AI News

CausalBind: Causal Modeling and Learning for Protein-Molecule Virtual Screening (arxiv.org)

Selective Critique for Cost-Aware LLM Agents in Long-Horizon Decision Making (arxiv.org)

Decoupling What from Where: How Should a Small GUI Grounding Model Receive the Action Type? (arxiv.org)

StaFIR: Convex Learning of Stationarity-Aware Causal Filters (arxiv.org)

SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction (arxiv.org)

Benchmarking Label-Revealed Online Updates for EEG BCI Decoding (arxiv.org)

Learnable Spectral Activations (arxiv.org)

Will the Judge Flip? Predicting Position-Sensitive LLM Judgments from Residual Stream Activations (arxiv.org)

Constant-Curvature Sliced Gromov-Wasserstein for Heterogeneous Cross-Curvature Alignment (arxiv.org)

When Does AI Supervision Help? A Role-Aware Study of Network Fraud Decision Management with Blockchain Auditability (arxiv.org)

Adaptive Gait Biofeedback With Participant-Held-Out Modeling and Participant-Specific Updating in Chronic Ankle Instability (arxiv.org)

2d-fet-bench: from spatial reasoning to fet design on flakes (arxiv.org)

Defense-in-Depth for LLMs: Evaluating Memory Gates Against Activation-Induced and Memory-Induced Sycophancy (arxiv.org)

Auditable Claims about AI Agents (arxiv.org)

LiLib: Lifelong Air-to-Ground Path-Loss Prediction on UAVs via a Drift-Triggered Model Library (arxiv.org)

Muon Is Theoretically Wrong For Convolutions, But Empirically Effective (arxiv.org)

SchemaFill: Efficient LLM Tool Calling via Slot-Parallel Speculative Decoding (arxiv.org)

When Attention Does Not Explain the Peak: Temporal Reference vs. Forecast Output in Attention-Based Time-Series Forecasting (arxiv.org)

Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding (arxiv.org)

DAEDALUS: Bootstrapping Agent Memory from Self-Generated Tasks (arxiv.org)

Same Feedback, Different Answer: Measuring Run-to-Run Instability in Frontier-Model Customer Feedback Analysis (arxiv.org)

Learning in Dreams, Winning in Reality: A Continuous Dyna Loop for a Ten-Hero MOBA (arxiv.org)

Learning from Revision Consequences: Hindsight Meta-Experience Distillation for Self-Improving Agents (arxiv.org)

Can Agents Work for Everyone? Cross-User Reliability for Mobile GUI Agents in Personalized User Interfaces (arxiv.org)

Confidence Reasoning Graphs: Structured Confidence Estimation for LLM Agents (arxiv.org)

SIGMA: Self-Improving Alignment Generalization from a Model Spec (arxiv.org)

Continuous Memory Machines (arxiv.org)

Isotropic Yet Undecodable: The Sequential Content-Sufficiency Gap in Latent-Predictive Text Representations (arxiv.org)

Hub for Outliers, Spokes for Inliers: Uniform Latent Space Construction for Dual-Mismatched Semi-Supervised Learning (arxiv.org)

What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training (arxiv.org)

Fed-BRDECS: Privacy-Preserving and Heterogeneity-Aware Federated Deep Embedded Clustering (arxiv.org)

Multigroup Fairness and Omniprediction: Separations and Equivalences (arxiv.org)

Dynamic Budget Allocation for LLM Evaluation under Hard Resource Constraints (arxiv.org)

Towards Explainable Benchmarking for Data-driven Post-Wildfire Debris Flow Prediction (arxiv.org)

Energy-Conditioned Noise Schedule and Whitening for Spectral Diffusion (arxiv.org)

Sim-to-Real Transfer of Vision-Language Navigation in Continuous Environments Using an Ackermann-Steered Mobile Robot (arxiv.org)

Is this machine playing? (arxiv.org)

AMBER: Training Long-Horizon Web Agents through Append-Only Memory (arxiv.org)

Cleave: Scaling Tensor Program Optimization via Decoupled Algebraic Search and Operator Scheduling (arxiv.org)

A Data-Driven Framework for Unsupervised Monitoring of Transmission Systems Using End-of-Line Testing Data: A Case Study at Ford Motor Company (arxiv.org)

Uncertainty in Representation Learning on Knowledge Graphs (arxiv.org)

EVFormer: An Egocentric Vision-EMG Bidirectional Attention Model for Bimanual Hand Pose Estimation (arxiv.org)

Do Neural PDE Solvers Learn the Right Dynamics? (arxiv.org)

Learning to Decide, Not to Reason: Parameter-Efficient Decision Operators via Low-Rank Activation Steering (arxiv.org)

Global Transport Couplings for Classifier-Free Guided Flows (arxiv.org)

TAFFY: A Task-Adaptive Tabular Foundation Model with In-Context Diversity (arxiv.org)

When to Remember, When to Abstain: Category-Conditioned Retention for Reliable Agent Memory (arxiv.org)

Verified, not generated: expert-verified AI study materials and the distribution of learning gains in a university course (arxiv.org)

Small Language Models for Smart Data Model Classification at the Edge: A Cost-Aware Hybrid Approach (arxiv.org)

Smart Content Ingestion for Generative AI Workloads (arxiv.org)