Staffing & Scheduling

Beyond Global Routing Aggregation: Phase-Aware Expert Merging for MoE Vision-Language Models

Mixture-of-experts vision-language models (MoE-VLMs) increase model capacity with sparse expert activation, yet deployment requires storing the full expert pool. Training-free expert merging reduces this burden, and many routing-based methods aggregate routing statistics across all tokens to determine merge compatibility. However, MoE-VLM inference is phase-structured: image-context tokens carry v...

CARVE: Cross-Slice Anisotropic Reallocation of Visual Evidence for Efficient 3D Medical Volume Understanding

Slice-based MLLMs leverage mature 2D encoders by representing 3D volumes as sequences of 2D slices. However, this slice-wise formulation produces thousands of visual tokens that burden the LLM backbone, many of which capture overlapping visual evidence across adjacent slices. To understand how effectively a growing visual token budget improves performance, we perform scaling analyses on two 3D med...

IRIS: A Visual Cortex-Inspired Framework for Analyzing Orientation Selectivity in Vision Transformers

Vision transformers (ViTs) have become the de facto standard for image encoding across many perception tasks. Despite their empirical success, it rema...

OPD-V: Visual On-Policy Self-Distillation with Modality Balance

On-Policy Self-Distillation (OPSD) has become a standard post-training approach for improving visual reasoning in multimodal large language models (ML...

RUTA: Principled Visual Token Allocation via Rate-Utility Optimization

High-resolution images and long videos provide vision-language models with rich context for multimodal reasoning and fine-grained perception, but the ...

Benchmarking Generalizability in Deep Learning-Based White Matter Tract Segmentation

White matter tracts (WMTs) are the brain's structural foundation for information transfer, underlying essential cognitive and behavioral functions. Wh...

Adaptive Two-Stage Visual Token Pruning for Efficient Inference in Video-Language Models

Vision-language models excel at image and video understanding but suffer from high inference latency due to the need to process thousands of tokens pe...

GVCCTurbo: Rate-Compute Quality Scheduling for Codebook Driven Generative Compression

Codebook-driven generative compression uses a pretrained image or video generator as a zero-shot visual prior and transmits compact codebook indices t...

ConformalShift: Targeted Event Reordering Against Adaptive ECG Monitoring

Adaptive conformal prediction can recover clinically important heartbeat classes missed by a point classifier, but delayed feedback makes its decision...

Keep the Needle, Prune the Haystack: Defect-Preserving Token Pruning for Efficient Zero-Shot Anomaly Detection

Zero-shot visual anomaly detection has achieved remarkable progress, with recent vision-only approaches further improving performance while simplifyin...

Localize, Don't Beautify: Client-Side Control of Image-Editing APIs for Cosmetic Surgery Previews

Ask a commercial image editor to preview a cosmetic procedure and it will often change more of the face than the request names: a nose edit can also s...

Schedule-Informed Temporal Fusion Forecasting of Hourly Airport Security-Checkpoint Throughput

Checkpoint staffing requires accurate forecasts of when screening demand will occur, yet flight schedules record departure times rather than passenger...

Architectural Safety Mechanisms for Multi-Agent Clinical LLM Systems Under Knowledge Base Distribution Shift

Objective: To evaluate whether multi-agent LLM architectures with explicit safety verification maintain guideline compliance when their clinical knowl...

GIFT: Geometry-Invariant Fine-Tuning for Non-Lambertian Monocular Depth Estimation

Monocular depth foundation models, benefiting from large-scale synthetic training data, have demonstrated strong generalization. However, they often h...

Rethinking PPG-based Sleep Staging: Datasets, Metrics, and Benchmarks

Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at...

SSR: Similarity-Shift Refinement for Training-Free Object-Centric Masks

Object-centric models often produce fragmented masks, boundary leakage, and incorrect region merging. We introduce Similarity-Shift Refinement (SSR), ...

Astrolabe: Spherical-Map Guidance Across Diffusion Pipelines for Full-Body Capture from Unconstrained Images

Full-body capture from unconstrained photographs requires global correspondence across arbitrary views, poses, crops, and occlusions. Yet pose, geomet...

ST-LoRA: Single Trajectory LoRA Ensemble for Uncertainty Aware Agricultural Segmentation

Reliable decision-support in digital agriculture requires accurate predictions and well-calibrated uncertainty estimates, particularly for dense predi...

SULAND v2: A Refined RGB Dataset and Deep Learning Object Detection Benchmark for UAV/UGV-Based SUrface LANDmine Detection Under Domain Shift

RGB imagery offers a practical, low-cost option for Unmanned Aerial/Ground Vehicle (UAV/UGV) survey support in surface-landmine detection, but object ...

First Investigation of Deep Learning for Intraoperative Gauze Segmentation in Minimally Invasive Abdominal Surgery

Surgical gauze is an essential part of surgical procedures, primarily used for controlling bleeding and absorbing bodily fluids. The post-surgical ret...