相关论文: DeCoDrift: Stabilizing Decoder Coupling in Closed-…
Autoregressive language models can often identify parallel subproblems, but standard decoding exposes only a single left-to-right output interface. External orchestration methods can launch multiple prompts concurrently, yet they provide no…
\noindent Memory has become the central mechanism enabling robust visual object tracking in modern segmentation-based frameworks. Recent methods built upon Segment Anything Model 2 (SAM2) have demonstrated strong performance by refining how…
The Segment-Anything Model (SAM) is a vision foundation model for segmentation with a prompt-driven framework. SAM generates class-agnostic masks based on user-specified instance-referring prompts. However, adapting SAM for automated…
We present the discriminative recurrent sparse auto-encoder model, comprising a recurrent encoder of rectified linear units, unrolled for a fixed number of iterations, and connected to two linear decoders that reconstruct the input and…
Purpose: Accurate tool segmentation is essential in computer-aided procedures. However, this task conveys challenges due to artifacts' presence and the limited training data in medical scenarios. Methods that generalize to unseen data…
Monocular Depth Estimation (MDE) aims to predict pixel-wise depth given a single RGB image. For both, the convolutional as well as the recent attention-based models, encoder-decoder-based architectures have been found to be useful due to…
We propose MisMatch, a novel consistency-driven semi-supervised segmentation framework which produces predictions that are invariant to learnt feature perturbations. MisMatch consists of an encoder and a two-head decoders. One decoder…
We introduce a comprehensive framework for the detection and demodulation of covert electromagnetic signals using solid-state spin sensors. Our approach, named RAPID, is a two-stage hybrid strategy that leverages nitrogen-vacancy (NV)…
Image deblurring is a critical task in the field of image restoration, aiming to eliminate blurring artifacts. However, the challenge of addressing non-uniform blurring leads to an ill-posed problem, which limits the generalization…
Training-free Camouflaged Object Segmentation (COS) seeks to segment camouflaged objects without task-specific training, by automatically generating visual prompts to guide the Segment Anything Model (SAM). However, existing pipelines…
Recently, pre-trained vision-language models have been increasingly used to tackle the challenging zero-shot segmentation task. Typical solutions follow the paradigm of first generating mask proposals and then adopting CLIP to classify…
Segment Anything Model (SAM) is one of the pioneering prompt-based foundation models for image segmentation and has been rapidly adopted for various medical imaging applications. However, in clinical settings, creating effective prompts is…
Modern control systems frequently operate under input delays and sampled state measurements. A common delay-compensation strategy is predictor feedback; however, practical implementations require solving an implicit ODE online, resulting in…
For sufficiently wide ranges of applied control signals (control voltages), MEMS and piezoelectric Deformable Mirrors (DMs), exhibit nonlinear behavior. The nonlinear behavior manifests itself in nonlinear actuator couplings, nonlinear…
Non-contact radar-based human sensing is often interpreted using simplified motion assumptions. However, respiration induces non-rigid surface deformation of the human body that impacts electromagnetic wave scattering and can degrade the…
We present a new scheme to efficiently establish entanglement between optical modes in a time-multiplexed coherent Ising machine (CIM) by means of nonlocal measurement and feedback. We numerically simulate and evaluate the generation of…
Dynamical decoupling techniques constitute an integral part of many quantum sensing platforms, often leading to orders-of-magnitude improvements in coherence time and sensitivity. Most AC sensing sequences involve a periodic echo-like…
Real-world weather, illumination, and imaging variations often induce severe domain shifts, degrading single-source detectors in unseen environments. Existing single-domain generalized object detection (SDGOD) methods mainly rely on data…
Foundation models (FM) are reshaping computer vision by reducing reliance on task-specific supervised learning and leveraging general visual representations learned at scale. In precision livestock farming, most pipelines remain dominated…
Standard Transformers have a fixed computational depth, fundamentally limiting their ability to generalize to tasks requiring variable-depth reasoning, such as multi-hop graph traversal or nested logic. We propose a depth-recurrent…