AI News

Hierarchical Projection for Adaptive Knowledge Transfer (arxiv.org)

Agentic Search for Counterfactual Recourse under Fixed LLM Budgets (arxiv.org)

SNR-ST-Mix: Sample-specific Neighborhood Regression Mixup for Augmented Spatial Transcriptomics Imputation with Deep Neural Network (arxiv.org)

Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency (arxiv.org)

A Geometric Measure of Linear Separability for Neural Representations (arxiv.org)

Declarative Outcome-Conformant Synthesis: Exact, Closed-Form Specification Satisfaction and a Conformance Benchmark (arxiv.org)

Understanding the Parameter Space Geometry of Transformers Encoding Boolean Functions (arxiv.org)

How Many Counterfactuals Does It Take? Probing VLM Hallucinations Through Circuits and Causal Effects (arxiv.org)

Reformulate LLM Reinforcement Learning for Efficient Training under Black-box Discrepancy (arxiv.org)

Stabilizing On-Policy Distillation for MLLM Reasoning with Global Normalization (arxiv.org)

mllm-shap: A Shapley Value Explainability Platform for Text-Audio Multimodal Large Language Models (arxiv.org)

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models (arxiv.org)

Bridging Traditional Explainability Methods and Multimodal Multilingual Models: An XAI-Based Analysis (arxiv.org)

Beware of GeeksBearing Gifts: Building True EU Frontier AI Sovereignty (arxiv.org)

Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents (arxiv.org)

Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation (arxiv.org)

DIYHealth Suite: Dataset, Model, and Benchmark for Health Management at Home (arxiv.org)

Concerns and Strategic Responses of Older Workers Navigating Generative AI in Bridge Employment (arxiv.org)

AI-Integrated Learning Management System for Middle School: A Longitudinal Study of Learning Outcomes Through High School and Beyond (arxiv.org)

Beyond Item IDs: Scaling Short-Form-Video Recommendation via Semantic-Native Long Sequence Modeling (arxiv.org)

Liberating LLM Capabilities in Full-Duplex Speech Models (arxiv.org)

The Montparnasse Algorithm for RNA Design (arxiv.org)

Considerations for an Integrated Detector Design at FCC-ee: A Human-AI Exploration (arxiv.org)

Symbolic Reasoning Frameworks Modulate LLM Risk Aversion in Multi-Agent Strategic Settings (arxiv.org)

Selecting New Measurement Locations to Diversify Traffic-Pattern Coverage: A Real-World Evaluation for Total Traffic Volume Estimation (arxiv.org)

Page image classifier fine-tuned on century-spanning archives of scanned documents for further content-specific processing (arxiv.org)

Phantom transitions in language model fine-tuning (arxiv.org)

SurfDesign: Effective Protein Design on Molecular Surfaces (arxiv.org)

A Systematic Study of Behavioral Cloning for Scientific Data Annotation (arxiv.org)

Disentanglement with Holographic Reduced Representations (arxiv.org)

Preserving Plasticity in Continual Learning via Dynamical Isometry (arxiv.org)

iOSWorld: A Benchmark for Personally Intelligent Phone Agents (arxiv.org)

Zero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge Continuum (arxiv.org)

Topological Neural Operators (arxiv.org)

Rethinking the Divergence Regularization in LLM RL (arxiv.org)

An Agency-Transferring Model-Free Policy Enhancement Technique (arxiv.org)

Multimodal Group Emotion Recognition In-the-Wild Towards a Privacy-Safe Non-Individual Approach (arxiv.org)

SlideCheck: Guiding Self-Supervised Pretraining of Pathology Foundation Models via Dataset Distributions (arxiv.org)

A Mechanistic Analysis of Adversarial Fine-tuning of Vision Transformers (arxiv.org)

VisualLeakBench: Reproducible Action-Boundary Propagation Failures in Vision-Language Agents (arxiv.org)

TinyJudge: Unverifiable Constraint Alignment via Lightweight Specialist Ensembles (arxiv.org)

Community-Specific Slang and Entity Detection via Semantic Shift in Fine-Tuned Language Models (arxiv.org)

CAPruner: Conceptual-Adjacent Scene Graph Pruner for Enhancing 3D Spatial Reasoning of Large Language Models (arxiv.org)

Priors Persist Through Suppression: A Stroop Paradigm for Lexical Override (arxiv.org)

Function-Vector Heads Are Two Populations: Writers and Cancellers in In-Context Learning (arxiv.org)

Can LLMs extract scientific consensus? A case study in high-temperature superconductivity (arxiv.org)

Forecasting Japanese elections: A nonlinear machine-learning approach (arxiv.org)

Forward-Looking Stress Testing Under Macro Scenarios: Stable SVaR Estimation Using a Hybrid GPR-HS Framework with SACS (arxiv.org)

Quantifying Uncertainty in Space Debris Capture with Active Tether-Net Systems Caused by Noisy Observations (arxiv.org)

Information-Geometric Optimization on Spheres (arxiv.org)