AI News

TianJi-Environ: An Autonomous AI Scientist for Atmospheric Environmental Research (arxiv.org)

MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models (arxiv.org)

Cross-View Urban Traffic Dataset: Drone-Supervised Ground Truth for Monocular Bird's-Eye View Localization (arxiv.org)

Scaling Decision-Focused Learning to Large Problems with Lagrangian Decomposition (arxiv.org)

Active Flow Expansion for Out-of-Distribution Discovery: from Theory to Molecules (arxiv.org)

Knowledge Graphs and Reasoning LLMs for Finding Simple Yet Effective Transcriptomic Perturbation Predictors (arxiv.org)

Diffuse AI Control on Fuzzy Tasks (arxiv.org)

Cheap Reward Hacking Detection (arxiv.org)

Synthetic but Not Realistic: The Evaluation Challenge in Generative Modelling for Structured Electronic Medical Records (arxiv.org)

Quantum-Enhanced Similarity Measures for Polarimetric Materials Classification (arxiv.org)

Beyond Point Estimates: Benchmarking Uncertainty Quantification Methods on the AION-1 Astronomical Foundation Model (arxiv.org)

Memetic Capture: A Pluralistic Policy Framework for Governing AI-Driven Cultural Disempowerment (arxiv.org)

SLMJury: Can Small Language Models Judge as Well as Large Ones? (arxiv.org)

C$^3$ache: Accelerating World Action Models with Cross Inference Chunk Cache (arxiv.org)

The ACUTE Protocol: Operationalizing Language Model Activations for Better Calibration, Utility, and Trust (arxiv.org)

Beyond English benchmarks: clinical llm evaluation in Brazilian Portuguese (arxiv.org)

Model Multiplicity for Adversarial Detection in Small Language Model Training on Edge Devices (arxiv.org)

The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models (arxiv.org)

The Cross-Architecture Substrate: A Domain-Transcendent, Calibration-Surviving Geometric Invariant of Modern Vision Encoders (arxiv.org)

Generalized Rank-based Evaluation for Knowledge Graph Completion: Perspectives, Framework, and Analyses (arxiv.org)

PROBE-Web: An Interactive System for Probing Evaluation Landscapes of Knowledge Graph Completion Models (arxiv.org)

From Hazard Functions to Language Space: Cox-Supervised Distillation of Survival Risk into a Large Language Model (arxiv.org)

Self-Consistent Generative Paths via Admissible Random Variational Transport (arxiv.org)

From inverse problems to neural operators: prediction, mechanism, and generalization of data-driven models (arxiv.org)

Online Learning with Recency: Algorithms for Sliding-window Streaming Multi-armed Bandits (arxiv.org)

LEAF: A Learning-Enabled ADMM Framework for Accelerated Convex Optimization (arxiv.org)

Structural Grid Descriptors Predict Within-Task Solver Success on ARC-AGI (arxiv.org)

TRIAGE: Dialectical Reasoning for Explainable Risk Prediction on Irregularly Sampled Medical Time Series with LLMs (arxiv.org)

DynaCF: Mitigating Shortcut Learning in Reward Models via Dynamic Counterfactual Sensitivity (arxiv.org)

Decoy-Calibrated Failure Audits for Language Models (arxiv.org)

Larch: Learned Query Optimization for Semantic Predicates (arxiv.org)

Decoupling Semantics and Logic: A Training-Free Coarse-to-Fine Pipeline for Video Retrieval-Augmented Generation (arxiv.org)

Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation (arxiv.org)

POISE: Position-Aware Undetectable Skill Injection on LLM Agents (arxiv.org)

From `May' to `Is': Certainty Distortion in Language Model Rewriting (arxiv.org)

RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attacks (arxiv.org)

Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidents (arxiv.org)

HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning (arxiv.org)

Beyond Convolution: Advancing Hypergraph Neural Networks with Hypergraph U-Nets (arxiv.org)

Stage-1 Controls the Entropy Regime, Not the Outcome (arxiv.org)

OnlyDense: Reduced-Order Modeling for Lagrangian simulation (arxiv.org)

A Unifying Lens on Reward Uncertainty in RLHF (arxiv.org)

SHIELD-IDS: Structurally Heterogeneous Ensemble with Integrated Layered Defense for Intrusion Detection Systems (arxiv.org)

Steer Where It Matters: Token-Level Visual-Sensitivity Steering for LVLMs Hallucination Mitigation (arxiv.org)

SC3: The Multi-Solvent Solubility Challenge and Benchmark (arxiv.org)

QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition (arxiv.org)

What neurosurgeons need to see: synthetic intra-operative MRI from ultrasound for brain-shift compensation in brain tumour surgery (arxiv.org)

Reconstructing Synthetic SDO/AIA 193 A EUV Images from He I 10830 A Observations with Diffusion Model Translator (arxiv.org)

FiberTune: Preserving Action-Fiber Visual Residuals in Vision-Language-Action Fine-Tuning (arxiv.org)

Latent Diffusion Policy: Shaping Latent Spaces for Diffusion-Based Robotic Manipulation (arxiv.org)