arXiv Machine Learning
Jul 28
Smooth Learning with Hard Constraints via Legendre-Regularized Policies
arXiv:2607. 24007v1 Announce Type: cross Abstract: We revisit contextual optimization from the perspective of policy class design.
Benchmarks and evaluation
Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv AI
Jul 28
Computational Experiments in Number Theory
arXiv:2504. 19451v4 Announce Type: replace-cross Abstract: This paper presents two concrete applications of Artificial Intelligence to algorithmic and analytic number theory.
arXiv AI
Jul 28
VLASH: Real-Time VLAs via Future-State-Aware Asynchronous Inference
arXiv:2512. 01031v2 Announce Type: replace-cross Abstract: Vision-Language-Action models (VLAs) are becoming increasingly capable across diverse robotic tasks.
arXiv Machine Learning
Jul 28
Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems
arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.
arXiv Machine Learning
Jul 28
Corner Reflector Array Jamming Discrimination Using Multi-Dimensional Micro-Motion Features with Frequency Agile Radar
arXiv:2604. 16008v3 Announce Type: replace Abstract: This paper introduces a robust discrimination method for distinguishing real ship targets from corner-reflector-array jamming with frequency-agile radar.
arXiv AI
Jul 28
Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction
arXiv:2607. 18985v2 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge.
arXiv Machine Learning
Jul 28
PerturbPFN: Probing the Limits of Synthetic Priors in Drug Perturbation Modelling
arXiv:2607. 23447v1 Announce Type: new Abstract: Predicting cellular responses to unseen chemical perturbations is challenging due to unknown targets and mechanisms, high-dimensional expression responses, and limited experimental coverage of the large small-molecule design space.
arXiv Machine Learning
Jul 28
DriveDNA: A Large-Scale Multimodal Naturalistic Driving Dataset and Benchmark for Driving Style Identification
arXiv:2607. 23822v1 Announce Type: new Abstract: Driving style captures stable, driver-specific patterns in how a vehicle is driven.
arXiv Machine Learning
Jul 28
Explainable Reinforcement Learning via Physics-Aware Policy Distillation
arXiv:2607. 24672v1 Announce Type: new Abstract: In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks.
arXiv AI
Jul 28
Scaling GUI Agents with Visual State Transitions
arXiv:2607. 24112v1 Announce Type: new Abstract: We introduce State Transition Pretraining (STP) as a new scaling axis for GUI agents.
arXiv Machine Learning
Jul 28
Source-Free Controlled Adaptation of Teachers for Continual Test-Time Adaptation
arXiv:2607. 23735v1 Announce Type: new Abstract: In many real-world scenarios, encountering continual shifts in domain during inference is very common.
arXiv AI
Jul 28
ADAGE: A Language-Agnostic Pipeline for Analogical Reasoning Evaluation
arXiv:2607. 23058v1 Announce Type: cross Abstract: Multilingual reasoning evaluation overwhelmingly relies on translating English benchmarks, a practice that introduces linguistic artifacts and fails to test culturally-grounded reasoning.
arXiv Machine Learning
Jul 28
Self-Boosting Vision-Language Models with Noisy Student On-Policy Self-Distillation
arXiv:2607. 23125v1 Announce Type: new Abstract: Post-training enables vision-language models (VLMs) to understand human instructions and perform various downstream tasks.
arXiv AI
Jul 28
scMIR: a vision-language foundation model for single-cell light microscopy image representation
arXiv:2607. 22712v1 Announce Type: cross Abstract: Single-cell light microscopy images have become an important data source for characterizing cell phenotypes, but their complexity and heterogeneity pose challenges to high-throughput automated analysis.
arXiv Machine Learning
Jul 28
SPRKD: Effective Knowledge Distillation for Deep Neural Networks via Saddle Region Approximation
arXiv:2607. 23346v1 Announce Type: new Abstract: Modern deep neural networks are potent catalysts for scientific and industrial impact, yet excessive parameter counts impede deployment in low-compute settings such as hospital equipment and energy infrastructure.
arXiv AI
Jul 28
UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation
arXiv:2602. 19349v2 Announce Type: replace-cross Abstract: LiDAR-camera fusion enhances 3D panoptic segmentation by leveraging camera images to complement sparse LiDAR scans, but it also introduces a critical failure mode.
arXiv AI
Jul 28
How Context Attribution Handles What the Model Already Knows
arXiv:2607. 23804v1 Announce Type: cross Abstract: Context attribution methods for large language models (LLMs) identify which input context contributes to the model response.
arXiv AI
Jul 28
LU-500: A Logo Benchmark for Concept Unlearning
arXiv:2607. 24101v1 Announce Type: cross Abstract: Concept unlearning is increasingly used to limit the reproduction of protected or unsafe visual concepts in text-to-image models.
arXiv AI
Jul 28
PhononBench-MP40: a spectrum-resolved benchmark dataset for phonon stability
arXiv:2607. 22573v1 Announce Type: new Abstract: Imaginary phonon modes remain a practical bottleneck in computational materials screening because otherwise plausible structures can be locally dynamically unstable under a chosen workflow.
arXiv AI
Jul 28
VlogReward: Learning Multi-Dimensional Evaluation for Vlog Editing
arXiv:2607. 22632v1 Announce Type: new Abstract: The rapid rise of vlogs as a personalized storytelling medium has created a demand for automated systems to evaluate and refine vlog editing plans.