arXiv:2603.10541v1 Announce Type: cross Abstract: Promptable Foundation Models (FMs), initially introduced for natural image segmentation, have also revolutionized medical image segmentation. The increasing number of models, along with evaluations varying in datasets, metrics, and compared models, makes direct performance comparison between models difficult and complicates the selection of the most suitable model for specific clinical […]
Gradient Flow Drifting: Generative Modeling via Wasserstein Gradient Flows of KDE-Approximated Divergences
arXiv:2603.10592v1 Announce Type: cross Abstract: We reveal a precise mathematical framework about a new family of generative models which we call Gradient Flow Drifting. With this framework, we prove an equivalence between the recently proposed Drifting Model and the Wasserstein gradient flow of the forward KL divergence under kernel density estimation (KDE) approximation. Specifically, we […]
Lost in the Middle at Birth: An Exact Theory of Transformer Position Bias
arXiv:2603.10123v1 Announce Type: cross Abstract: The “Lost in the Middle” phenomenon — a U-shaped performance curve where LLMs retrieve well from the beginning and end of a context but fail in the middle — is widely attributed to learned Softmax artifacts or the distance-decay of positional encodings like RoPE. This paper makes a single, precise […]
PatchDenoiser: Parameter-efficient multi-scale patch learning and fusion denoiser for Low-dose CT imaging
arXiv:2602.21987v2 Announce Type: replace-cross Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but their quality is often degraded by noise from low-dose acquisition, patient motion, or scanner limitations, affecting both clinical interpretation and downstream analysis. Traditional filtering approaches often over-smooth and lose fine anatomical […]
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
arXiv:2603.10156v1 Announce Type: cross Abstract: Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on open-source platforms. However, these training artifacts are rarely reused for subsequent experiments despite containing […]
Towards Cognitive Defect Analysis in Active Infrared Thermography with Vision-Text Cues
arXiv:2603.10549v1 Announce Type: cross Abstract: Active infrared thermography (AIRT) is currently witnessing a surge of artificial intelligence (AI) methodologies being deployed for automated subsurface defect analysis of high performance carbon fiber-reinforced polymers (CFRP). Deploying AI-based AIRT methodologies for inspecting CFRPs requires the creation of time consuming and expensive datasets of CFRP inspection sequences to train […]
Delta-K: Boosting Multi-Instance Generation via Cross-Attention Augmentation
arXiv:2603.10210v1 Announce Type: cross Abstract: While Diffusion Models excel in text-to-image synthesis, they often suffer from concept omission when synthesizing complex multi-instance scenes. Existing training-free methods attempt to resolve this by rescaling attention maps, which merely exacerbates unstructured noise without establishing coherent semantic representations. To address this, we propose Delta-K, a backbone-agnostic and plug-and-play inference […]
Conformal Tradeoffs: Operational Profiles Beyond Coverage
arXiv:2602.18045v3 Announce Type: replace-cross Abstract: Conformal prediction gives exact finite-sample coverage guarantees under exchangeability, but deployed systems are judged by more than coverage alone. For a fixed calibrated rule reused over a finite operational window, stakeholders also care about deployment-facing quantities such as commitment frequency, deferral, and decisive error exposure. These are not determined by […]
SCORE: Replacing Layer Stacking with Contractive Recurrent Depth
arXiv:2603.10544v1 Announce Type: cross Abstract: Residual connections are central to modern deep neural networks, enabling stable optimization and efficient information flow across depth. In this work, we propose SCORE (Skip-Connection ODE Recurrent Embedding), a discrete recurrent alternative to classical layer stacking. Instead of composing multiple independent layers, SCORE iteratively applies a single shared neural block […]
Joint Imaging-ROI Representation Learning via Cross-View Contrastive Alignment for Brain Disorder Classification
arXiv:2603.10253v1 Announce Type: cross Abstract: Brain imaging classification is commonly approached from two perspectives: modeling the full image volume to capture global anatomical context, or constructing ROI-based graphs to encode localized and topological interactions. Although both representations have demonstrated independent efficacy, their relative contributions and potential complementarity remain insufficiently understood. Existing fusion approaches are typically […]
SEED-SET: Scalable Evolving Experimental Design for System-level Ethical Testing
arXiv:2603.01630v2 Announce Type: replace Abstract: As autonomous systems such as drones, become increasingly deployed in high-stakes, human-centric domains, it is critical to evaluate the ethical alignment since failure to do so imposes imminent danger to human lives, and long term bias in decision-making. Automated ethical benchmarking of these systems is understudied due to the lack […]
Quantum entanglement provides a competitive advantage in adversarial games
arXiv:2603.10289v1 Announce Type: cross Abstract: Whether uniquely quantum resources confer advantages in fully classical, competitive environments remains an open question. Competitive zero-sum reinforcement learning is particularly challenging, as success requires modelling dynamic interactions between opposing agents rather than static state-action mappings. Here, we conduct a controlled study isolating the role of quantum entanglement in a […]