Detection, segmentation, depth and recognition research, plus the vision backbones that keep displacing the last generation.
arXiv:2606. 31456v1 Announce Type: new Abstract: With an increasing number of Object Detection (OD) models being deployed on edge devices, Zero-Shot Quantization for OD (ZSQ-OD) aims to quantize these models when access to the original training data is prohibited.
arXiv:2606. 31938v1 Announce Type: cross Abstract: Deploying Vision Transformer (ViT) models on edge platforms remains challenging due to their high computational demands and the architectural heterogeneity of modern hybrid ViT models, which incorporate both fully connected and convolutional layers.
arXiv:2606. 30813v1 Announce Type: cross Abstract: Deep neural networks with repeated architectural blocks, such as transformers, often exhibit structured relationships across layers that emerge during training.
arXiv:2606. 31577v1 Announce Type: cross Abstract: Conformal predictions have attracted significant attention in the field of uncertainty quantification, mainly because of their strong marginal coverage guarantees.
arXiv:2606. 32027v1 Announce Type: cross Abstract: Reward design remains a central bottleneck for autonomous robot policy improvement, especially in long-horizon manipulation tasks where sparse success labels provide too little signal and binary preferences collapse many competing notions of quality into one ambiguous signal.
arXiv:2606. 31609v1 Announce Type: cross Abstract: Radar sensors provide reliable perception under adverse weather and lighting conditions, but their sparse, noisy, and weakly semantic measurements make dense semantic segmentation challenging.
arXiv:2603. 14579v3 Announce Type: replace-cross Abstract: Vision language models (VLMs) have shown significant promise in visual grounding for images as well as videos.
arXiv:2606. 32018v1 Announce Type: cross Abstract: Classifiers based on Deep Neural Networks exhibit strong performance across domains, yet can fail catastrophically if they rely on spurious correlations, i.
arXiv:2606. 02301v2 Announce Type: replace-cross Abstract: Chronic pain diminishes quality of life by decreasing functional ability, yet objectively measuring this functional impact remains challenging in real-world settings.
arXiv:2602. 02124v2 Announce Type: replace-cross Abstract: Drug-induced toxicity is a leading cause of preclinical and early-clinical failure, making early detection critical.
arXiv:2606. 31421v1 Announce Type: cross Abstract: Single-stage video object detectors are increasingly deployed in time-critical applications, yet it remains unclear whether these models genuinely reason over temporal context or merely exploit a single informative frame-a gap hidden by standard metrics, which reward correct predictions regardless of how they are reached.
Thermodynamic computing devices based on the Ising model show great promise for low-power AI inference and edge computing, but scalable methods for training large models for such hardware remain limited. Prior theory shows that the time-averaged behavior of high-temperature Gibbs-sampled Ising systems can implement feed-forward neural inference.
State-of-the-art speech datasets predominantly focus on widely spoken languages, often overlooking low-resource languages such as Luxembourgish, which remain underrepresented in speech technology research. In this work, we introduce LuxEmo, a 21-hour conversational expressive speech corpus for Luxembourgish with 4 emotion categories.
High-throughput plant phenotyping now generates image derived datasets far faster than scientists can analyze them. At Oak Ridge National Laboratory's Advanced Plant Phenotyping Laboratory (APPL), automated stations image hundreds of plants daily across multiple remote sensing modalities; yet, trait extraction and interpretation remain manual, expert-bound, and strictly post-hoc, making analysis, not acquisition, the binding constraint on discovery.
Graph-based cardiac segmentation with implicit anatomical correspondences provides topological guarantees and population-level analysis capabilities, but models trained on independent frames of image sequences exhibit temporal discontinuities that affect reliable clinical measurements, particularly in cardiac ultrasound. In this work, we introduce self-supervised temporal regularization as a post-training refinement stage that exploits the temporal coherence in image sequences to enforce consistent cardiac segmentation and motion estimation over time, without requiring per-frame annotations.
arXiv:2605. 16401v2 Announce Type: replace-cross Abstract: While high-capacity AI models have advanced state-of-the-art performance, their practical deployment is often hindered by high inference costs, environmental impact, and a "one-size-fits-all" approach that ignores varying sample complexity.
arXiv:2606. 29438v1 Announce Type: cross Abstract: In this paper, we develop a fractional stochastic neural network with residual dynamics driven by fractional Brownian motion.
arXiv:2606. 29112v1 Announce Type: new Abstract: Deep learning, which in general relies on voluminous amounts of training data, is vulnerable to data poisoning attacks, including error-generic attacks and backdoors (Trojans).
arXiv:2606. 29020v1 Announce Type: cross Abstract: Weather synthesis aims to add weather effects to input videos while preserving scene identity, structure, and motion.
arXiv:2508. 02425v2 Announce Type: replace-cross Abstract: In physical human-robot collaboration (pHRC) settings, humans and robots collaborate directly in shared environments.