AI News

Annealed Entropic Allocation for Ranking and Selection (arxiv.org)

Enhancing Spectral Embedding through Robust and Flexible Knowledge Transfer in Electronic Health Records (arxiv.org)

Renewable Lasso without Batch-Number Constraints: A Gradient-Enhanced Approach (arxiv.org)

From Persistence to Survival: Hypothesis Testing, Effect Sizes and Vectorisation for Topological Features (arxiv.org)

Phase Transitions in Attention: A Bayesian Theory of Copy Head Emergence (arxiv.org)

Fixed-Parameter Tractability of Private Synthetic Data Generation (arxiv.org)

Quantized Stochastic Primal-Dual Methods for Distributed Optimization under Relaxed Global Geometry (arxiv.org)

GraphGP: Scalable Gaussian Processes with Vecchia's Approximation (arxiv.org)

Signed Compression Progress on a Sealed Audit is Goodhart-Resistant (arxiv.org)

The Power of Test-Time Training for Approximate Sampling (arxiv.org)

CRUMB: Efficient Prior Fitted Network Inference via Distributionally Matched Context Batching (arxiv.org)

Unbiased Derivative Estimation for Stationary Mean of Parameterized Markov chains (arxiv.org)

Continuous biome representations from Earth observation embeddings (arxiv.org)

Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies (arxiv.org)

Visualizing LLM Latent Space Geometry Through Dimensionality Reduction (arxiv.org)

CaReTS: A Multi-Task Framework Unifying Classification and Regression for Time Series Forecasting (arxiv.org)

Time-multiplexed layer reuse for physical neural networks (arxiv.org)

Energy Use of AI Inference, Efficiency Pathways, and Test-Time Scaling (arxiv.org)

Tensor Methods: A Unified and Interpretable Approach for Material Design (arxiv.org)

Persistent Homology as a Theory of Emergent Structure (arxiv.org)

AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin (arxiv.org)

Learning Patterns and Abstractions from Perceptual Sequences (arxiv.org)

Context-Driven Incremental Compression for Multi-Turn Dialogue Generation (arxiv.org)

UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning (arxiv.org)

MARIC: Multi-Agent Reasoning for Image Classification (arxiv.org)

Cross-Layer Discrete Concept Discovery for Interpreting Language Models (arxiv.org)

Diffusion-based Cumulative Adversarial Purification for Vision Language Models (arxiv.org)

Adjoint Method versus Physics-Informed Neural Networks in PDE-Constrained Inverse Problems (arxiv.org)

Measuring Semantic Progress in Multi-turn Dialogue via Information Gain (arxiv.org)

Learning What to Say to Your VLA: Mostly Harmless Vision Language Action Model Steering (arxiv.org)

PianoKontext: Expressive Performance Rendering from Deadpan Context (arxiv.org)

Finding Sparse Subnetworks in One Training Cycle via Progressive Magnitude-Based Pruning (arxiv.org)

MLT-Dedup: Efficient Large-Scale Online Video Deduplication via Multi-Level Representations and Spatial-Temporal Matching (arxiv.org)

Quantum Occam Learning: Sample-Supported Expressibility for Circuit-Based Quantum Learning (arxiv.org)

Making Models Unmergeable via Scaling-Sensitive Loss Landscape (arxiv.org)

An XAI View on Explainable ASP: Methods, Systems, and Perspectives (arxiv.org)

Resource-Aware LLM Reasoning for Mobile Edge General Intelligence (arxiv.org)

Sustainability assessment using multimodal AI agents (arxiv.org)

Beyond Dark Knowledge: Mixup-Based Distillation for Reliable Predictions (arxiv.org)

DAM-VLA: Decoupled Asynchronous Multimodal Vision Language Action model (arxiv.org)

Categorical Robustness Assessment for Machine Learning based Network Intrusion Detection Systems (arxiv.org)

Neuro-Relational Programs: Unifying Queries and Neural Computation over Structured Data (arxiv.org)

Corpus Augmentation for Sign Language Translation via LLM-Guided Video Stitching (arxiv.org)

NARRAS: Edge-Triggered Distributed Inference for CSI-Based Localization in Vehicular IoT Networks (arxiv.org)

Continual Learning with Support Boundary Experience Blending (arxiv.org)

MLaGA: Multimodal Large Language and Graph Assistant (arxiv.org)

Offline Diffusion Policy for Multi-User Delay-Constrained Scheduling (arxiv.org)

Autoregressive Direct Preference Optimization (arxiv.org)

Reroute, Don't Remove: Recoverable Visual Token Routing for Vision-Language Models (arxiv.org)

GraspLLM: Towards Zero-Shot Generalization on Text-Attributed Graphs with LLMs (arxiv.org)