arxiv.org)

On the Adversarial Vulnerability of Neural Receivers with Unrolled LDPC Decoders (arxiv.org)

Federated Differentially Private Optimization via Low-Rank Preconditioning (arxiv.org)

XALIGN: A Human-centric Visual Analytics Approach to Understanding AI Explanations (arxiv.org)

Why is AI-generated language so hard to understand? (arxiv.org)

AI-Based End-to-End Automotive Design and Software Development for SDVs (arxiv.org)

Where Does Timbre Hide? Localizing Speaker Information in Speech Signals (arxiv.org)

ORSMT: Unleashing the Potential of Satisfiability Modulo Theories for Semantic Verification and Repair in LLM-Based Optimization (arxiv.org)

Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis (arxiv.org)

Graph-Recurrent Learning of Emergent Collective Dynamics (arxiv.org)