Staffing & Scheduling

Prototype Latent World Model Replay for Class-Incremental Learning

Class-incremental learning requires a model to learn new classes while preserving decision regions for old ones. This is difficult when raw old samples are no longer available. We propose Prototype Latent World Model Replay, a memory-free framework that stores old classes as distributions over stable hidden states rather than as images. A frozen ImageNet-pretrained encoder maps each image into a l...

Noradrenergic administration improves cognitive flexibility even after glutamatergic damage in rat mediodorsal thalamus or thalamic nucleus reuniens

Cognitive flexibility, switching behaviour responses to changing task demands, is classically attributed to the prefrontal cortex. Prefrontal thalamocortical circuits from mediodorsal thalamus (MD) or thalamic nucleus reuniens (RE) are altered in neurological conditions with cognitive flexibility deficits. Interventions targeting thalamocortical interactions may offer therapeutic benefits. Using t...

Long-term memory performance optimization via Neural network-based curve fitting in Drosophila

Long-term memory (LTM) formation typically requires extensive training. While operant conditioning is expected to produce stronger LTM than classical ...

Retrieval-Warmed Energy-Based Reasoning: A Five-Arm Ablation Methodology for Diffusion-as-Inference on Structured Reasoning Tasks

Warm-started diffusion samplers accelerate iterative inference, but it is rarely clear which part of the pipeline carries the gain. We study \textbf{r...

From Celebrities to Anyone: Characterizing AI Nudification Content, Technology, and Community Dynamics on 4chan

AI nudification uses generative models to create synthetic non-consensual sexually explicit imagery (SNEACI) of real individuals. Prior work has exami...

ViQ: Text-Aligned Visual Quantized Representations at Any Resolution

A unified representation for text and vision is a natural pursuit, as it enables simpler multimodal modeling and more efficient training. However, rep...

EMA-FS: Accelerating GBDT Training via Gain-Informed Feature Screening

Gradient Boosted Decision Trees (GBDT), exemplified by LightGBM, spend a dominant fraction of training time -- typically 65-70% -- constructing per-fe...

Shift Variant Image Degradation and Restoration Using Singular Value Decomposition

Shift-variant image degradation is frequently encountered in practical imaging systems where the point spread function (PSF) varies across the image f...

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it r...

Are Text-to-Image Models Inductivist Turkeys? A Counterfactual Benchmark for Causal Reasoning

Text-to-image (T2I) generation models have achieved remarkable progress in producing visually realistic images from natural language prompts. Yet it r...

Adaptive Hebbian Memory Routing in Vision Transformers for Few-Shot Learning

Few-shot image recognition requires models to adapt to new classes from a small labeled support set. Hebbian fast-weight memory can provide temporary ...

Federated Survival Analysis in Healthcare: A Multi-Model Evaluation on Cross-Institutional Heterogeneous Breast Cancer Data

Survival analysis is central to clinical decision-making, yet reliable time-to-event models require large, diverse cohorts that are rarely available a...

Optimal Practice Schedules in a Dual-Rate Model of Motor Adaptation, and Their Recovery by Reinforcement Learning

A clinician guiding a stroke patient through a 45-minute rehabilitation session, a coach planning a training day, a teacher choosing the order of prac...

Retrieval-Augmented Multimodal Learning for Enzyme-Substrate Interaction Prediction Under Low-Homology Shift

Enzyme substrate interaction (ESI) prediction is a fundamental computational task for biocatalyst discovery and reaction screening in large biochemica...

Leveraging AutoML for Sustainable Deep Learning: A Multi-Objective HPO Approach on Deep Shift Neural Networks

Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pos...

Curvature-aware 3D length estimation of greenhouse cucumbers using RGB-D imaging and cubic spline arc-length integration

Commercial greenhouse cucumber production is graded by fruit length, which drives harvest scheduling, labour allocation, and logistics. Manual measure...

Interpretable Uncertainty Routing Separating Emotion Ambiguity from Distribution Shift in Facial Expression Recognition

Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distr...

RNAStabFormer: Region-Aware Multi-Task Hybrid Learning for RNA Stability Prediction from Pulse-Chase Transcriptomics

RNA stability is a central layer of post-transcriptional gene regulation, yet large-scale stability labels derived from pulse-chase transcriptomics de...

Deep Learning-Based Reconstruction: Model Comparison for Variable-Density GRAPPA 1H MRSI

Proton magnetic resonance spectroscopic imaging (1H MRSI) enables quantitative mapping of brain metabolites, but its clinical use remains limited by l...

Quantization as a Malicious Task: Removing Quantization-Conditioned Backdoors via Task Arithmetic

Model quantization is widely adopted to reduce memory usage and inference cost when deploying deep neural networks on resource-constrained devices. Ho...