Tootfinder

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
Yuhao Wang, Wei Xi
https://arxiv.org/abs/2508.09000

UniConvNet: Expanding Effective Receptive Field while Maintaining Asymptotically Gaussian Distribution for ConvNets of Any Scale
Convolutional neural networks (ConvNets) with large effective receptive field (ERF), still in their early stages, have demonstrated promising effectiveness while constrained by high parameters and FLOPs costs and disrupted asymptotically Gaussian distribution (AGD) of ERF. This paper proposes an alternative paradigm: rather than merely employing extremely large ERF, it is more effective and efficient to expand the ERF while maintaining AGD of ERF by proper combination of smaller kernels, such a…

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
Jianuo Huang, Yaojie Zhang, Yicun Yang, Benhao Huang, Biqing Qi, Dongrui Liu, Linfeng Zhang
https://arxiv.org/abs/2510.09309

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
Diffusion large language models (dLLMs) present a promising alternative to dominant autoregressive models (ARMs) by the ability of parallel decoding at the expense of substantial computation and memory costs. Specifically, the cache mechanism for bidirectional attention in dLLMs demands large memory footprint, restricting their ability to handle long contexts under resource-limited settings. Existing cache eviction strategies are designed for ARMs and ignore the unique characteristics of dLLMs,…

Unified Framework for Hybrid Aleatory and Epistemic Uncertainty Propagation via Decoupled Multi-Probability Density Evolution Method
Yi Luo, Meng-Ze Lyu, Matteo Broggi, Marko Thiele, Vasileios C. Fragkoulis, Michael Beer
https://arxiv.org/abs/2509.09535

Unified Framework for Hybrid Aleatory and Epistemic Uncertainty Propagation via Decoupled Multi-Probability Density Evolution Method
This paper presents a unified framework for uncertainty propagation in dynamical systems involving hybrid aleatory and epistemic uncertainties. The framework accommodates precise probabilistic, imprecise probabilistic, and non-probabilistic representations, including the distribution-free probability-box (p-box). A central aspect of the framework involves transforming the original uncertainty inputs into an augmented random space, yielding the primary challenge of determining the conditional pr…

Nonlinear Symmetry Breaking to Enhance the Sagnac Effect in a Microresonator Gyroscope
Thariq Shanavas, Gregory Krueper, Jiangang Zhu, Wounjhang Park, Juliet T. Gopinath
https://arxiv.org/abs/2508.09132

Nonlinear Symmetry Breaking to Enhance the Sagnac Effect in a Microresonator Gyroscope
Optical gyroscopes based on the Sagnac effect have been widely used for inertial navigation in aircrafts, submarines, satellites and unmanned robotics. With the rapid progress in the field of ultrahigh-quality whispering gallery mode and ring resonators in recent years, these devices offer the promise of a compact alternative to ring-laser gyroscopes (RLGs) and fiber-optic gyroscopes (FOGs). Yet, successful commercialization of a microresonator gyroscope has been hindered by the scaling of the …

Uncertainty Estimation using Variance-Gated Distributions
H. Martin Gillis, Isaac Xu, Thomas Trappenberg
https://arxiv.org/abs/2509.08846 https://arxiv.org…

Uncertainty Estimation using Variance-Gated Distributions
Evaluation of per-sample uncertainty quantification from neural networks is essential for decision-making involving high-risk applications. A common approach is to use the predictive distribution from Bayesian or approximation models and decompose the corresponding predictive uncertainty into epistemic (model-related) and aleatoric (data-related) components. However, additive decomposition has recently been questioned. In this work, we propose an intuitive framework for uncertainty estimation a…

Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models
Qiguang Chen, Hanjing Li, Libo Qin, Dengyun Peng, Jinhao Liu, Jiangyi Wang, Chengyue Wu, Xie Chen, Yantao Du, Wanxiang Che
https://arxiv.org/abs/2510.09544

Beyond Surface Reasoning: Unveiling the True Long Chain-of-Thought Capacity of Diffusion Large Language Models
Recently, Diffusion Large Language Models (DLLMs) have offered high throughput and effective sequential reasoning, making them a competitive alternative to autoregressive LLMs (ALLMs). However, parallel decoding, which enables simultaneous token updates, conflicts with the causal order often required for rigorous reasoning. We first identify this conflict as the core Parallel-Sequential Contradiction (PSC). Behavioral analyses in both simple and complex reasoning tasks show that DLLMs exhibit g…

Nonlinear opto-magnetic signuature of d-wave altermagnets
Lijun Yang, Long Liang
https://arxiv.org/abs/2509.08254 https://arxiv.org/pdf/2509.08254

Nonlinear opto-magnetic signuature of d-wave altermagnets
Altermagnetism, a recently discovered collinear magnetic order with net zero magnetization but exhibits spin-splitting band structure, has attracted much research interest due to the rich fundamental physics and possible applications. In this work, we investigate the opto-magnetic response of $d$-wave altermagnets, focusing on the inverse Cotton-Mouton effect--the induction of static magnetization via linearly polarized light. We find that the direction of the induced magnetization is determine…

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Yansong Wang, Qihui Lin, Junjie Huang, Tao Jia
https://arxiv.org/abs/2510.09129 https://

Generative Data Augmentation in Graph Contrastive Learning for Recommendation
Recommendation systems have become indispensable in various online platforms, from e-commerce to streaming services. A fundamental challenge in this domain is learning effective embeddings from sparse user-item interactions. While contrastive learning has recently emerged as a promising solution to this issue, generating augmented views for contrastive learning through most existing random data augmentation methods often leads to the alteration of original semantic information. In this paper, w…

Sliding-tuned Quantum Geometry in Moir\'e Systems: Nonlinear Hall Effect and Quantum Metric Control
Shi-Ping Ding, Miao Liang, Tian-Le Wu, Meng-Hao Wu, Jing-Tao L\"u, Jin-Hua Gao, X. C. Xie
https://arxiv.org/abs/2509.09077

Sliding-tuned Quantum Geometry in Moiré Systems: Nonlinear Hall Effect and Quantum Metric Control
Sliding is a ubiquitous phenomenon in moiré systems, but its direct influence on moiré bands, especially in multi-twist moiré systems, has been largely overlooked to date. Here, we theoretically show that sliding provides a unique pathway to engineer the quantum geometry (Berry curvature and quantum metric) of moiré bands, exhibiting distinct advantages over conventional strategies. Specifically, we first suggest alternating twisted trilayer $\mathrm{MoTe_2}$ (AT3L-$\mathrm{MoTe_2}$) and ch…

Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
Dimitrios Anastasiou, Razvan Caramalau, Nazir Sirajudeen, Matthew Boal, Philip Edwards, Justin Collins, John Kelly, Ashwin Sridhar, Maxine Tran, Faiz Mumtaz, Nevil Pavithran, Nader Francis, Danail Stoyanov, Evangelos B. Mazomenos
https://arxiv.org/abs/2509.09327…

Exploring Pre-training Across Domains for Few-Shot Surgical Skill Assessment
Automated surgical skill assessment (SSA) is a central task in surgical computer vision. Developing robust SSA models is challenging due to the scarcity of skill annotations, which are time-consuming to produce and require expert consensus. Few-shot learning (FSL) offers a scalable alternative enabling model development with minimal supervision, though its success critically depends on effective pre-training. While widely studied for several surgical downstream tasks, pre-training has remained …