AI News

TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning (arxiv.org)

Rethinking Molecular Text Representations for LLMs: An Empirical Study (arxiv.org)

Learn When and Where to Connect: Adaptive Virtual Nodes for Dynamic Message Passing on Graphs (arxiv.org)

Resource-Constrained Adaptive Inference for Sequential Pricing (arxiv.org)

Towards Compact Autonomous Driving Perception with Balanced Learning and Multi-sensor Fusion (arxiv.org)

Pretraining Language Models on Historical Text (arxiv.org)

Two-Action Apple Tasting with Switching Costs (arxiv.org)

State-Coupled Volatility in Latent Dynamical Systems: Recovery Under Partial Observation (arxiv.org)

From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework (arxiv.org)

Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning (arxiv.org)

DECA: Decentralizing Block-Wise Adam for Efficient LLM Full-Parameter Fine-Tuning on Non-IID Data (arxiv.org)

From Answers to States: Verifiable Process-Level Evaluation of Chemical Reasoning in Large Language Models (arxiv.org)

Annot-Mix: Learning with Noisy Class Labels from Multiple Annotators via a Mixup Extension (arxiv.org)

Safety Measurements for Fine-tuned LLMs Should be Grounded in Capability (arxiv.org)

TurtleAI: Benchmarking Multimodal Models for Visual Programming in Turtle Graphics (arxiv.org)

FFR: Forward-Forward Learning for Regression (arxiv.org)

Finding Needles in the Haystack: Transductive Active Labeling in Ecology (arxiv.org)

VLESA: Vision-Language Embodied Safety Agent for Human Activity Monitoring (arxiv.org)

Learning Temporal Causal Structure via Smooth Differentiable Optimization (arxiv.org)

Rethinking the Role of Tensor Decompositions in Post-Training LLM Compression (arxiv.org)

OpenAgenet/OAN: Technical Architecture for Trust-Governed Agent Identity and Discovery (arxiv.org)

SeSE: Black-Box Uncertainty Quantification for Large Language Models Based on Structural Information Theory (arxiv.org)

COD10K-C: Benchmarking Robustness of Camouflaged Object Detection Under Natural Image Corruptions (arxiv.org)

Merit or networks? What decides where research is published (arxiv.org)

Code-on-Graph: Iterative Programmatic Reasoning via Large Language Models on Knowledge Graphs (arxiv.org)

Neural Navigation Functions for Zero-Shot Generalizable Motion Planning (arxiv.org)

EqGINO: Equivariant Geometry-Informed Fourier Neural Operators for 3D PDEs (arxiv.org)

LLM-Assisted Reranking to Operationalize Nuanced Objectives in Recommender Systems (arxiv.org)

AUGUSTE: Online-Learning dApp for Predictive URLLC Scheduling (arxiv.org)

Relational Linearity is a Predictor of Hallucinations (arxiv.org)

MAdam: Metric-Aware Multi-Objective Adam (arxiv.org)

Phantom Transfer: Data Poisoning can Survive Data-Level Defences (arxiv.org)

Bregman meets L\'evy: Stochastic mirror descent with heavy-tailed noise in continuous and discrete time (arxiv.org)

Let There Be Light: Reflection, Refraction and Scattering for Neural Operators (arxiv.org)

Reproducibility is the New Copyleft: Defining AGI-oriented Reproducible Builds (arxiv.org)

Formalizing the Binding Problem (arxiv.org)

Forecasting Conceptual Diffusion in Science: The Case of Quantum Computing (arxiv.org)

CoralBay: A Self-Supervised CT Foundation Model (arxiv.org)

Whose Name Comes Up? II: Benchmarking and Intervention-Based Auditing of LLM-Based Scholar Recommendation (arxiv.org)

Synthetic Hallucinations, Real Gains: Hard Negatives from Frontier Models for FIM Hallucination Mitigation (arxiv.org)

Are Deep Learning Based Hybrid PDE Solvers Reliable? Why Training Paradigms and Update Strategies Matter (arxiv.org)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning (arxiv.org)

Identifying Quantum Structure in AI Language: Evidence for Evolutionary Convergence of Human and Artificial Cognition (arxiv.org)

R2DN: Scalable Parameterization of Contracting and Lipschitz Recurrent Deep Networks (arxiv.org)

PHASE: Physiology-Aware Hyperspectral Reconstruction via Object-to-Human Domain Adaptation (arxiv.org)

Target Updates May Stabilize Linear Q-Learning: Periodic and Soft Dynamics (arxiv.org)

ASAP: Exploiting the Satisficing Generalization Edge in Neural Combinatorial Optimization (arxiv.org)

Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent (arxiv.org)

Building Trust in Black-box Optimization: A Comprehensive Framework for Explainability (arxiv.org)

IdEst: Assessing Self-Supervised Learning Representations via Intrinsic Dimension (arxiv.org)