AI News

SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise (arxiv.org)

PatientWM: Towards Generalizable Clinical World Models via Unified Patient States (arxiv.org)

VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval (arxiv.org)

BehaviorFormer: Discovering Behavioral Patterns via Clusterable Next-Token Prediction (arxiv.org)

Neos: Learning to Interleave Search and Visual Reasoning (arxiv.org)

Benchmarking Quantum Kernel SVMs for Credit Card Fraud Detection: Performance Realities Under NISQ Constraints (arxiv.org)

Understanding Personalization Gains in Whisper (arxiv.org)

Glasseek: A Transparent Recipe for Training and Trustworthy Evaluation of DeepSearch Agents (arxiv.org)

AutoMARS: Automatic and Scalable Multi-Agent Large Language Model Framework for Supply Chain Risk Assessment (arxiv.org)

PRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models (arxiv.org)

MADDIE: Multi-Agent Drug Discovery Engine (arxiv.org)

WeFair: Fidelity-Aware Alignment from Human Feedback for Personalized Query Rewriting in Short-Video Search (arxiv.org)

Transparent Information Flow Modeling for Role-Aware AI Act Assessment (arxiv.org)

Neural Bayesian Networks for Modular and Scalable Decision-Making Under Uncertainty (arxiv.org)

Observe, Share, or Predict? Disentangling Partner Information in Embodied Multi-Agent Collaboration (arxiv.org)

Transparency as Answerability: Role-Dependent Information Flow Modeling (arxiv.org)

Acceptable Misalignment (arxiv.org)

CLIVO: Differentiable Cluster-Based Instruction Mixing with Learned Validation Objectives (arxiv.org)

The Format is the Filter: Scoring Format Fixes What an LLM Judge Can Express (arxiv.org)

LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints (arxiv.org)

Game-Creation-Agents: Autonomous Game Production (arxiv.org)

Geospatial Vector Geometry as a Native Spatial Modality for Vision-Language Models (arxiv.org)

Separating Prompt Harmfulness from Interaction Safety via Partial Generation (arxiv.org)

Lost in Translation: Why Lower Bias Scores Don't Mean Fairer Models (arxiv.org)

Parameter-Efficient Temporal Domain Generalization (arxiv.org)

Bridging Academia and Industry: A Comprehensive Benchmark for Attributed Graph Clustering (arxiv.org)

On the Dynamics of Delayed Generalization in Linear Models (arxiv.org)

Queue-Aware Token Communications: Bridging AI Representation and Wireless Service (arxiv.org)

Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision (arxiv.org)

Structural Baselines Matter for Agent Failure Detection and Attribution (arxiv.org)

Does a Hosted Decision Model Respect Irrelevant Alternatives? A Pre-Registered Test of Option-Set Dependence in Jev (arxiv.org)

LATCH: LLM-Assisted Timing Closure Harness for Post-Route FPGA Optimisation (arxiv.org)

Rational Transductors (arxiv.org)

Deep Time-series Forecasting Needs Kernelized Moment Balancing (arxiv.org)

SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning (arxiv.org)

Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification (arxiv.org)

Long-Range Distillation: Distilling 10,000 Years of Simulated Climate into Long Timestep AI Weather Models (arxiv.org)

When 1+1 Backfires: Rethinking Relevance-Diversity Balancing for Sample-Aware Visual Token Reduction (arxiv.org)

Double-Rollout Reinforcement Learning with Sampling-based Reward Estimation (arxiv.org)

G$^2$WAM: World Action Models for Efficient and Geometry Grounded Image-Goal Navigation (arxiv.org)

Audit tools of the trade: Automated Auditor Elicitation Can Be Sensitive to the Context the Auditor Is Given (arxiv.org)

A Versatile Variational Quantum Kernel Framework for Non-Trivial Classification (arxiv.org)

AI Discovery in Combinatorics: From Problems to Solutions and Back to Bigger Problems (arxiv.org)

Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels (arxiv.org)

Overtaught, Underlearned: Learner-Centered Distillation from Multi-Agent Discussion (arxiv.org)

Does the Explanation Drift Before the Guarantee? Label-Free Early Warning on Evolving Graphs (arxiv.org)

Rule-based and reinforcement-learning policies for resource allocation in a pediatric echo lab: a simulation study (arxiv.org)

EAU: Environment-Agent-User Co-evolution for Training User-Centric Agents (arxiv.org)

Boosting the Learning for Ranking Patterns (arxiv.org)

PXRD-Bench: How Close Are We to Determining Crystal Structures from Powder Diffraction? (arxiv.org)