AI News

Evaluation of ML Resource Utilization Requires Model Life Cycle Assessment (arxiv.org)

Trait-space Monitoring for Emergent Misalignment During Supervised Finetuning (arxiv.org)

Large Language Models Should Learn Personalized Rather Than Aggregated Human Preferences (arxiv.org)

Semantic Cache Distillation: Efficient State Transfer via Reuse and Selective Patching (arxiv.org)

DOME: Learning Transferable Domain Variables from Sparse Supervision for Test-Time Adaptation (arxiv.org)

LogNEO: A GPT-Neo Reinforcement Learning Framework for Accurate Real-Time Log Anomaly Detection (arxiv.org)

Cost-Aware Speculative Execution for LLM-Agent Workflows: An Integrated Five-Dimension Method (arxiv.org)

Does Persona Make LLMs K-pop Fans? A Pilot Study of LLM-Based Online Concert Audience Agents (arxiv.org)

Agentic multi-fidelity learning of quasiparticle and excitonic properties (arxiv.org)

Learning Transfers: Kan Extensions for Neural Invariants (arxiv.org)

Sequential statistical inference for Large Language Models: Representation, validity, and monitoring (arxiv.org)

Finite Certificates for In-Context Determinacy and a Threshold Theory of Emergence in Language Models (arxiv.org)

Airport Terminal Passenger Queue Forecasting for Departure Gates and Security Checkpoints (arxiv.org)

HASA: Subnet Allocation for Compute-Constrained Model-Heterogeneous Federated Learning (arxiv.org)

Test-Time Adaptive Composition for Machine Learning as a Service (MLaaS) in IoT Environments (arxiv.org)

Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence (arxiv.org)

Beyond Pass/Fail: Using Process Mining to Understand How LLMs Resist (and Fail) Red Team Attacks (arxiv.org)

Beyond Accuracy: Interpreting Topic Representation in Suicide Ideation Detection Models (arxiv.org)

FineGen: A VLM-based Multi-Agent Framework for Fine-Grained Image-Text Dataset Construction (arxiv.org)

Position: Anthropomorphic Misalignment Research Needs Stronger Evidence (arxiv.org)

From Coarse to Fine: Managing Temporal Granularity in Spatio-Temporal Data for Fine-Grained Traffic Prediction (arxiv.org)

Graph Neural Networks for Predicting Solvability of Finite Groups (arxiv.org)

ScaleSweep: Accurate NVFP4 Post-Training Quantization of LLMs via Block Scale Initialization (arxiv.org)

Query Lens: Interpreting Sparse Key-Value Features with Indirect Effects (arxiv.org)

Item Response Scaling Laws: A Measurement Theory Approach for Efficient and Generalizable Neural Scaling Estimation (arxiv.org)

Beyond Neural Collapse: Task-Intrinsic Geometry Governs Neural Representations in Modular Arithmetic (arxiv.org)

In-Context Learning for Latent Space Bayesian Optimization (arxiv.org)

On Choosing the $\mu$ Parameter in Gaussian Differential Privacy (arxiv.org)

BSTabDiff: Block-Subunit Diffusion Priors for High-Dimensional Tabular Data Generation (arxiv.org)

Asymptotic Optimality of Thompson Sampling for Risk-Averse Bandits with Sub-Gaussian Rewards (arxiv.org)

Data augmented bootstrap: Unifying confidence interval construction by approximate invariance (arxiv.org)

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin (arxiv.org)

Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs (arxiv.org)

Backward Coherence and Hidden-State Stability in Recurrent Neural Networks: A Quasi-Reverse-Martingale Theory (arxiv.org)

sGPO: Trading Inference FLOPs for Training Efficiency in RLVR (arxiv.org)

Intrinsic Selection and Particle Resampling for Inference-Time Scaling Beyond Domain Verifiability (arxiv.org)

TT-DAC-PS: Twin-Target Deterministic Actor-Critic with Policy Smoothing for Optimal Trade Execution (arxiv.org)

CP-factorization for high dimensional tensor time series and double projection iterations (arxiv.org)

Querying Counterfactuals on Tissue Graphs with Supervised Disentanglement (arxiv.org)

Nonparametric undirected graphical model selection using diffusion models (arxiv.org)

When Are Neural Interaction Discoveries Real? Identifiability, Recoverability, and a Pre-Fit Diagnostic (arxiv.org)

The Spectral Dynamics and Noise Geometry of Muon (arxiv.org)

A Switching Beamformer for Highly Non-Stationary Environments (arxiv.org)

How Deep Are Deep GPs, Really? A Sharp Threshold and a Non-Gaussian Limit for Compositional GPs (arxiv.org)

Assessing model calibration with boosting trees (arxiv.org)

Inference for High-Dimensional Sparse Spectral Precision Matrices (arxiv.org)

Partially Performative Prediction (arxiv.org)

Instrumented data for causal scientific machine learning (arxiv.org)

Large-scale empirical tuning and comparison of default optimizers for variational inference (arxiv.org)

A Framework for Evaluating and Benchmarking Concept Drift Detection Methods (arxiv.org)