AI News

Active Client Selection in Federated Trajectory Prediction with Uncertainty-Awareness and Heterogeneous Complexity (arxiv.org)

A Computational Framework for Modelling Organisation-Level Semantic Identity from Longitudinal Textual Data (arxiv.org)

Investigating White Blood Cells as a Source of False-Positive Malaria Parasite Detection in African Blood-Smear Images (arxiv.org)

Augur: A Synthetic Decision Lab for Rehearsing Reactions to Product and Policy Changes (arxiv.org)

Underwater C3-JEPA: An Object-Centric Cross-View World Model for ROV Salvage (arxiv.org)

Does a model's stated reason for rejecting a candidate do any work? (arxiv.org)

R-DEIM Net: An Efficient Rationale-Augmented Dual-Expert Interaction Model for Paraphrase Detection (arxiv.org)

Accelerating Video Diffusion via Training-Free Trajectory Routing (arxiv.org)

Federated Learning of AnDE Classifiers (arxiv.org)

Precise Convergence Speed of Clipped SGD (arxiv.org)

Decoupled Learning and Selection in Slate Recommendation for Privacy and Stability Under Noisy Scores (arxiv.org)

SPADE-DFL: Communication-Efficient Decentralized Federated Learning via Derivative-Free Linearized ADMM (arxiv.org)

ICE: Task-Aligned Clifford Latent Fields for Multimodal Graph Foundation Models (arxiv.org)

ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation (arxiv.org)

AT-SKM-Net: An Accelerated Trainable Sampling Kaczmarz-Motzkin Framework for Linear Hard-Constraint Feasibility on Dynamic Graphs (arxiv.org)

DCRMTA: Deep Causal Representation Learning for Multi-Touch Attribution (arxiv.org)

How Reproducible Are Evaluation Conclusions? A Self-Audit of LLM-Inferred Prompt Structure (arxiv.org)

KernelOPT: Dispatch-Aware Agentic Search for GPU Kernel Optimization (arxiv.org)

Can Labor Markets Function in the Age of AI? The Evaluation Bottleneck in Hiring (arxiv.org)

Era by Eon: Benchmarking Enterprise Agents on Hidden Knowledge (arxiv.org)

Canopy: Exploiting Piecewise Smooth Tree Priors for Multi-Fidelity Bandits (arxiv.org)

Low-Cost Assays for Measuring Model Behavior Across Vendors and Releases (arxiv.org)

TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction (arxiv.org)

Neuralized Multi-Wavelet Decomposition for Time Series Classification and Forecasting (arxiv.org)

Beyond Feature Reliability: Repeat-Informed Multifractal Curve Regression for Brain-Age Prediction (arxiv.org)

Online Task Adaptation via Self-Organisation (arxiv.org)

Stable and Faithful Explanations for Knowledge Tracing (arxiv.org)

FlowAtom: Atom-Based Evidence Aggregation for Multi-Label Website Fingerprinting (arxiv.org)

Guardrails or Roadblocks? Effects of Pedagogical Style and Context Awareness in AI Teaching Assistants for Programming (arxiv.org)

From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation (arxiv.org)

Learning Better Reasoning for Generative Recommendation with Semantic IDs (arxiv.org)

World Action Agent: Harnessing VLMs for Robot Manipulation via World Action Rehearsal (arxiv.org)

Automated Regulatory Compliance Question Answering in Financial Services with Domain-Adapted Retrieval-Augmented Generation (arxiv.org)

ADATEX4D: adaptive texture capacity allocation for 4D gaussian splatting (arxiv.org)

Beyond Average Safety: Chance-Constrained LLM Fine-tuning (arxiv.org)

Tracking States or Tracking Cosets? An Algebraic Account of Learned State Tracking (arxiv.org)

Mind What Matters for Reasoning: Aligning Cross-Modal Attention via Selective Probability Mass Concentration (arxiv.org)

Safe Skill Retirement for Physical Agents (arxiv.org)

Clinical Knowledge Graphs for Chest X-Ray Device Reasoning (arxiv.org)

Delay-of-Gratification as a Multi-Agent Survival Micro-benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets (arxiv.org)

Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy (arxiv.org)

SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories (arxiv.org)

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures (arxiv.org)

Upholding Robustness in Federated Learning: Trends, Emerging Strategies, and Research Opportunities (arxiv.org)

NNV3: Expanding Neural Network Verification to New Architectures and Domains (arxiv.org)

LabFactory: Building and Evaluating Executable AI Labs (arxiv.org)

Thinking Leakage: A Causal Audit of NoThink Post-Training in Hybrid Reasoning Models (arxiv.org)

Beyond Static Graph World Models: Learning Stochastic Latent Dynamics over Evolving Topologies (arxiv.org)

OPDiv: Optimal Selection of Top-K High-Scoring, Diverse Compounds (arxiv.org)

Wearable ECG Quality Assessment: A Deep Learning and Ambulatory Context-Awareness Approach (arxiv.org)