Related papers: Depth Registers Unlock W4A4 on SwiGLU: A Reader/Ge…

Reasoning-enabled LLMs perform strongly on medical reasoning benchmarks, but it remains unclear whether these gains transfer to structured clinical documentation; we investigate this question using SOAP note generation from clinical…

In this paper, we test the performance of templates in detection and characterization of Spin-orbit resonant (SOR) binaries. We use precessing SEOBNRv3 waveforms as well as {\it four} numerical relativity (NR) waveforms to model GWs from…

Whole-slide images (WSIs) are critical for cancer diagnosis due to their ultra-high resolution and rich semantic content. However, their massive size and the limited availability of fine-grained annotations pose substantial challenges for…

Quantum computers promise tremendous impact across applications -- and have shown great strides in hardware engineering -- but remain notoriously error prone. Careful design of low-level controls has been shown to compensate for the…

Quantum processors are often affected by biased noise and noisy readout, which reduce reliability and reproducibility. This work combines two complementary strategies to address these challenges. The first is bias tailoring, which aligns…

We examine models for the magneto-conductivity correction in 2DEGs with both Rashba and Dresselhaus spin-orbit coupling (SOC) for their applicability to experimental data fitting. In particular, we compare the Landau-quantized Cooperon…

Self-attention scales quadratically with sequence length, limiting transformer-based speech models on edge devices. We introduce the Learnable Pulse Accumulator (LPA), an O(n) replacement that substitutes key-query dot products with learned…

To bring Spin Wave (SW) based computing paradigm into practice and develop ultra low power Magnonic circuits and computation platforms, one needs basic logic gates that operate and can be cascaded within the SW domain without requiring back…

Gating mechanisms have been widely utilized, from early models like LSTMs and Highway Networks to recent state space models, linear attention, and also softmax attention. Yet, existing literature rarely examines the specific effects of…

Sparse vision transformers have gained popularity as efficient encoders for medical volumetric segmentation, with Swin emerging as a prominent choice. Swin uses local attention to reduce complexity and yields excellent performance for many…

Context: Deep learning has achieved remarkable progress in various domains. However, like any software system, deep learning systems contain bugs, some of which can have severe impacts, as evidenced by crashes involving autonomous vehicles.…

WaveNet is a state-of-the-art text-to-speech vocoder that remains challenging to deploy due to its autoregressive loop. In this work we focus on ways to accelerate the original WaveNet architecture directly, as opposed to modifying the…

The purpose of this work is to implement physics-based regularization as a stopping condition in tuning an untrained deep neural network for reconstructing MR images from accelerated data. The ConvDecoder neural network was trained with a…

Among the flourishing research of weakly supervised learning (WSL), we recognize the lack of a unified interpretation of the mechanism behind the weakly supervised scenarios, let alone a systematic treatment of the risk rewrite problem, a…

Generative flow models offer powerful priors learned from large-scale natural images, but directly adapting them to restoration tasks such as motion deblurring causes severe fidelity degradation, as their training objective is inherently…

Robust maritime obstacle detection is critical for safe navigation of autonomous boats and timely collision avoidance. The current state-of-the-art is based on deep segmentation networks trained on large datasets. However, per-pixel ground…

Deep machine learning methods have been studied for the software trigger of the future PANDA experiment at FAIR, using Monte Carlo simulated data from the GEANT-based detector simulation framework PandaRoot. Ten physics channels that cover…

Information seeking demands iterative evidence gathering and reflective reasoning, yet large language models (LLMs) still struggle with it in open-web question answering. Existing prompting and supervised fine-tuning (SFT) methods remain…

We introduce Gated-SwinRMT, a family of hybrid vision transformers that combine the shifted-window attention of the Swin Transformer with the Manhattan-distance spatial decay of Retentive Networks (RMT), augmented by input-dependent gating.…

We report an approach to achieve deeply sub-diffractive mode volumes in all-dielectric ring resonators. Specifically, we leverage simultaneous usage of nanostructured subwavelength metamaterial waveguides and excitation of standing wave…