arXiv:2603.19139v2 Announce Type: replace Abstract: Learning systems must balance generalization across experiences with discrimination of task-relevant details. Effective learning therefore requires representations that support both. Online…
arXiv:2509.14562v5 Announce Type: replace Abstract: Large models recently are widely applied in machine learning, so efficient training of large models has received widespread attention. More recently,…
arXiv:2501.18530v3 Announce Type: replace-cross Abstract: We consider a teacher-student model of supervised learning with a fully-trained two-layer neural network whose width $k$ and input dimension $d$…
arXiv:2607.13897v3 Announce Type: replace Abstract: The broadcast nature of wireless channels exposes radio-frequency (RF) networks to anomalous and malicious transmissions, making anomaly detection a fundamental requirement…
arXiv:2601.19618v2 Announce Type: replace-cross Abstract: Differential privacy protects the patients whose images train medical imaging models, but it lowers diagnostic accuracy, and the initialization is the…
arXiv:2607.22262v1 Announce Type: cross Abstract: Modeling shared and subject-specific structure in multisubject spatiotemporal data remains challenging, particularly in neuroimaging, where both spatial and temporal patterns exhibit…
arXiv:2607.20368v2 Announce Type: replace Abstract: Recent autoregressive video diffusion methods are increasingly built upon Self Forcing, where the student is trained on histories produced by its…
arXiv:2607.21973v1 Announce Type: new Abstract: Vision foundation models are increasingly reused as frozen backbones for downstream visual recognition, making parameter-efficient adaptation a central problem. Prompt-based adaptation,…
arXiv:2606.10135v4 Announce Type: replace Abstract: Interactive video world models commonly convert bidirectional video generators into causal autoregressive systems through control fine-tuning, autoregressive training, causal initialization, and…
arXiv:2607.21970v1 Announce Type: new Abstract: Automating radiology report generation is important for improving reporting consistency and clinical workflows . While Contrastive Language--Image Pretraining (CLIP) has advanced…
arXiv:2602.21473v3 Announce Type: replace Abstract: A key challenge in translating Visual Place Recognition (VPR) from the lab to long-term deployment is ensuring a priori that a…
arXiv:2607.21953v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) communication is expected to support a wide range of low-altitude applications in 6G mobile networks. However, traditional…
arXiv:2509.10058v2 Announce Type: replace Abstract: Accurate color alignment in text-to-image (T2I) generation is critical for applications such as fashion, product visualization, and interior design, yet current…
arXiv:2607.21904v1 Announce Type: new Abstract: Image inpainting aims to reconstruct missing or corrupted regions of an image while preserving as much as possible, visual and semantic…
arXiv:2411.19715v4 Announce Type: replace Abstract: We describe Forensics Adapter, an adapter network designed to transform CLIP into an effective and generalizable face forgery detector. Although CLIP…
arXiv:2607.21897v1 Announce Type: new Abstract: The rapid advancement of generative models has spurred the critical need to evaluate the worst-case robustness of deepfake detectors. In this…
arXiv:2607.22393v1 Announce Type: cross Abstract: Vision-language model (VLM) agents increasingly use tools to act on 3D scenes rather than only describe them. Existing 3D benchmarks score…
arXiv:2607.21787v1 Announce Type: new Abstract: Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisition variation across operators…
arXiv:2607.21792v1 Announce Type: new Abstract: One-to-many facial identification is commonly used to match a probe image from surveillance video against a gallery of driver's licenses and/or…
arXiv:2607.21840v1 Announce Type: new Abstract: Learning high-fidelity point-cloud features in the 3D space poses significant challenges, including permutation invariance, lack of local context, difficulty in fine-grained…
arXiv:2607.21850v1 Announce Type: new Abstract: As semiconductor manufacturing advances toward sub-2nm nodes, local place-and-route (P&R) design-rule violation (DRV) fixing is increasingly limited by complex rule interactions,…
arXiv:2607.21848v1 Announce Type: new Abstract: Recent conditional video generation models have shown promising potentials to transform 3D engine renderings, such as depth maps and untextured geometry,…
arXiv:2607.21896v1 Announce Type: new Abstract: Semantic 3D Gaussians provide a compact representation for 3D semantic occupancy prediction by rendering semantic primitives into a voxel volume under…
arXiv:2607.21881v1 Announce Type: new Abstract: Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and…