Related papers: Orthogonal Quadratic Complements for Vision Transf…
Recent feed-forward networks have achieved remarkable progress in sparse-view 3D reconstruction by predicting dense point maps directly from RGB images. However, they often suffer from geometric inconsistencies and limited fine-grained…
We introduce Steerable Transformers, an extension of the Vision Transformer mechanism that maintains equivariance to the special Euclidean group $\mathrm{SE}(d)$. We propose an equivariant attention mechanism that operates on features…
We review recent advances in the capabilities of the open source ab initio Quantum Monte Carlo (QMC) package QMCPACK and the workflow tool Nexus used for greater efficiency and reproducibility. The auxiliary field QMC (AFQMC) implementation…
Occupancy prediction has garnered increasing attention in recent years for its comprehensive fine-grained environmental representation and strong generalization to open-set objects. However, cumbersome voxel features and 3D convolution…
Multimodal medical imaging provides complementary information that is crucial for accurate delineation of pathology, but the development of deep learning models is limited by the scarcity of large datasets in which different modalities are…
Large optical coherent-state superpositions are essential to advance quantum sensing, quantum repeaters and error-correction codes. We propose a deterministic feedforward protocol employing qubit-mode dispersive coupling, currently…
Audio-visual speech enhancement system is regarded to be one of promising solutions for isolating and enhancing speech of desired speaker. Conventional methods focus on predicting clean speech spectrum via a naive convolution neural network…
In this work, we aim to learn an unpaired image enhancement model, which can enrich low-quality images with the characteristics of high-quality images provided by users. We propose a quality attention generative adversarial network (QAGAN)…
As a randomized learner model, SCNs are remarkable that the random weights and biases are assigned employing a supervisory mechanism to ensure universal approximation and fast learning. However, the randomness makes SCNs more likely to…
The development of orbital angular momentum (OAM)-based radio vortex transmission presents a promising opportunity for increasing the capacity of wireless communication in correlated channels due to its inherent orthogonality among…
We propose an adaptation to the training of Vision Transformers (ViTs) that allows for an explicit modeling of objects during the attention computation. This is achieved by adding a new branch to selected attention layers that computes an…
Filter bank multi-carrier with offset quadrature amplitude modulation (FBMC/OQAM) has been heavily studied as an alternative waveform for 5G systems. Its advantages of higher spectrum efficiency, localized frequency response and…
Optical Coherence Tomography (OCT) was originally conceived as a volumetric imaging method. Quickly, OCT images went beyond structural data and started to provide functional information about an object enabling for example visualization of…
Deep learning models for channel estimation in Orthogonal Frequency Division Multiplexing (OFDM) systems often suffer from performance degradation under fast-fading channels and low-SNR scenarios. To address these limitations, we introduce…
AI-driven crop health mapping systems offer substantial advantages over conventional monitoring approaches through accelerated data acquisition and cost reduction. However, widespread farmer adoption remains constrained by technical…
Scaling full finetuning of large foundation models strains GPU memory and training time. Parameter Efficient Fine-Tuning (PEFT) methods address this issue via adapter modules which update only a small subset of model parameters. In this…
Quantum Optical Coherence Tomography (Q-OCT) is the non-classical counterpart of Optical Coherence Tomography (OCT) - a high-resolution 3D imaging technique based on white-light interferometry. Because Q-OCT uses a source of…
In this study, we introduce a method for learning group (known or unknown) equivariant functions by learning the associated quadratic form $x^T A x$ corresponding to the group from the data. Certain groups, known as orthogonal groups,…
Bayesian inference, while foundational to probabilistic reasoning, is often hampered by the computational intractability of posterior distributions, particularly through the challenging evidence integral. Conventional approaches like Markov…
Conventional computer vision models rely on very deep, feedforward networks processing whole images and trained offline with extensive labeled data. In contrast, biological vision relies on comparatively shallow, recurrent networks that…