arXiv:2605.22968v1 Announce Type: new Abstract: Machine learning methods provide a methodological innovation that can help screen for cardiovascular disease through noninvasive and readily available measurement modalities. Recent investments in using electrocardiogram (ECG) data to screen for structural heart disease (SHD) are one example, where ECGs provide a low-cost, available modality for screening. This has led […]
CVSearch: Empowering Multimodal LLMs with Cognitive Visual Search for High-Resolution Image Perception
arXiv:2605.23655v1 Announce Type: cross Abstract: High-resolution (HR) image perception presents a key bottleneck for multimodal large language models (MLLMs). While visual search offers a promising solution, existing methods struggle with the trade-off between coverage and efficiency. Visual expert-assisted search is efficient but prone to blind spots when proposals fail, whereas scan-based search guarantees coverage at […]
Active Sensing Subserves Task-Level Control
arXiv:2605.22988v1 Announce Type: new Abstract: Active sensing is traditionally defined as the expenditure of energy, typically in the form of movement, for obtaining information. Here, we propose that the combination of reliance on adaptive sensors, the linkage between movement and sensing, and task-level control inevitably gives rise to the emergence of active sensing movements. In […]
Test-Time Training Undermines Safety Guardrails
arXiv:2605.22984v1 Announce Type: cross Abstract: Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such as few-shot learning, retrieval-augmented generation, and complex reasoning. However, this dynamic adaptation introduces new vulnerabilities that adversaries can exploit to jailbreak models. We identify three threat models for TTT […]
A Mathematical Reconstruction of Endothelial Cell Networks
arXiv:2405.09748v2 Announce Type: replace Abstract: Endothelial cells form the linchpin of vascular and lymphatic systems, creating intricate networks that are pivotal for angiogenesis, controlling vessel permeability, and maintaining tissue homeostasis. Despite their critical roles, there is no rigorous mathematical framework to represent the connectivity structure of endothelial networks. Here, we develop a pioneering mathematical formalism […]
MadEvolve: Evolutionary Optimization of Trading Systems with Large Language Models
arXiv:2605.23007v1 Announce Type: cross Abstract: We explore the application of LLM-driven algorithm optimization to several common tasks in quantitative finance. MadEvolve, a general-purpose algorithm optimization framework inspired by DeepMind’s Alpha-Evolve, was recently developed to optimize algorithms in computational cosmology. Here we demonstrate the utility of MadEvolve to optimize algorithmic trading strategies and alpha generation at […]
Integrating Cognitive Load and Embodied Cognition Theories Through Representations as Multi-Scale Attractors
arXiv:2605.23012v1 Announce Type: new Abstract: This article proposes a formal rapprochement between cognitive load theory and embodied cognition by reconceptualizing psychological representations as dynamic multiscale attractors within a temporal-hierarchical prediction architecture. The apparent conflict between the two theories dissolves when viewed through a complex systems lens. Cognitive load theory describes compressed representations operating at medium […]
VGAS: Value-Guided Action-Chunk Selection for Few-Shot Vision-Language-Action Adaptation
arXiv:2602.07399v2 Announce Type: replace Abstract: Vision–Language–Action (VLA) models bridge multimodal reasoning with physical control, but adapting them to new tasks with scarce demonstrations remains unreliable. While fine-tuned VLA policies often produce semantically plausible trajectories, failures often arise from unresolved geometric ambiguities, where near-miss actions lead to divergent execution outcomes under limited supervision. We study few-shot […]
Decomposing and Measuring Evaluation Awareness
arXiv:2605.23055v1 Announce Type: cross Abstract: Frontier language models sometimes recognize that they are being evaluated and adjust their behavior, undermining validity of benchmark results. Yet the field studies it without a shared foundation, conflating properties of the evaluation with properties of the model, and detection with behavioral response. We ground evaluation awareness in social psychology, […]
The Deterministic Horizon: Impossibility Results as Design Specifications for Trustworthy AI Systems
arXiv:2605.23024v1 Announce Type: new Abstract: Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Free Lunch theorems, shape what computation can do. This thesis turns such impossibility results from curiosities into design rules. Its flagship result proves an accuracy ceiling set […]
Dithering Defense: Adversarial Robustness of Vision Foundation Models via Multi-Level Floyd-Steinberg Dithering
arXiv:2605.23065v1 Announce Type: cross Abstract: Vision foundation models are widely used as frozen backbones across many downstream tasks, making them a single point of failure under adversarial attack. We study multi-level Floyd-Steinberg error-diffusion dithering as a lightweight, model-agnostic input transformation that disrupts adversarial perturbations while preserving semantic content. Unlike prior work, which was limited to […]
Atom-level Protein Representation Learning Improves Protein Structure Prediction
arXiv:2605.22133v2 Announce Type: replace Abstract: Recent advances in generative modeling show that pretrained representations can improve generation as conditioning features or alignment targets. Motivated by this, we study protein representations for predicting structures beyond conventional function annotation. We propose TriProRep, a structure-aware pretraining method that jointly models three aligned residue-level views: amino-acid identity, backbone geometry, […]