AI News

REFINEPPO: Learning Continuous Control Policies by Iterative Action Refinement (arxiv.org)

Do Quantum Models Scale Like LLMs? (arxiv.org)

Near-Optimal Acceleration for Smooth $\ell_p$ / $\ell_q$ Nondual Convex First-Order Oracle Optimization (arxiv.org)

IntBMoE: Integrating Block-Level Conditioning into Expert Composition for Full-Participation Mixture-of-Experts (arxiv.org)

TinyCeNN-LM: Quality-Gated Conversion of Pretrained Attention with CeNN-Inspired Cellular-Recurrent Layers (arxiv.org)

Decoupling Internal Representational Changes and Causal Importance in Fine-Tuned Large Language Models (arxiv.org)

Detecting Hallucination in LLMs: Tracing the Topological Signatures of Impaired Context Sharing (arxiv.org)

LoRA Enhanced Contrastive Learning with SAS Vision Transformers (arxiv.org)

CaLR: Causal Latent Revision for Robust Diffusion Reasoning (arxiv.org)

Attention-Aware Routing: Coupling Routing and Attention in MoEs (arxiv.org)

RBS-Attention: Radius-Bounded Sparse Prefill for Long-Context Large Language Models (arxiv.org)

World Modeling in Transformers (arxiv.org)

Listen Before You Speak: Response Planning from Listener Facial Reactions for Conversational Speech Generation (arxiv.org)

Value-Sensitive Delegation in Everyday AI Agent Use: Evidence from OpenClaw (arxiv.org)

Trajectory Entropy Reinforcement Learning for Robust Robot Motor Skill Learning (arxiv.org)

Near-Universal Multiplicative Updates for Nonnegative Einsum Factorization (arxiv.org)

Robust Mixture Models for Algorithmic Fairness Under Latent Heterogeneity (arxiv.org)

Moral Entropy: Auditing Bias and Uncertainty in Moral Judgment (arxiv.org)

Schedule optimization for tau-leaping in masked discrete diffusion (arxiv.org)

Geometric Mean Pooling for Equal-Weight Multiplicative Coarse-Graining (arxiv.org)

EnterpriseVal: Quantifying the Efficacy, Reliability and Value of Generative AI in the Enterprise (arxiv.org)

Neural composite likelihood estimation: simulation based inference for time series (arxiv.org)

Single-Loop Stochastic Projected Damped Extragradient Methods for Stochastic Nonconvex--(Strongly) Concave Minimax Optimization (arxiv.org)

Routine Blood Tests Outperform CRP for Distinguishing Bacterial From Viral Infection in Children (arxiv.org)

FairLMs: A Turnkey Library for Fairness in Language Models (arxiv.org)

Multi-Domain Clustering via Measure Quantization (arxiv.org)

NemotronLabs VoiceChat: An Open Full-duplex Speech-to-Speech Model with Tool Calling Capabilities (arxiv.org)

Bayesian Belief Layer for Controllable Opinion Dynamics in LLM Agents (arxiv.org)

Robust Dual-Regularized Variable Selection under Outlier Contamination (arxiv.org)

Repulsive normalizing flow mixtures for adaptive importance sampling: reliability analysis of complex systems (arxiv.org)

Layerwise Decoupling for Stable Structured Sparsification of Fully Connected Layers (arxiv.org)

Aggregated Posterior Predictive Checks for Generative Modeling (arxiv.org)

Training-Adaptive Convolutional Sparse Coding via Information Bottleneck for Robust Visual Representation (arxiv.org)

Riemannian Simultaneous Inference for Tangent Vector Field Regression (arxiv.org)

How Many Posterior Samples? Calibrated Stopping for Adaptive Sensing (arxiv.org)

Improving the Predictive Performance of Bootstrap Aggregating by Dirichlet Resampling (arxiv.org)

Brownian Heads for Deep ReLU Representations: Activation Mass and the Cost of Same-Sample Selection (arxiv.org)

Collab-Solver: Collaborative Solving Policy Learning for Mixed-Integer Linear Programming (arxiv.org)

On the Limitations of Large Language Models for Conceptual Database Modeling (arxiv.org)

Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models (arxiv.org)

Sparse Identification for Automatic Large-Scale Screening: A Constraint-Aware Framework with Ultra Fast Decoding Algorithm (arxiv.org)

Diagonalized Attention for Individualized Regression: Latent-Row Localization and Prediction (arxiv.org)

Triply-Scalable Equivariant Gaussian Process Modeling (arxiv.org)

A Smoothed Discrepancy Principle for Random Feature Methods and Neural Networks (arxiv.org)

Multi-Subject Pretraining Enables Short-Calibration Personalization for Closed-Corpus Surface EMG Speech Decoding (arxiv.org)

MIRCID: Inferred Hub-miRNAs Drive Cross-Task Improvements in Drug Mechanistic Modeling (arxiv.org)

Reliability-Centered Evaluation of Sparse Longitudinal CT Lesion-Size Forecasting with Conformal Interval Calibration and Gompertz-Inspired Regularization (arxiv.org)

Prediction Dynamics in Depth-Recurrent Language Models (arxiv.org)

Weighted Quantum Signal Processing: Low-Depth Polynomial Approximation with Applications to Kolmogorov-Arnold Networks (arxiv.org)

Benchmarking Autonomous Driving Planners Across Leaderboards: A Unified CARLA-Based Evaluation (arxiv.org)