arXiv:2604.07393v3 Announce Type: replace-cross Abstract: Accurate forecasting of industrial time series requires balancing predictive accuracy with physical plausibility under non-stationary operating conditions. Existing data-driven models often achieve strong statistical performance but struggle to respect regime-dependent interaction structures and transport delays inherent in real-world systems. To address this challenge, we propose DSPR (Dual-Stream Physics-Residual Networks), a […]
Pretraining Objective Matters in Extreme Low-Data FGVC: A Backbone-Controlled Study
arXiv:2605.15599v2 Announce Type: replace-cross Abstract: Extreme low-data fine-grained classification is common in expert domains where labeling is expensive, yet practitioners still need principled guidance for selecting pretrained encoders. We study emerald inclusion grading with a custom dataset of labeled images across three classes and ask: under matched backbone capacity, how does pretraining objective affect downstream […]
Targeted Downstream-Agnostic Attack
arXiv:2605.19446v1 Announce Type: cross Abstract: Recently, pre-trained encoders have gained widespread use due to their strong capability in representation extraction. However, they are vulnerable to downstream-agnostic attacks (DAAs). Existing DAA methods operate under a permissive threat model, where an attack is successful if the generated downstream-agnostic adversarial examples (DAEs) change the original prediction, without requiring […]
Synergistic Foundation Models for Semi-Supervised Fetal Cardiac Ultrasound Analysis: SAM-Med2D Boundary Refinement and DINOv3 Semantic Enhancement
arXiv:2605.19799v1 Announce Type: cross Abstract: We present a semi-supervised framework for joint segmentation and classification of fetal cardiac ultrasound images. Built upon the EchoCare multi-task backbone, our method integrates SAM-Med2D for boundary refinement and leverages DINOv3 to enhance pseudo-label quality. We introduce view-specific hard masking along with a two-stage optimization strategy: an EMA phase to […]
Hierarchical Contrastive Learning for Multi-Domain Protein-Ligand Binding
arXiv:2605.19902v1 Announce Type: cross Abstract: Predicting protein-ligand binding affinity remains intractable for multi-domain proteins, where inter-domain dynamics govern molecular recognition. Existing geometric deep learning methods typically treat proteins as monolithic static graphs, suffering from rigid-body assumptions and aleatoric noise in flexible regions. To address this, we introduced HCLBind, a self-supervised framework that decouples geometric representation […]
Atoms of Thought: Universal EEG Representation Learning with Microstates
arXiv:2605.20182v1 Announce Type: cross Abstract: Learning universal representations from electroencephalogram (EEG) signals is a cutting-edge approach in the field of neuroinformatics and brain-computer interfaces (BCIs). Conventionally, EEG is treated as a multivariate temporal signal, where time- or frequency-domain features are extracted for representation learning. This paper investigates a simple yet effective EEG representation, i.e., microstates. […]
Reshaping Neural Representation via Associative, Presynaptic Short-Term Plasticity
arXiv:2601.10397v3 Announce Type: replace Abstract: Short-term synaptic plasticity (STP) is often regarded as a presynaptic filter of spikes, independent of postsynaptic activity. Recent experiments, however, indicate an associative STP that depends on pre- and postsynaptic coactivation. We develop a normative, information-theoretic theory of associative STP. Extending Fisher-information-based learning to Tsodyks-Markram synapses, we derive learning rules […]
Active Testing of Large Language Models via Approximate Neyman Allocation
arXiv:2605.10075v2 Announce Type: replace Abstract: Large language models (LLMs) require reliable evaluation from pre-training to test-time scaling, making evaluation a recurring rather than one-off cost. As model scales grow and target tasks increasingly demand expert annotators, both the compute and labeling costs needed for each evaluation rise rapidly. Active testing aims to alleviate this bottleneck […]
Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews
arXiv:2403.07183v4 Announce Type: replace-cross Abstract: We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. […]
Jailbreaking on Text-to-Video Models via Scene Splitting Strategy
arXiv:2509.22292v2 Announce Type: replace-cross Abstract: Along with the rapid advancement of numerous Text-to-Video (T2V) models, growing concerns have emerged regarding their safety risks. While recent studies have explored vulnerabilities in models like LLMs, VLMs, and Text-to-Image (T2I) models through jailbreak attacks, T2V models remain largely unexplored, leaving a significant safety gap. To address this gap, […]
NORi: An ML-Augmented Ocean Boundary Layer Parameterization
arXiv:2512.04452v2 Announce Type: replace-cross Abstract: NORi is a machine learning (ML) parameterization of ocean boundary layer turbulence that is physics-based and augmented with neural networks. NORi stands for neural ordinary differential equations (NODEs) Richardson number (Ri) closure. The physical parameterization is controlled by a Richardson number-dependent diffusivity and viscosity. The neural ODEs are trained to […]
Protein Autoregressive Modeling via Multiscale Structure Generation
arXiv:2602.04883v2 Announce Type: replace-cross Abstract: We present protein autoregressive modeling (PAR), the first multi-scale autoregressive framework for protein backbone generation via coarse-to-fine next-scale prediction. Using the hierarchical nature of proteins, PAR generates structures that mimic sculpting a statue, forming a coarse topology and refining structural details over scales. To achieve this, PAR consists of three […]