AI News

Understanding Perturbed Parameter Ensemble Sensitivities Using A Contrastive Learning Approach (arxiv.org)

What Will Remain Human in Software Architecture? A Focus Group Report (arxiv.org)

Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops (arxiv.org)

SignTrace: Describe a Sign, Find the Word (arxiv.org)

SlideLab: Audience-Centered Scientific Slide Generation and Evaluation (arxiv.org)

Cartograph: Federated Tool Discovery with Operator-Attested Retrieval for AI Agents (arxiv.org)

When Is a Multi-Agent Code Judge Actually Grounded? Two Label-Free Measurements, and a Judge That Declines to Guess (arxiv.org)

ScopeBench: Do Agents Preserve Engagement Boundaries Under Goal Pressure? (arxiv.org)

Bringing AI to Autonomous Systems -- From Cognition to Collective Intelligence (arxiv.org)

T-RoPE: Time-Aware Rotary Position Embedding for Sequential Recommendation (arxiv.org)

Backbone-Adaptive Evidence Routing for Robust Pairwise LLM Judging (arxiv.org)

Beyond Bag-of-Words: Diagnosing Compositional Binding Failures in Vision-Language Models (arxiv.org)

RAPTOR: Ridge-Adaptive Logistic Probes (arxiv.org)

Dynamic Welfare-Maximizing Pooled Testing (arxiv.org)

Prompt-Based Continual Compositional Zero-Shot Learning (arxiv.org)

Thinking Less to Simulate Better: Intuitive Prompting Improves LLM Agents Simulating Individual Social Media Reactions, Including Unfamiliar Content (arxiv.org)

Rank-Reliable Teacher-Guided Fitness Approximation for Expensive Evolutionary Optimization: A TinyML Architecture Search Study (arxiv.org)

Predicting Transmembrane Protein Topology from 3D Structure (arxiv.org)

Towards VLA-Dreamer: Refining VLA Behavior Using World Models (arxiv.org)

Statistical attribute alignment for black-box generative AI via output post-processing (arxiv.org)

Compact Documentation for Coding Agents: A Benchmark, an Optimizer, and Why It Does Not Transfer (arxiv.org)

UniAR: A Unified Framework for Autism Recognition Enhanced by Multi-View Prompt Learning (arxiv.org)

Softmax Reparameterization for Output-Head Quantization (arxiv.org)

Resource-Optimized and Energy-Aware Agentic AI Framework Anchored on Blockchain for Secure Software Supply Chains (arxiv.org)

Cognitive Skills in the Age of AI: Computing Students and Experts Perceptions (arxiv.org)

MoSAR: Mixture of Semantic Attention Regimes for Learning Adaptive and Approximable Attention Geometries (arxiv.org)

Murmurations, Mestre--Nagao sums, and Convolutional Neural Networks for elliptic curves (arxiv.org)

Foundations of Reinforcement Learning and Interactive Decision Making (arxiv.org)

Multivariate conformal uncertainty propagation in multitask atomistic simulation: Successes and pitfalls (arxiv.org)

LUCID: Learning Under Confounding for Inference and Discovery in Time Series (arxiv.org)

DIAL: Position-Debiased LLM Judges with Adaptive Human Preference Calibration (arxiv.org)

A Flatness-Generalization Relation in the Teacher-Student Tree-Committee Machine (arxiv.org)

SAGE: A sampling-aware global evaluation benchmark for species distribution modeling (arxiv.org)

Ensembles of Exactly Solved Subsamples for Clusterwise Regression: Trimming Without a Trimming Level (arxiv.org)

Coupled Usage-Sense Processes: Temporal and Attributable Lexical Semantic Change (arxiv.org)

TR-SSQP: A Trust-Region Method for Constrained Stochastic Optimization under Heavy-Tailed Noise (arxiv.org)

Design-Ignoring versus Design-Respecting World Models for Epidemiology (arxiv.org)

Causal Retention in Interactive Agents: Interface Factorization and Selective Adaptation (arxiv.org)

Entropy Regularization: A Free Correction to Cross-Entropy for Verified Demonstrations (arxiv.org)

Atelier: Learning Local Self-Supervised Features for CryoEM Volumes via Hypernetworks (arxiv.org)

High-dimensional Gaussian Graphical Model Testing for Long-Memory Time Series (arxiv.org)

Learning to Replace MCMC in Split-Gibbs Diffusion Posterior Sampling via Deep Unfolding (arxiv.org)

Learning to Bias: Machine Learning-Enhanced Particle Filters (arxiv.org)

Breaking Homogeneity: Diversifying Persona Sets for Creative LLM Outputs (arxiv.org)

An End-to-End Pipeline for Causal ML with Continuous Treatments: An Application to Financial Decision Making (arxiv.org)

Cost-Aware Best-LLM Identification using Dueling Feedback (arxiv.org)

Strategic Self-Consistency (arxiv.org)

First-Order Stationarity of Reverse Diffusions (arxiv.org)

Uncertainty and Explainability in Deep Rough Volatility: A Neural Information-Theoretic Posterior Approach (arxiv.org)

Geometric Feature Learning for Functional Data Valued on the Symmetric Positive Definite Manifold (arxiv.org)