Tootfinder

Exploiting ID-Text Complementarity via Ensembling for Sequential Recommendation
Liam Collins, Bhuvesh Kumar, Clark Mingxuan Ju, Tong Zhao, Donald Loveland, Leonardo Neves, Neil Shah
https://arxiv.org/abs/2512.17820 https://arxiv.org/pdf/2512.17820 https://arxiv.org/html/2512.17820
arXiv:2512.17820v1 Announce Type: new
Abstract: Modern Sequential Recommendation (SR) models commonly utilize modality features to represent items, motivated in large part by recent advancements in language and vision modeling. To do so, several works completely replace ID embeddings with modality embeddings, claiming that modality embeddings render ID embeddings unnecessary because they can match or even exceed ID embedding performance. On the other hand, many works jointly utilize ID and modality features, but posit that complex fusion strategies, such as multi-stage training and/or intricate alignment architectures, are necessary for this joint utilization. However, underlying both these lines of work is a lack of understanding of the complementarity of ID and modality features. In this work, we address this gap by studying the complementarity of ID- and text-based SR models. We show that these models do learn complementary signals, meaning that either should provide performance gain when used properly alongside the other. Motivated by this, we propose a new SR method that preserves ID-text complementarity through independent model training, then harnesses it through a simple ensembling strategy. Despite this method's simplicity, we show it outperforms several competitive SR baselines, implying that both ID and text features are necessary to achieve state-of-the-art SR performance but complex fusion architectures are not.
toXiv_bot_toot

An algebra modality admitting countably many deriving transformations
Jean-Baptiste Vienney
https://arxiv.org/abs/2510.03953 https://arxiv.org/pdf/2510.039…

An algebra modality admitting countably many deriving transformations
A differential category is an additive symmetric monoidal category, that is, a symmetric monoidal category enriched over commutative monoids, with an algebra modality, axiomatizing smooth functions, and a deriving transformation on this algebra modality, axiomatizing differentiation. Lemay proved that a comonoidal algebra modality has at most one deriving transformation, thus differentiation is unique in models of differential linear logic. It was then an open problem whether this result extend…

Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation
Chengpeng Hu, Calvin Yu-Chian Chen
https://arxiv.org/abs/2510.12498

Artificial Intelligence Virtual Cells: From Measurements to Decisions across Modality, Scale, Dynamics, and Evaluation
Artificial Intelligence Virtual Cells (AIVCs) aim to learn executable, decision-relevant models of cell state from multimodal, multiscale measurements. Recent studies have introduced single-cell and spatial foundation models, improved cross-modality alignment, scaled perturbation atlases, and explored pathway-level readouts. Nevertheless, although held-out validation is standard practice, evaluations remain predominantly within single datasets and settings; evidence indicates that transport acr…

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
Bajian Xiang, Shuaijiang Zhao, Tingwei Guo, Wei Zou
https://arxiv.org/abs/2510.12116

Understanding the Modality Gap: An Empirical Study on the Speech-Text Alignment Mechanism of Large Speech Language Models
End-to-end Large Speech Language Models (LSLMs) have demonstrated impressive conversational generation abilities, yet consistently fall short of traditional pipeline systems on semantic understanding benchmarks. In this work, we reveal through systematic experimentation that although LSLMs lose some text input performance after speech-text alignment training, the performance gap between speech and text inputs is more pronounced, which we refer to as the modality gap. To understand this gap, we …

Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
KiHyun Nam, Jongmin Choi, Hyeongkeun Lee, Jungwoo Heo, Joon Son Chung
https://arxiv.org/abs/2510.11330

Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap
Contrastive audio-language pretraining yields powerful joint representations, yet a persistent audio-text modality gap limits the benefits of coupling multimodal encoders with large language models (LLMs). We present Diffusion-Link, a diffusion-based modality-bridging module that generatively maps audio embeddings into the text-embedding distribution. The module is trained at the output embedding from the frozen multimodal encoder and implemented as a lightweight network with three residual MLP…

(PDF, PhD thesis 2018) Improving visual-to-auditory cross-modality information conversions https://eprints.nottingham.ac.uk/55721/ by Shern Shiou Tan, on visual-to-auditory sensory substitution (VASS) devices.
"The integration of visual recognition in parallel with the soundscape will be the…

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis
Feng Yuan, Yifan Gao, Yuehua Ye, Haoyue Li, Xin Gao
https://arxiv.org/abs/2510.02815 https://

Med-K2N: Flexible K-to-N Modality Translation for Medical Image Synthesis
Cross-modal medical image synthesis research focuses on reconstructing missing imaging modalities from available ones to support clinical diagnosis. Driven by clinical necessities for flexible modality reconstruction, we explore K to N medical generation, where three critical challenges emerge: How can we model the heterogeneous contributions of different modalities to various target tasks? How can we ensure fusion quality control to prevent degradation from noisy information? How can we mainta…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Donglin Zhou, Weike Pan, Zhong Ming
https://arxiv.org/abs/2510.10556 htt…

Self-Supervised Representation Learning with ID-Content Modality Alignment for Sequential Recommendation
Sequential recommendation (SR) models often capture user preferences based on the historically interacted item IDs, which usually obtain sub-optimal performance when the interaction history is limited. Content-based sequential recommendation has recently emerged as a promising direction that exploits items' textual and visual features to enhance preference learning. However, there are still three key challenges: (i) how to reduce the semantic gap between different content modality representatio…

A 3D Generation Framework from Cross Modality to Parameterized Primitive
Yiming Liang, Huan Yu, Zili Wang, Shuyou Zhang, Guodong Yi, Jin Wang, Jianrong Tan
https://arxiv.org/abs/2510.08656

A 3D Generation Framework from Cross Modality to Parameterized Primitive
Recent advancements in AI-driven 3D model generation have leveraged cross modality, yet generating models with smooth surfaces and minimizing storage overhead remain challenges. This paper introduces a novel multi-stage framework for generating 3D models composed of parameterized primitives, guided by textual and image inputs. In the framework, A model generation algorithm based on parameterized primitives, is proposed, which can identifies the shape features of the model constituent elements, …

Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration
Tengwei Song, Min Wu, Yuan Fang
https://arxiv.org/abs/2510.07035 https:/…

Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Integration
Molecular representation learning plays a crucial role in advancing applications such as drug discovery and material design. Existing work leverages 2D and 3D modalities of molecular information for pre-training, aiming to capture comprehensive structural and geometric insights. However, these methods require paired 2D and 3D molecular data to train the model effectively and prevent it from collapsing into a single modality, posing limitations in scenarios where a certain modality is unavailabl…

Tjurina Number Jumps and Unimodal Hypersurface Singularities in Positive Characteristic
Hongrui Ma, Aoyu Ying, Huaiqing Zuo
https://arxiv.org/abs/2510.02619 https://

Tjurina Number Jumps and Unimodal Hypersurface Singularities in Positive Characteristic
This paper generalizes existing methods to derive stronger bounds on the modality of hypersurface singularities. Our results demonstrate that each sudden jump in the Tjurina number necessarily increases the modality. Furthermore, we provide a full classification of unimodal isolated hypersurface singularities in characteristic p > 3 under contact equivalence. Keywords. isolated singularity, classification, modality, positive characteristic.

Towards Robust and Realible Multimodal Fake News Detection with Incomplete Modality
Hengyang Zhou, Yiwei Wei, Jian Yang, Zhenyu Zhang
https://arxiv.org/abs/2510.05839 https://…

Towards Robust and Realible Multimodal Fake News Detection with Incomplete Modality
Multimodal fake news detection (MFND) has become an urgent task with the emergence of huge multimodal fake content on social media platforms. Previous studies mainly focus on complex feature extraction and fusion to learn discriminative information from multimodal content. However, in real-world applications, multimedia news may naturally lose some information during dissemination, resulting in modality incompleteness, which is detrimental to the generalization and robustness of existing models…

nnSAM2: nnUNet-Enhanced One-Prompt SAM2 for Few-shot Multi-Modality Segmentation and Composition Analysis of Lumbar Paraspinal Muscles
Zhongyi Zhang, Julie A. Hides, Enrico De Martino, Abdul Joseph Fofanah, Gervase Tuxworth
https://arxiv.org/abs/2510.05555

nnSAM2: nnUNet-Enhanced One-Prompt SAM2 for Few-shot Multi-Modality Segmentation and Composition Analysis of Lumbar Paraspinal Muscles
Purpose: To develop and validate No-New SAM2 (nnsam2) for few-shot segmentation of lumbar paraspinal muscles using only a single annotated slice per dataset, and to assess its statistical comparability with expert measurements across multi-sequence MRI and multi-protocol CT. Methods: We retrospectively analyzed 1,219 scans (19,439 slices) from 762 participants across six datasets. Six slices (one per dataset) served as labeled examples, while the remaining 19,433 slices were used for testing.…

Multi-modal Foundation Model for Cosmological Simulation Data
Bin Xia, Nesar Ramachandra, Azton I. Wells, Salman Habib, John Wise
https://arxiv.org/abs/2510.07684 https://

Multi-modal Foundation Model for Cosmological Simulation Data
We present a multi-modal foundation model for astrophysical galaxy data, designed to map between simulation- and observation-based galactic features. Our encoder-only transformer flexibly ingests scalar quantities (e.g., redshifts, galaxy masses) and vectors (e.g., star formation histories, spectra), supporting multi-task training that includes within-modality reconstruction and cross-modality prediction. With a dynamic masking strategy, the model can query arbitrary galaxy properties from part…

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
Kaisi Guan, Xihua Wang, Zhengfeng Lai, Xin Cheng, Peng Zhang, XiaoJiang Liu, Ruihua Song, Meng Cao
https://arxiv.org/abs/2510.03117

Taming Text-to-Sounding Video Generation via Advanced Modality Condition and Interaction
This study focuses on a challenging yet promising task, Text-to-Sounding-Video (T2SV) generation, which aims to generate a video with synchronized audio from text conditions, meanwhile ensuring both modalities are aligned with text. Despite progress in joint audio-video training, two critical challenges still remain unaddressed: (1) a single, shared text caption where the text for video is equal to the text for audio often creates modal interference, confusing the pretrained backbones, and (2) …

Imperceptible Jailbreaking against Large Language Models
Kuofeng Gao, Yiming Li, Chao Du, Xin Wang, Xingjun Ma, Shu-Tao Xia, Tianyu Pang
https://arxiv.org/abs/2510.05025 https:/…

Imperceptible Jailbreaking against Large Language Models
Jailbreaking attacks on the vision modality typically rely on imperceptible adversarial perturbations, whereas attacks on the textual modality are generally assumed to require visible modifications (e.g., non-semantic suffixes). In this paper, we introduce imperceptible jailbreaks that exploit a class of Unicode characters called variation selectors. By appending invisible variation selectors to malicious questions, the jailbreak prompts appear visually identical to original malicious questions…

Exploring the Feasibility of Gaze-Based Navigation Across Path Types
Yichuan Zhang, Liangyuting Zhang, Xuning Hu, Yong Yue, Hai-Ning Liang
https://arxiv.org/abs/2510.07184 https…

Exploring the Feasibility of Gaze-Based Navigation Across Path Types
Gaze input, as a modality inherently conveying user intent, offers intuitive and immersive experiences in extended reality (XR). With eye-tracking now being a standard feature in modern XR headsets, gaze has been extensively applied to tasks such as selection, text entry, and object manipulation. However, gaze based navigation despite being a fundamental interaction task remains largely underexplored. In particular, little is known about which path types are well suited for gaze navigation and …

Classification of Lipschitz unimodal function germs
Nhan Nguyen, Maria Ruas, Saurabh Trivedi
https://arxiv.org/abs/2510.06792 https://arxiv.org/pdf/2510.06…

Classification of Lipschitz unimodal function germs
In this paper, we introduce the notion of Lipschitz modality for isolated singularities $ f: (\mathbb{C}^n, 0) \to (\mathbb{C}, 0)$ and provide a complete classification of Lipschitz unimodal singularities of corank~2 with non-zero $4$-jets. As a consequence, such singularities are Lipschitz unimodal if they deform to $J_{10}$ but not to $J_{3,0}$. Furthermore, we show that singularities with vanishing $6$-jets have Lipschitz modality at least~$2$, thus establishing an upper bound for the order…

Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Sharut Gupta, Shobhita Sundaram, Chenyu Wang, Stefanie Jegelka, Phillip Isola
https://arxiv.org/abs/2510.08492

Better Together: Leveraging Unpaired Multimodal Data for Stronger Unimodal Models
Traditional multimodal learners find unified representations for tasks like visual question answering, but rely heavily on paired datasets. However, an overlooked yet potentially powerful question is: can one leverage auxiliary unpaired multimodal data to directly enhance representation learning in a target modality? We introduce UML: Unpaired Multimodal Learner, a modality-agnostic training paradigm in which a single model alternately processes inputs from different modalities while sharing pa…

Personality-Enhanced Multimodal Depression Detection in the Elderly
Honghong Wang, Jing Deng, Rong Zheng
https://arxiv.org/abs/2510.08004 https://arxiv.org…

Personality-Enhanced Multimodal Depression Detection in the Elderly
This paper presents our solution to the Multimodal Personality-aware Depression Detection (MPDD) challenge at ACM MM 2025. We propose a multimodal depression detection model in the Elderly that incorporates personality characteristics. We introduce a multi-feature fusion approach based on a co-attention mechanism to effectively integrate LLDs, MFCCs, and Wav2Vec features in the audio modality. For the video modality, we combine representations extracted from OpenFace, ResNet, and DenseNet to co…

Towards polarization-enhanced PET: Study of random background in polarization-correlated Compton events
Ana Marija Ko\v{z}uljevi\'c, Tomislav Bokuli\'c, Darko Gro\v{s}ev, Siddharth Parashari, Luka Paveli\'c, Marinko Rade, Marijan \v{Z}uvi\'c, Mihael Makek
https://arxiv.org/abs/2510.11504

Towards polarization-enhanced PET: Study of random background in polarization-correlated Compton events
Positron Emission Tomography (PET) is a medical imaging modality that utilizes positron-emitting isotopes, such as Ga-68 and F-18, for many diagnostic purposes. The positron annihilates with an electron from the surrounding area, creating two photons of 511 keV energy and opposite momenta, entangled in their orthogonal polarizations. When each photon undergoes a Compton scattering process, the difference of their azimuthal scattering angles reflects the initial orthogonality of their polarizati…

Efficient Domain Generalization in Wireless Networks with Scarce Multi-Modal Data
Minsu Kim, Walid Saad, Dour Calin
https://arxiv.org/abs/2510.04359 https://

Efficient Domain Generalization in Wireless Networks with Scarce Multi-Modal Data
In 6G wireless networks, multi-modal ML models can be leveraged to enable situation-aware network decisions in dynamic environments. However, trained ML models often fail to generalize under domain shifts when training and test data distributions are different because they often focus on modality-specific spurious features. In practical wireless systems, domain shifts occur frequently due to dynamic channel statistics, moving obstacles, or hardware configuration. Thus, there is a need for learn…

Replaced article(s) found for eess.AS. https://arxiv.org/list/eess.AS/new
[1/1]:
- Stimulus Modality Matters: Impact of Perceptual Evaluations from Different Modalities on Speech E...
Huang-Cheng Chou, Haibin Wu, Hung-yi Lee, Chi-Chun Lee

Replaced article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[5/9]:
- Modality-Balancing Preference Optimization of Large Multimodal Models by Adversarial Negative Mining
Chenxi Liu, Tianyi Xiong, Yanshuo Chen, Ruibo Chen, Yihan Wu, Junfeng Guo, Tianyi Zhou, Heng Huang

Replaced article(s) found for math.CT. https://arxiv.org/list/math.CT/new
[1/1]:
- An algebra modality admitting countably many deriving transformations
Jean-Baptiste Vienney

Characterizing Web Search in The Age of Generative AI
Elisabeth Kirsten, Jost Grosse Perdekamp, Mihir Upadhyay, Krishna P. Gummadi, Muhammad Bilal Zafar
https://arxiv.org/abs/2510.11560

Characterizing Web Search in The Age of Generative AI
The advent of LLMs has given rise to a new type of web search: Generative search, where LLMs retrieve web pages related to a query and generate a single, coherent text as a response. This output modality stands in stark contrast to traditional web search, where results are returned as a ranked list of independent web pages. In this paper, we ask: Along what dimensions do generative search outputs differ from traditional web search? We compare Google, a traditional web search engine, with four g…

Mull-Tokens: Modality-Agnostic Latent Thinking
Arijit Ray, Ahmed Abdelkader, Chengzhi Mao, Bryan A. Plummer, Kate Saenko, Ranjay Krishna, Leonidas Guibas, Wen-Sheng Chu
https://arxiv.org/abs/2512.10941

Stochastic numerical head phantoms to enable virtual imaging studies of transcranial photoacoustic computed tomography
Hsuan-Kai Huang, Joseph Kuo, Seonyeong Park, Umberto Villa, Lihong V. Wang, Mark A. Anastasio
https://arxiv.org/abs/2510.09758

Stochastic numerical head phantoms to enable virtual imaging studies of transcranial photoacoustic computed tomography
Transcranial photoacoustic computed tomography (PACT) is an emerging neuroimaging modality, but skull-induced aberrations can result in severe image artifacts if not compensated for during image reconstruction. The development of advanced image reconstruction methods for transcranial PACT is hindered by the lack of well-characterized, clinically relevant evaluation frameworks. Virtual imaging studies offer a solution, but require realistic numerical phantoms. To address this need, this study in…

Replaced article(s) found for cs.MM. https://arxiv.org/list/cs.MM/new
[1/1]:
- Towards Robust and Realible Multimodal Misinformation Recognition with Incomplete Modality
Hengyang Zhou, Yiwei Wei, Jian Yang, Zhenyu Zhang

Crosslisted article(s) found for cs.AI. https://arxiv.org/list/cs.AI/new
[7/8]:
- Unified Molecule Pre-training with Flexible 2D and 3D Modalities: Single and Paired Modality Inte...
Tengwei Song, Min Wu, Yuan Fang

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Minkyoung Cho, Ruben Ohana, Christian Jacobsen, Adityan Jothi, Min-Hung Chen, Z. Morley Mao, Ethem Can
https://arxiv.org/abs/2510.09561

TC-LoRA: Temporally Modulated Conditional LoRA for Adaptive Diffusion Control
Current controllable diffusion models typically rely on fixed architectures that modify intermediate activations to inject guidance conditioned on a new modality. This approach uses a static conditioning strategy for a dynamic, multi-stage denoising process, limiting the model's ability to adapt its response as the generation evolves from coarse structure to fine detail. We introduce TC-LoRA (Temporally Modulated Conditional LoRA), a new paradigm that enables dynamic, context-aware control by c…

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Lin Lin, Jiefeng Long, Zhihe Wan, Yuchi Wang, Dingkang Yang, Shuang Yang, Yueyang Yao, Xu Chen, Zirui Guo, Shengqiang Li, Weiran Li, Hanyu Li, Yaling Mou, Yan Qiu, Haiyang Yu, Xiao Liang, Hongsheng Li, Chao Feng
https://arxiv.org/abs/2510.12709

SAIL-Embedding Technical Report: Omni-modal Embedding Foundation Model
Multimodal embedding models aim to yield informative unified representations that empower diverse cross-modal tasks. Despite promising developments in the evolution from CLIP-based dual-tower architectures to large vision-language models, prior works still face unavoidable challenges in real-world applications and business scenarios, such as the limited modality support, unstable training mechanisms, and industrial domain gaps. In this work, we introduce SAIL-Embedding, an omni-modal embedding …

Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models
Tol\'ul\d{o}p\'e \`Og\'unr\`em\'i, Christopher D. Manning, Dan Jurafsky, Karen Livescu
https://arxiv.org/abs/2510.02569

Transcribe, Translate, or Transliterate: An Investigation of Intermediate Representations in Spoken Language Models
Spoken language models (SLMs) that integrate speech with large language models (LMs) rely on modality adapters (MAs) to map the output of speech encoders to a representation that is understandable to the decoder LM. Yet we know very little about how these crucial MAs transform representations. Here we examine the MA output representation in three SLMs (SALMONN, Qwen2-Audio and Phi-4-Multimodal-Instruct). By finding the nearest decoder LM token to an MA representation, we uncover two strategies …

LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection
Benjamin Shiue-Hal Chou, Purvish Jajal, Nick John Eliopoulos, James C. Davis, George K. Thiruvathukal, Kristen Yeon-Ji Yun, Yung-Hsiang Lu
https://arxiv.org/abs/2510.08580

LadderSym: A Multimodal Interleaved Transformer for Music Practice Error Detection
Music learners can greatly benefit from tools that accurately detect errors in their practice. Existing approaches typically compare audio recordings to music scores using heuristics or learnable models. This paper introduces \textit{LadderSym}, a novel Transformer-based method for music error detection. \textit{LadderSym} is guided by two key observations about the state-of-the-art approaches: (1) late fusion limits inter-stream alignment and cross-modality comparison capability; and (2) relia…

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Jianglin Lu, Hailing Wang, Yi Xu, Yizhou Wang, Kuo Yang, Yun Fu
https://arxiv.org/abs/2510.05184

Representation Potentials of Foundation Models for Multimodal Alignment: A Survey
Foundation models learn highly transferable representations through large-scale pretraining on diverse data. An increasing body of research indicates that these representations exhibit a remarkable degree of similarity across architectures and modalities. In this survey, we investigate the representation potentials of foundation models, defined as the latent capacity of their learned representations to capture task-specific information within a single modality while also providing a transferabl…

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
Jisu Han, Wonjun Hwang
https://arxiv.org/abs/2510.09473 https://…

D-TPT: Dimensional Entropy Maximization for Calibrating Test-Time Prompt Tuning in Vision-Language Models
Test-time adaptation paradigm provides flexibility towards domain shifts by performing immediate adaptation on unlabeled target data from the source model. Vision-Language Models (VLMs) leverage their generalization capabilities for diverse downstream tasks, and test-time prompt tuning has emerged as a prominent solution for adapting VLMs. In this work, we explore contrastive VLMs and identify the modality gap caused by a single dominant feature dimension across modalities. We observe that the …

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
Alin Fan, Hanqing Li, Sihan Lu, Jingsong Yuan, Jiandong Zhang
https://arxiv.org/abs/2510.11066

Decoupled Multimodal Fusion for User Interest Modeling in Click-Through Rate Prediction
Modern industrial recommendation systems improve recommendation performance by integrating multimodal representations from pre-trained models into ID-based Click-Through Rate (CTR) prediction frameworks. However, existing approaches typically adopt modality-centric modeling strategies that process ID-based and multimodal embeddings independently, failing to capture fine-grained interactions between content semantics and behavioral signals. In this paper, we propose Decoupled Multimodal Fusion (…

Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
Omri Uzan, Asaf Yehudai, Roi pony, Eyal Shnarch, Ariel Gera
https://arxiv.org/abs/2510.05038 htt…

Guided Query Refinement: Multimodal Hybrid Retrieval with Test-Time Optimization
Multimodal encoders have pushed the boundaries of visual document retrieval, matching textual query tokens directly to image patches and achieving state-of-the-art performance on public benchmarks. Recent models relying on this paradigm have massively scaled the sizes of their query and document representations, presenting obstacles to deployment and scalability in real-world pipelines. Furthermore, purely vision-centric approaches may be constrained by the inherent modality gap still exhibited…

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Soroosh Tayebi Arasteh, Mina Shaigan, Christiane Kuhl, Jakob Nikolas Kather, Sven Nebelung, Daniel Truhn
https://arxiv.org/abs/2510.07191

Resolution scaling governs DINOv3 transfer performance in chest radiograph classification
Self-supervised learning (SSL) has advanced visual representation learning, but its value in chest radiography, a high-volume imaging modality with fine-grained findings, remains unclear. Meta's DINOv3 extends earlier SSL models through Gram-anchored self-distillation. Whether these design choices improve transfer learning for chest radiography has not been systematically tested. We benchmarked DINOv3 against DINOv2 and ImageNet initialization across seven datasets (n>814,000). Two representati…

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
Tianren Ma, Mu Zhang, Yibing Wang, Qixiang Ye
https://arxiv.org/abs/2510.02880 https://

Consolidating Reinforcement Learning for Multimodal Discrete Diffusion Models
Optimizing discrete diffusion model (DDM) with rewards remains a challenge: the non-autoregressive paradigm makes importance sampling intractable and rollout complex, puzzling reinforcement learning methods such as Group Relative Policy Optimization (GRPO). In this study, we introduce MaskGRPO, the first viable approach to enable scalable multimodal reinforcement learning in discrete diffusion with effective importance sampling and modality-specific adaptations. To this end, we first clarify th…

A Novel Helical Thin-Film Flow Diverter: Design, Fabrication, and Computational Assessment of Hemodynamic Performance
Samuel Voss, Philipp Berg, Janneck Stahl, Daniel Behme, Gabor Janiga, Rodrigo Lima de Miranda, Eckhard Quandt, Prasanth Velvaluri
https://arxiv.org/abs/2510.05320

A Novel Helical Thin-Film Flow Diverter: Design, Fabrication, and Computational Assessment of Hemodynamic Performance
Flow diversion has become a key treatment modality for selected intracranial aneurysms, relying on the principle that a dense mesh of stent wires disrupts blood flow into the aneurysm sac, promoting thrombosis and vessel reconstruction. Despite its clinical success, a subset of patients experiences incomplete occlusion or complications. This study investigates innovative helical thin-film implants (HTFIs), aiming to evaluate their flow-diverting efficacy. Highly resolved computational fluid dyn…

Semantic Segmentation Algorithm Based on Light Field and LiDAR Fusion
Jie Luo, Yuxuan Jiang, Xin Jin, Mingyu Liu, Yihui Fan
https://arxiv.org/abs/2510.06687 https://

Semantic Segmentation Algorithm Based on Light Field and LiDAR Fusion
Semantic segmentation serves as a cornerstone of scene understanding in autonomous driving but continues to face significant challenges under complex conditions such as occlusion. Light field and LiDAR modalities provide complementary visual and spatial cues that are beneficial for robust perception; how- ever, their effective integration is hindered by limited viewpoint diversity and inherent modality discrepancies. To address these challenges, the first multimodal semantic segmentation datase…

Crosslisted article(s) found for physics.med-ph. https://arxiv.org/list/physics.med-ph/new
[1/1]:
- multimodars: A Rust-powered toolkit for multi-modality cardiac image fusion and registration
Anselm W. Stark, Marc Ilic, Ali Mokhtari, Pooya Mohammadi Kazaj, Christoph Graeni…

Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography
Refik Mert Cam, Seonyeong Park, Umberto Villa, Mark A. Anastasio
https://arxiv.org/abs/2510.03431

Application of a Virtual Imaging Framework for Investigating a Deep Learning-Based Reconstruction Method for 3D Quantitative Photoacoustic Computed Tomography
Quantitative photoacoustic computed tomography (qPACT) is a promising imaging modality for estimating physiological parameters such as blood oxygen saturation. However, developing robust qPACT reconstruction methods remains challenging due to computational demands, modeling difficulties, and experimental uncertainties. Learning-based methods have been proposed to address these issues but remain largely unvalidated. Virtual imaging (VI) studies are essential for validating such methods early in …