AI News

vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models (arxiv.org)

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

ScoreStop: Gradient-based early stopping using functional score tests (arxiv.org)

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

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

Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts (arxiv.org)

Beyond Gradient Descent: Adam for Analog Ising Machines (arxiv.org)

DiffUNet^2: Bidirectional Prediction, Probabilistic Generation and Collaborative Visual Discovery for Scientific Data (arxiv.org)

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

SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction (arxiv.org)

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

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

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

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

Test-Time Optimization of Physical Query Plans with LLMs (arxiv.org)

Multi-Modal Machine Learning for Breast Cancer Recurrence Prediction (arxiv.org)

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

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

Learning to See via Epiretinal Implant Stimulation in silico with Model-Based Deep Reinforcement Learning (arxiv.org)

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

When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning (arxiv.org)

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

FRED: A Multi-Modal Autonomous Driving Dataset for Flooded Road Environments (arxiv.org)

Denoise First, Orthogonalize Later: Understanding Momentum in Muon via Spectral Filtering (arxiv.org)

DRAN: A Distribution and Relation Adaptive Network for Spatio-temporal Forecasting (arxiv.org)

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

SkillPyramid: A Hierarchical Skill Consolidation Framework for Self-Evolving Agents (arxiv.org)

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

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

Position: Adversarial ML for LLMs Is Not Making Any Progress (arxiv.org)

PINNfluence: Interpreting PINNs through Influence Functions (arxiv.org)

Multi-Modal Graph Neural Network with Transformer-Guided Adaptive Diffusion for Preclinical Alzheimer Classification (arxiv.org)

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

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

Introduction to optimization methods for training SciML models (arxiv.org)

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

Attribution via Distributional Paths for Information Revelation (arxiv.org)

Too Much of a Good Thing: When sim2real Efforts Impede Policy Learning (And What to Do About It) (arxiv.org)

Edge-Aware and Content-Adaptive Infrared Gas Leak Detection for Industrial Safety Monitoring (arxiv.org)

HARVE: Hacking-Aware Reward-Head Vector Editing for Robust Reward Models (arxiv.org)

Pretraining Language Models on Historical Text (arxiv.org)

FGRPO: Federated GRPO with Adaptive Aggregation on Non-IID Data (arxiv.org)

Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency (arxiv.org)

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

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

AugMask: Training Diffusion Models on Incomplete Tabular Data via Stochastic Augmentation and Masking (arxiv.org)

Towards Non-Monotonic Entailment in Propositional Defeasible Standpoint Logic (arxiv.org)

Beyond Encoder Accumulation: Measuring Encoder Roles in Multi-Encoder VLMs (arxiv.org)

The Road Ahead in Autonomous Driving: The KITScenes Multimodal Dataset (arxiv.org)

BAHSD: Bridging the Long-tail Gap via Adaptive Distillation in Black-box Sequential Recommendation (arxiv.org)