AI News

Trust Hinders Bidirectional Human-AI Alignment (arxiv.org)

GesBench: When and Where Do Multimodal Language Models Perceive Social Meaning? (arxiv.org)

Retrieval Over Training: Similarity search-based Model Selection for Time Series Anomaly Detection (arxiv.org)

HGRP: Heterogeneous Graph Neural Network for Routability Prediction (arxiv.org)

Dimension-Optimal Dynamic Regret in Exp-Concave Online Learning (arxiv.org)

RM-OPD: On-Policy Distillation for Generative Reward Models (arxiv.org)

Structural Chain-of-Thought: Reasoning with Executable Computational Graphs (arxiv.org)

Self-Evolving Visual Agent via Margin Reward (arxiv.org)

Knowledge transfer between simple discrete worlds (arxiv.org)

Exposing AI Inference as a Telco Network API over the 5G User Plane (arxiv.org)

Trace Evolution Bench: Measuring Whether Agents Improve from Their Own Environment Traces (arxiv.org)

Similar Models, Broken Odds: Where Luce's Axiom Fails in Chatbot Arena (arxiv.org)

Revisiting Generative vs. Dense Retrieval: A Static Value Prior Reverses the Gap (arxiv.org)

Smart Alone, Blind Together: Why Accuracy Fails to CertifyTheory of Mind in Multi-Agent Teams (arxiv.org)

Optimization for One, Feasibility for Most: Decoupling Optimization from Feasibility in Chance-Constrained Programs (arxiv.org)

ShellElastic: Scalable Elastic Pretraining with Simultaneous Maximal Updates and Hyperparameter Transfer (arxiv.org)

Lifted State Policy Optimization: Internalizing Self-Correction through Transition Geometry (arxiv.org)

scHFBiMamba: a bidirectional Mamba autoencoder for cardiac disease-state classification from single-nucleus RNA-seq data (arxiv.org)

TurnCost: Turns, Not Observations: Cache-Aware Loop Engineering for Coding Agents (arxiv.org)

Improving the Bounds on Approximating Weighted Maximin Share for Chores (arxiv.org)

VLCQ: Post-training quantization for deep neural networks using variable length coding (arxiv.org)

Have You Been Convinced? A Neuro-symbolic Argumentation Reasoning Approach to Detecting Persuasiveness in ChangeMyView Discussions (arxiv.org)

GAMW: Generation-Aware Mel-Domain Watermarking for TTS Traceability (arxiv.org)

Deep Learning-based Semantic Segmentation of Dental Radiographs: Comparative Evaluation of PSPNet, DeepLabv3, UNet, and UNet++ (arxiv.org)

InCLAD: A Continual Learning Benchmark for Industrial Visual Anomaly Detection (arxiv.org)

How Far Can Coding Agents Go in Visual Generation? (arxiv.org)

Discovering Undisclosed Concepts in LoRA Adapters for Diffusion-Based AIGC Models (arxiv.org)

Virtual-Alloy Physics-Aware Semantic System for extrapolative prediction of perovskite solar cells (arxiv.org)

Physical Layer Anomaly Detection via Adaptive Gaussian Mixture Model (arxiv.org)

Beyond Equation Search: Conjecture-Guided Discovery with SCOPE and ClosureBench (arxiv.org)

Toward System One Clinical Intelligence: Parameter-Efficient Fine-Tuning and Counterfactual Explainability of Decision Foundation Models (arxiv.org)

UltraBERT: Beyond the Limit of BERT Pre-Training (arxiv.org)

Recurrent In-Context Learning for Tabular Foundation Models (arxiv.org)

Mixing Regularization for Average-Reward $Q$-Learning and $Q$-Planning (arxiv.org)

Too Late to Prune: Generative AI, the Screen, and Team Creative Decisions (arxiv.org)

The Agentic Scientist: Orchestrating Coding Agents for Automated Scientific (Co-)Discovery (arxiv.org)

TorchSpin: Differentiable Electron Paramagnetic Resonance Simulation in PyTorch (arxiv.org)

Popularity Trajectories and Mixing Patterns of Urban Venues in Two European Cities (arxiv.org)

Distinguishing Process Change, Instrument Fault and Data-Path Corruption in Streaming Telemetry: A Reference Implementation and Benchmark (arxiv.org)

AI-Driven, Timing-Aware Power Optimization (arxiv.org)

Fitting Every Hint Is Not Enough: Premature Floods in Recurrent Algorithmic Reasoners (arxiv.org)

Humans vs. Machines: A Comparison With AI Agents in Software Reverse Engineering (arxiv.org)

Counterfactual Rollouts for Offline Contrastive Goal-Conditioned Reinforcement Learning (arxiv.org)

Probabilistic Multi-Source Data Selection via Learnable Categorical Priors: Variance Reduction and Guaranteed Derandomization (arxiv.org)

Physics-Guided Multi-Fidelity Surrogate Modeling for Natural Supercavity Geometry of an Axisymmetric Conical Cavitator (arxiv.org)

Select or Rewrite: Oracle-Guided Fine-Tuning for Generative ASR Post-Editing from N-Best Hypotheses (arxiv.org)

Getting Space Right: Agentic Rewards for Image Generation (arxiv.org)

Cross-Lingual TTS for Indian Languages: A Benchmark and Inference-Time Duration Estimation Strategies (arxiv.org)

AI-Native Product Management: A Vision (arxiv.org)

Seamless Deployment of Machine Learning Inference at the Far Edge: An Empirical AWS IoT Greengrass Architecture for Industrial Predictive Maintenance (arxiv.org)