AI News

Physical knowledge on historical data matters more than enforcing physical constraints on the forecast (arxiv.org)

TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives (arxiv.org)

For Your Eyes Only: Evaluating Coordination Between Isolated Language Model Instances (arxiv.org)

CoreSense: Traceable Failure Recall and Conflict-Aware Belief Gating for Auditable Robot Decisions (arxiv.org)

AURORA: A Natural Language-Driven Agentic Framework for Understanding, Reasoning, and Orchestrating Reliable Air-Ground Co-Simulation (arxiv.org)

Detecting Soft Errors in Parallel Software with LLM-tuned Instruction Duplication (arxiv.org)

FacetCRS: Multi-Faceted Preference Learning for Pricking Filter Bubbles in Conversational Recommender System (arxiv.org)

Music Hallucination in Audio-Language Models: A Hierarchical Formulation and Empirical Study (arxiv.org)

MAS-Shield: A Defense Framework for Secure and Efficient LLM MAS (arxiv.org)

FAMOS: Feed-Forward 3D Articulation Modeling from Sparse Observations (arxiv.org)

CoMa: Contextual Massing Generation with Vision-Language Models (arxiv.org)

Sim-and-Human Co-training for Data-Efficient and Scene-Generalizable Bimanual Manipulation (arxiv.org)

Cross-Sectional Asset Retrieval via Future-Aligned Soft Contrastive Learning (arxiv.org)

When Consistency Becomes Bias: Interviewer Effects in Semi-Structured Clinical Interviews (arxiv.org)

Large language models eroding science understanding: an empirical study of malignment (arxiv.org)

Interactive proofs for verifying (quantum) learning and testing (arxiv.org)

Perspective of Software Engineering Researchers on Machine Learning Practices Regarding Research, Review, and Education (arxiv.org)

A Large-Scale Vision-Language Dataset Derived from Open Scientific Literature to Advance Biomedical Generalist AI (arxiv.org)

Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks (arxiv.org)

Enabling automatic transcription of child-centered audio recordings from real-world environments (arxiv.org)

Evaluating Out-of-Distribution Robustness in Graph-Based Android Malware Classification: A New Principled Benchmark (arxiv.org)

Learn2Drive: A neural network-based framework for socially compliant automated vehicle control (arxiv.org)

Comparison of Image Processing Models in Quark Gluon Jet Classification (arxiv.org)

UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation (arxiv.org)

Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation (arxiv.org)

Understanding Role Switching in Human-AI Collaboration through Multimodal Behavioral Signals (arxiv.org)

BuildBench: Benchmarking LLM Agents on Compiling Real-World Open-Source Software (arxiv.org)

Learning and Transferring Closed-Loop Robot Software (arxiv.org)

KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms (arxiv.org)

Efficiently Distributed Federated Learning (arxiv.org)

FedFIbOS: Fisher Importance based Optimal Submodelling for Heterogeneous Federated Learning (arxiv.org)

The Complexity Kink: A Prompt-Side Structural Complexity Index for Code-Generation Reliability (arxiv.org)

LSTM-UT and Recurrent-Depth Transformers on Cellular Automata (arxiv.org)

MaskHarness-WAM: Instance-Grounded Harnessing for Long-Horizon Robot Manipulation (arxiv.org)

Past, Future, All at Once: Mitigating Stability-Plasticity Dilemma via Post-hoc JANUS Rectification (arxiv.org)

AVTrace: Diagnosing Audio-Visual Temporal Reasoning in Omni Models (arxiv.org)

Long-horizon autoformalization of a core theorem underlying MIP* = RE (arxiv.org)

Reproducing Transparent and Scrutable Recommendations: Exploring Open-Weight Models via Natural-Language User Profiles (arxiv.org)

When fairness metrics fail: A utility-based perspective on $\varepsilon$-fairness (arxiv.org)

Personalized Federated Hierarchical Gaussian Processes for Privacy-Preserving Modeling of Heterogeneous Distributed Systems (arxiv.org)

Recursive Quantum Long Short-Term Memory for Stable Short-Horizon Temperature Forecasting (arxiv.org)

COIN-GP: Cooperative Online Learning in Networked Distributed Systems with Partial Measurements via Gaussian Process Regression (arxiv.org)

Trust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression Proxies (arxiv.org)

Improving Cross-embodiment Transfer in Latent Action Models with Action-Similarity Supervision (arxiv.org)

PACE: Precise AI Cinematic Expression: A Typed Specification for Script-Grounded Previsualization and Geometric Conformance (arxiv.org)

Multi-center Medical Data Mining with FL-Net - A One-stop Shop for Federated Learning (arxiv.org)

COMPASS: Ordered Clustered Routing at 100K Scale (arxiv.org)

Integrating knowledge from case reports: a medical ontology based multimodal information system with structured summary (arxiv.org)

Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure (arxiv.org)

A Functional Pilot for Certified Freshness-Aware Semantic--Spatial Range Retrieval (arxiv.org)