AI News

Learning tactile perception from high-bandwidth single-point sensing (arxiv.org)

Beyond Final-Token Classification: Heterogeneous Readouts for Evidence-Grounded Suicide Risk Detection (arxiv.org)

Bridging Local and Population Causal Effects: A Proximal Instrumental Variable Approach (arxiv.org)

Classification with Abstention Under Class-Conditional Error Constraints (arxiv.org)

Monotone-Constrained Diffusion Models for Long-Horizon Production Forecasting (arxiv.org)

Optimal High-Order Methods for Solving Monotone Variational Inequalities (arxiv.org)

Subspace Learning with Interval-Censored Likelihoods for Dequantizing Percept PC LFP Snapshots (arxiv.org)

ParA-LLM: A Unified Approach to Paralinguistic and Acoustic Speech Understanding (arxiv.org)

The shape of quark flavors (arxiv.org)

A Horizon-Independent Regret Bound for Optimistic Hedge in General-Sum Games (arxiv.org)

Intelligent Degradation Monitoring in Lithium-ion Batteries via Discharge Incremental Capacity Feature Estimation (arxiv.org)

Per-Query Gating of LLM Rerankers for Multi-Hop Retrieval (arxiv.org)

Scout: Open-World Species Recognition on the Edge (arxiv.org)

AVTR-1: Open Stack for Real-Time Interactive Avatars (arxiv.org)

CLEAR: Complex Learned Explicit Analytical Regularization for Ultra-Accelerated 4D Flow CMR Reconstruction (arxiv.org)

An LLM-Assisted AutoML Framework for Intrusion Detection in IoT Networks (arxiv.org)

Real-Time Plasma State Prediction via FPGA-Accelerated Quantized Recurrent Probabilistic Neural Networks (arxiv.org)

SDC-GON: Singular Decomposition and Consistency-Regularized Green's Operator Networks for Solving Partial Differential Equations (arxiv.org)

Causilo Technical Report (arxiv.org)

LPINNs: First-Layer Gated Localization for Physics-Informed Neural Networks (arxiv.org)

Interpretable Multi-Hypersphere Deep Anomaly Detection for Open-set Supervised Anomaly Detection (arxiv.org)

An Exact Junction-Tree Extended Formulation for Optimal Classification Trees (arxiv.org)

Auditing Bayesian Graph Alignment: Diagnostic Comparisons and Reference Failure (arxiv.org)

Robot World Models Are Not Invariant to How the Actions Are Written (arxiv.org)

Latent Telepathy: Multi-Robot Communication with Self-Supervised Perceptual Latents (arxiv.org)

Co-occurrence Patterns of LoRA Adapters in Production Diffusion Model Inference Services (arxiv.org)

Stochastic Reconfiguration as Statistical Filtering for Overparameterized Neural Quantum States (arxiv.org)

Low-Rank Frequency Convolution and Noise-Range Augmentation for Real-Time Pitch Estimation on Edge Devices (arxiv.org)

Multi-Armed Bernoulli Bandits via Minimax Single-Arm Stopping (arxiv.org)

On attention heads and bilinear forms (arxiv.org)

Distributional Balancing with Machine Learning for Clinical Trial Augmentation Using Real-World Data (arxiv.org)

Decoupled Causal Discovery (arxiv.org)

Belted Engression: Sufficient Dimension Reduction for Generative Distributional Regression (arxiv.org)

Machine-Interpretable Information: Compiling Documents into Searchable and Readable Protocol States (arxiv.org)

Poisson Exchange Beyond Submodularity: Effective Approximation Algorithms for Offline and Online Subset Selection over Matroids (arxiv.org)

Not All Task Vectors Need Equal Rank: Energy-Proportional Allocation for Model Merging (arxiv.org)

Fathom-Vaidya: Advancing Medical Reasoning with Rubric-Based Rewards (arxiv.org)

SSP-GNN: Learning to Track via Bilevel Optimization (arxiv.org)

Horizon-Aware Early Event Prediction for Tokamak Disruption Alarms (arxiv.org)

Complexities of Weak Proximal Oracle Methods for Composite Convex Optimization (arxiv.org)

A Lightweight Convolutional Neural Network for Real-Time Recognition of Hand-Drawn Geometric Shapes (arxiv.org)

Topographic Training Concentrates Causal Circuits Without Improving Neuron Monosemanticity (arxiv.org)

Adapting Boltz-2 with limited experimental activity data improves early enrichment in virtual screening (arxiv.org)

Temporal Generalization and Explanation Stability of Control Flow Graph Neural Networks for Malware Detection (arxiv.org)

A principled approach for energy-efficient training via phase-aware GPU frequency tuning (arxiv.org)

MCP-GRANITE Benchmark: GRANularity Interface TEsting for MCP-Based LLM Agents (arxiv.org)

Leveraging Inference-Time Compute for Diffusion Models via Global Scheduling of Denoising Trajectories (arxiv.org)

CurvFlow-DTA: dual-graph discrete Ricci curvature flow for drug--target affinity prediction (arxiv.org)

Testing the Construct Validity of a Functional Valence Axis in LLM Agents (arxiv.org)

A Hybrid Attention Model Learning Unified Time-aware Patch Representation for Irregular Multivariate Time Series Forecasting (arxiv.org)