Staffing & Scheduling

Stake the Points: Structure-Faithful Instance Unlearning

Machine unlearning (MU) addresses privacy risks in pretrained models. The main goal of MU is to remove the influence of designated data while preserving the utility of retained knowledge. Achieving this goal requires preserving semantic relations among retained instances, which existing studies often overlook. We observe that without such preservation, models suffer from progressive structural col...

Adaptation of Weakly Supervised Localization in Histopathology by Debiasing Predictions

Weakly Supervised Object Localization (WSOL) models enable joint classification and region-of-interest localization in histology images using only image-class supervision. When deployed in a target domain, distributions shift remains a major cause of performance degradation, especially when applied on new organs or institutions with different staining protocols and scanner characteristics. Under s...

ForensicZip: More Tokens are Better but Not Necessary in Forensic Vision-Language Models

Multimodal Large Language Models (MLLMs) enable interpretable multimedia forensics by generating textual rationales for forgery detection. However, pr...

PhosSight: a Unified Deep Learning Framework Boosting and Accelerating Phosphoproteome Identification to Enable Biological Discoveries

Protein phosphorylation is a key regulator of signaling, with mass spectrometry (MS) based phosphoproteomics serving as the premier technology for its...

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity

Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows th...

Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation

While Diffusion Models excel in text-to-image synthesis, they often suffer from concept omission when synthesizing complex multi-instance scenes. Exis...

Prune Redundancy, Preserve Essence: Vision Token Compression in VLMs via Synergistic Importance-Diversity

Vision-language models (VLMs) face significant computational inefficiencies caused by excessive generation of visual tokens. While prior work shows th...

Multi-Kernel Gated Decoder Adapters for Robust Multi-Task Thyroid Ultrasound under Cross-Center Shift

Thyroid ultrasound (US) automation couples two competing requirements: global, geometry-driven reasoning for nodule delineation and local, texture-dri...

MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data

Contrastive learning has become a fundamental approach in both uni-modal and multi-modal frameworks. This learning paradigm pulls positive pairs of sa...

Towards High-resolution and Disentangled Reference-based Sketch Colorization

Sketch colorization is a critical task for automating and assisting in the creation of animations and digital illustrations. Previous research identif...

CLoPA: Continual Low Parameter Adaptation of Interactive Segmentation for Medical Image Annotation

Interactive segmentation enables clinicians to guide annotation, but existing zero-shot models like nnInteractive fail to consistently reach expert-le...

Self-Supervised Flow Matching for Scalable Multi-Modal Synthesis

Strong semantic representations improve the convergence and generation quality of diffusion and flow models. Existing approaches largely rely on exter...

dAMN: a genome scale neural-mechanistic hybrid model to predict bacterial growth dynamics

This study presents dAMN, a hybrid neural-mechanistic model that integrates neural networks with genome-scale dynamic flux balance analysis (dFBA) to ...

BEGA-UNet: Boundary-Explicit Guided Attention U-Net with Multi-Scale Feature Aggregation for Colonoscopic Polyp Segmentation

Accurate polyp segmentation from colonoscopy images is critical for colorectal cancer prevention, yet the generalization of deep learning models under...

UniPAR: A Unified Framework for Pedestrian Attribute Recognition

Pedestrian Attribute Recognition is a foundational computer vision task that provides essential support for downstream applications, including person ...

Layer by layer, module by module: Choose both for optimal OOD probing of ViT

Recent studies have observed that intermediate layers of foundation models often yield more discriminative representations than the final layer. While...

Frequency-Aware Error-Bounded Caching for Accelerating Diffusion Transformers

Diffusion Transformers (DiTs) have emerged as the dominant architecture for high-quality image and video generation, yet their iterative denoising pro...

Faster science, penalties in evaluation, and concerns on quality and impact: Researchers' use and perceptions of preprints

The preprint ecosystem has expanded rapidly over the past decade, fundamentally altering science communication. Yet, the scholarly community's attitud...

Design and Rationale of the My Heart Counts Cardiovascular Health Study: a Large-Scale, Fully Digital Biobank, and Randomized Trial of Large Language Model-Driven Coaching of Physical Activity

Background: Cardiovascular disease remains the leading cause of global morbidity and mortality. The original My Heart Counts smartphone application de...

An autonomous system for multi-objective continuous evolution at scale

Natural evolution is high-dimensional; organisms adapt to many pressures at once, across substrates, environments, and genetic backgrounds. Yet most d...