Tootfinder

Distance-informed Neural Processes
Aishwarya Venkataramanan, Joachim Denzler
https://arxiv.org/abs/2508.18903 https://arxiv.org/pdf/2508.18903

Distance-informed Neural Processes
We propose the Distance-informed Neural Process (DNP), a novel variant of Neural Processes that improves uncertainty estimation by combining global and distance-aware local latent structures. Standard Neural Processes (NPs) often rely on a global latent variable and struggle with uncertainty calibration and capturing local data dependencies. DNP addresses these limitations by introducing a global latent variable to model task-level variations and a local latent variable to capture input similar…

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
Junjie Li, Jing Peng, Yangui Fang, Shuai Wang, Kai Yu
https://arxiv.org/abs/2508.18998

MOSA: Mixtures of Simple Adapters Outperform Monolithic Approaches in LLM-based Multilingual ASR
End-to-end multilingual ASR aims to transcribe speech from different languages into corresponding text, but is often limited by scarce multilingual data. LLM-based ASR aligns speech encoder outputs with LLM input space via a projector and has achieved notable success. However, prior work mainly improves performance by increasing data, with little focus on cross-lingual knowledge sharing. Moreover, a single complex projector struggles to capture both shared and language-specific features effecti…

Quantum-Assisted Learning of Time-Dependent Parabolic PDEs
Nahid Binandeh Dehaghani, Ban Tran, A. Pedro Aguiar, Rafal Wisniewski, Susan Mengel
https://arxiv.org/abs/2508.17553 h…

Quantum-Assisted Learning of Time-Dependent Parabolic PDEs
We present a hybrid quantum-classical framework for solving general time-dependent parabolic partial differential equations (PDEs) using quantum variational circuits. Building on the QPINN approach, this method applies broadly to parabolic PDEs. To demonstrate its effectiveness, we focus on the 1D and 2D heat equations as representative examples and analyze its performance under constrained quantum resources. Our results show that the framework can accurately capture spatiotemporal dynamics, of…

Real-space second Chern number using the kernel polynomial method
Rui Chen, Bin Zhou
https://arxiv.org/abs/2507.18919 https://arxiv.org/pdf/2507.18919

Real-space second Chern number using the kernel polynomial method
We evaluate the real-space second Chern number of four-dimensional Chern insulators using the kernel polynomial method. Our calculations are performed on a four-dimensional system with $30^4$ sites, and the numerical results agree well with theoretical expectations. Moreover, we show that the method is capable of capturing the disorder effects. This is evidenced by the phase diagram obtained for disordered systems, which agrees well with predictions from the self-consistent Born approximation. …

BoSS: Beyond-Semantic Speech
Qing Wang, Zehan Li, Hang Lv, Hongjie Chen, Yaodong Song, Jian Kang, Jie Lian, Jie Li, Yongxiang Li, Zhongjiang He, Xuelong Li
https://arxiv.org/abs/2507.17563

BoSS: Beyond-Semantic Speech
Human communication involves more than explicit semantics, with implicit signals and contextual cues playing a critical role in shaping meaning. However, modern speech technologies, such as Automatic Speech Recognition (ASR) and Text-to-Speech (TTS) often fail to capture these beyond-semantic dimensions. To better characterize and benchmark the progression of speech intelligence, we introduce Spoken Interaction System Capability Levels (L1-L5), a hierarchical framework illustrated the evolution…

A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
Tolga \c{C}ukur, Salman U. H. Dar, Valiyeh Ansarian Nezhad, Yohan Jun, Tae Hyung Kim, Shohei Fujita, Berkin Bilgic
https://arxiv.org/abs/2507.16715

A Tutorial on MRI Reconstruction: From Modern Methods to Clinical Implications
MRI is an indispensable clinical tool, offering a rich variety of tissue contrasts to support broad diagnostic and research applications. Clinical exams routinely acquire multiple structural sequences that provide complementary information for differential diagnosis, while research protocols often incorporate advanced functional, diffusion, spectroscopic, and relaxometry sequences to capture multidimensional insights into tissue structure and composition. However, these capabilities come at the…

Multiple crossover in the decay of metastable volume fraction of a Blume-Capel ferromagnetic needle
Ishita Tikader, Muktish Acharyya
https://arxiv.org/abs/2508.15219 https://

Multiple crossover in the decay of metastable volume fraction of a Blume-Capel ferromagnetic needle
The transient behaviours of a Blume-Capel ferromagnetic needle have been studied extensively by Monte-Carlo simulation. The needle has an elongated length in one direction compared to its cross-section. In the context of transient behaviour, we have captured the decay of the metastable state and the magnetic relaxation behaviours in our study. The dependence of metastable behaviour with anisotropy (single site) has been studied. \emph{Interestingly, we have observed multiple (different values o…

OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos
Miao Zhang, Yifei Zhu, Linfeng Shen, Fangxin Wang, Jiangchuan Liu
https://arxiv.org/abs/2508.14237 https:…

OmniSense: Towards Edge-Assisted Online Analytics for 360-Degree Videos
With the reduced hardware costs of omnidirectional cameras and the proliferation of various extended reality applications, more and more $360^\circ$ videos are being captured. To fully unleash their potential, advanced video analytics is expected to extract actionable insights and situational knowledge without blind spots from the videos. In this paper, we present OmniSense, a novel edge-assisted framework for online immersive video analytics. OmniSense achieves both low latency and high accura…

LeanExplore: A search engine for Lean 4 declarations
Justin Asher (Independent Researcher)
https://arxiv.org/abs/2506.11085 https://a…

LeanExplore: A search engine for Lean 4 declarations
The expanding Lean 4 ecosystem poses challenges for navigating its vast libraries. This paper introduces LeanExplore, a search engine for Lean 4 declarations. LeanExplore enables users to semantically search for statements, both formally and informally, across select Lean 4 packages (including Batteries, Init, Lean, Mathlib, PhysLean, and Std). This search capability is powered by a hybrid ranking strategy, integrating scores from a multi-source semantic embedding model (capturing conceptual me…

Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte, Chikao Tsuchiya, Dhaval Bhanderi
https://arxiv.org/abs/2506.10317

Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving
Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this information often follows conventions encoded in natural language, through design codes that reflect the road structure and road names that capture the road functionality. We augment this information in a lightweight manner to SMERF, a map-prior-based online lane-topology prediction model, by combining structured road…