Tootfinder

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
Thong Nguyen, Yibin Lei, Jia-Huei Ju, Eugene Yang, Andrew Yates
https://arxiv.org/abs/2510.00671 ht…

Milco: Learned Sparse Retrieval Across Languages via a Multilingual Connector
Learned Sparse Retrieval (LSR) combines the efficiency of bi-encoders with the transparency of lexical matching, but existing approaches struggle to scale beyond English. We introduce MILCO, an LSR architecture that maps queries and documents from different languages into a shared English lexical space via a multilingual connector. MILCO is trained with a specialized two-stage regime that combines Sparse Alignment Pretraining with contrastive training to provide representation transparency and …

Adaptive Bayesian Joint Latent Space Modeling via Cumulative Shrinkage
Bin Lv, Yincai Tang, Siliang Zhang
https://arxiv.org/abs/2509.18580 https://arxiv.or…

And the sunny context really helps to make space to consider our shared history.
Did I mention the harbour already 😉?

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Ran Liu, Yuan Fang, Xiaoli Li
https://arxiv.org/abs/2510.00894 https://arxiv.or…

FusionAdapter for Few-Shot Relation Learning in Multimodal Knowledge Graphs
Multimodal Knowledge Graphs (MMKGs) incorporate various modalities, including text and images, to enhance entity and relation representations. Notably, different modalities for the same entity often present complementary and diverse information. However, existing MMKG methods primarily align modalities into a shared space, which tends to overlook the distinct contributions of specific modalities, limiting their performance particularly in low-resource settings. To address this challenge, we pro…

Generative Co-Design of Antibody Sequences and Structures via Black-Box Guidance in a Shared Latent Space
Yinghua Yao, Yuangang Pan, Xixian Chen
https://arxiv.org/abs/2508.11424

Generative Co-Design of Antibody Sequences and Structures via Black-Box Guidance in a Shared Latent Space
Advancements in deep generative models have enabled the joint modeling of antibody sequence and structure, given the antigen-antibody complex as context. However, existing approaches for optimizing complementarity-determining regions (CDRs) to improve developability properties operate in the raw data space, leading to excessively costly evaluations due to the inefficient search process. To address this, we propose LatEnt blAck-box Design (LEAD), a sequence-structure co-design framework that opt…

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models
Zhifang Zhang, Jiahan Zhang, Shengjie Zhou, Qi Wei, Shuo He, Feng Liu, Lei Feng
https://arxiv.org/abs/2509.19994

Improving Generalizability and Undetectability for Targeted Adversarial Attacks on Multimodal Pre-trained Models
Multimodal pre-trained models (e.g., ImageBind), which align distinct data modalities into a shared embedding space, have shown remarkable success across downstream tasks. However, their increasing adoption raises serious security concerns, especially regarding targeted adversarial attacks. In this paper, we show that existing targeted adversarial attacks on multimodal pre-trained models still have limitations in two aspects: generalizability and undetectability. Specifically, the crafted targe…

Mixture of Encoders is a vector-native alternative that models both structured and unstructured data in a unified embedding space. At Berlin Buzzwords 2025, Filip Makraduli and Ben Gutkovich introduced the method, demonstrated how it powers natural language search and real-time recommendations, and shared open-source tools and benchmarks for replacing complex hybrid stacks.
Watch the full session: https://youtu.be/v-ak-Ohjqas?si=Lyvqcr0fb-0sa4ZW
Berlin Buzzwords returns on 7-9 June 2026: https://tickets.plainschwarz.com/bbuzz26/c/8Hvk0ZvJA/

I resisted giving an information security lecture in the changing room at the swimming pool but really. Teenage girls, one in the shared space and one in a changing cubicle 10 yards away. “He never said that?” “He did, he chatted me! Where’s my phone?” “It’s out here. What’s your password?” “222222”

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Jiehui Luo, Yuguo Yin, Yuxin Xie, Jinghan Ru, Xianwei Zhuang, Minghua He, Aofan Liu, Zihan Xiong, Dongchao Yang
https://arxiv.org/abs/2509.21033

SupCLAP: Controlling Optimization Trajectory Drift in Audio-Text Contrastive Learning with Support Vector Regularization
Contrastive language-audio pretraining, which aims to unify multimodal representations in a shared embedding space, serves as a cornerstone for building a wide range of applications, from cross-modal retrieval to cutting-edge multimodal large language models. However, we find that the perpendicular component of the pushing force from negative samples in contrastive learning is a double-edged sword: it contains rich supplementary information from negative samples, yet its unconstrained nature ca…

Exploring Bichronous Collaboration in Virtual Environments
Alexander Giovannelli, Shakiba Davari, Cherelle Connor, Fionn Murphy, Trey Davis, Haichao Miao, Vuthea Chheang, Brian Giera, Peer-Timo Bremer, Doug A. Bowman
https://arxiv.org/abs/2509.17230

Exploring Bichronous Collaboration in Virtual Environments
Virtual environments (VEs) empower geographically distributed teams to collaborate on a shared project regardless of time. Existing research has separately investigated collaborations within these VEs at the same time (i.e., synchronous) or different times (i.e., asynchronous). In this work, we highlight the often-overlooked concept of bichronous collaboration and define it as the seamless integration of archived information during a real-time collaborative session. We revisit the time-space ma…

Admission Control for Inelastic Traffic on a Link Shared by Deadline-Driven Elastic Traffic
Patrick Kreidl
https://arxiv.org/abs/2509.08135 https://arxiv.o…

Admission Control for Inelastic Traffic on a Link Shared by Deadline-Driven Elastic Traffic
Consider a (logical) link between two distributed data centers with available bandwidth designated for both deadline-driven elastic traffic, such as for scheduled synchronization services, and profitable inelastic traffic, such as for real-time streaming services. Admission control in this setting is cast as a stochastic shortest path problem, with state space derived from (discretization of) the elastic flow's size/deadline and action space corresponding to alternative subsets of admitted inel…

Sequential Convex Programming with Filtering-Based Warm-Starting for Continuous-Time Multiagent Quadrotor Trajectory Optimization
Minsen Yuan, Yue Yu
https://arxiv.org/abs/2508.14299

Sequential Convex Programming with Filtering-Based Warm-Starting for Continuous-Time Multiagent Quadrotor Trajectory Optimization
Optimizing the trajectories of multiple quadrotors in a shared space is a core challenge in various applications. Many existing trajectory optimization methods enforce constraints only at the discretization points, leading to violations between discretization points. They also often lack warm-starting strategies for iterative solution methods such as sequential convex programming, causing slow convergence or sensitivity to the initial guess. We propose a framework for optimizing multiagent quad…

The Mall That Could Have Been: What Happened to Our Vision for SF Centre / Westfield Mall
https://www.kultivatelabs.org/blog/the-mall-that-could-have-been-what-happened-to-our-vision-for-sf-centre

SPANER: Shared Prompt Aligner for Multimodal Semantic Representation
Thye Shan Ng, Caren Soyeon Han, Eun-Jung Holden
https://arxiv.org/abs/2508.13387 https://

SPANER: Shared Prompt Aligner for Multimodal Semantic Representation
Recent advances in multimodal Parameter-Efficient Fine-Tuning (PEFT) have significantly improved performance on downstream tasks such as few-shot retrieval. However, most existing approaches focus on task-specific gains while neglecting the structure of the multimodal embedding space. As a result, modality-specific representations often remain isolated, limiting cross-modal generalisation. In this work, we introduce Shared Prompt AligNER (SPANER), a modality-agnostic PEFT framework designed to …

Scaling Language-Centric Omnimodal Representation Learning
Chenghao Xiao, Hou Pong Chan, Hao Zhang, Weiwen Xu, Mahani Aljunied, Yu Rong
https://arxiv.org/abs/2510.11693 https://…

Scaling Language-Centric Omnimodal Representation Learning
Recent multimodal embedding approaches leveraging multimodal large language models (MLLMs) fine-tuned with contrastive learning (CL) have shown promising results, yet the underlying reasons behind their superiority remain underexplored. This work argues that a crucial advantage of MLLM-based approaches stems from implicit cross-modal alignment achieved during generative pretraining, where the language decoder learns to exploit multimodal signals within a shared representation space for generati…

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…

Diffusion-Guided Multi-Arm Motion Planning
Viraj Parimi, Brian C. Williams
https://arxiv.org/abs/2509.08160 https://arxiv.org/pdf/2509.08160

Diffusion-Guided Multi-Arm Motion Planning
Multi-arm motion planning is fundamental for enabling arms to complete complex long-horizon tasks in shared spaces efficiently but current methods struggle with scalability due to exponential state-space growth and reliance on large training datasets for learned models. Inspired by Multi-Agent Path Finding (MAPF), which decomposes planning into single-agent problems coupled with collision resolution, we propose a novel diffusion-guided multi-arm planner (DG-MAP) that enhances scalability of lea…

Fair metric distortion for matching with preferences
Jabari Hastings, Prasanna Ramakrishnan
https://arxiv.org/abs/2510.05460 https://arxiv.org/pdf/2510.054…

Fair metric distortion for matching with preferences
We consider the matching problem in the metric distortion framework. There are $n$ agents and $n$ items occupying points in a shared metric space, and the goal is to design a matching mechanism that outputs a low-cost matching between the agents and items, using only agents' ordinal rankings of the candidates by distance. A mechanism has distortion $α$ if it always outputs a matching whose cost is within a factor of $α$ of the optimum, in every instance regardless of the metric space. Typic…

Batched high-rate logical operations for quantum LDPC codes
Qian Xu, Hengyun Zhou, Dolev Bluvstein, Madelyn Cain, Marcin Kalinowski, John Preskill, Mikhail D. Lukin, Nishad Maskara
https://arxiv.org/abs/2510.06159

Batched high-rate logical operations for quantum LDPC codes
High-rate quantum LDPC (qLDPC) codes reduce memory overhead by densely packing many logical qubits into a single block of physical qubits. Here we extend this concept to high-rate computation by constructing \emph{batched} fault-tolerant operations that apply the same logical gate across many code blocks in parallel. By leveraging shared physical resources to execute many logical operations in parallel, these operations realize high rates in space-time and significantly reduce computational cos…

3D Aware Region Prompted Vision Language Model
An-Chieh Cheng, Yang Fu, Yukang Chen, Zhijian Liu, Xiaolong Li, Subhashree Radhakrishnan, Song Han, Yao Lu, Jan Kautz, Pavlo Molchanov, Hongxu Yin, Xiaolong Wang, Sifei Liu
https://arxiv.org/abs/2509.13317

3D Aware Region Prompted Vision Language Model
We present Spatial Region 3D (SR-3D) aware vision-language model that connects single-view 2D images and multi-view 3D data through a shared visual token space. SR-3D supports flexible region prompting, allowing users to annotate regions with bounding boxes, segmentation masks on any frame, or directly in 3D, without the need for exhaustive multi-frame labeling. We achieve this by enriching 2D visual features with 3D positional embeddings, which allows the 3D model to draw upon strong 2D priors…

Flow-Based Fragment Identification via Binding Site-Specific Latent Representations
Rebecca Manuela Neeser, Ilia Igashov, Arne Schneuing, Michael Bronstein, Philippe Schwaller, Bruno Correia
https://arxiv.org/abs/2509.13216

Flow-Based Fragment Identification via Binding Site-Specific Latent Representations
Fragment-based drug design is a promising strategy leveraging the binding of small chemical moieties that can efficiently guide drug discovery. The initial step of fragment identification remains challenging, as fragments often bind weakly and non-specifically. We developed a protein-fragment encoder that relies on a contrastive learning approach to map both molecular fragments and protein surfaces in a shared latent space. The encoder captures interaction-relevant features and allows to perfor…

Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings
Neal G. Ravindra, Arijit Sehanobish
https://arxiv.org/abs/2509.06966 https://

Cross-device Zero-shot Label Transfer via Alignment of Time Series Foundation Model Embeddings
High-quality, medically validated labels exist for clinical actigraphy data but not for ubiquitous consumer wearables like the Apple Watch. Manually labeling wearables data is expensive and doesn't scale. This paper offers a novel framework that transfers valuable labels from a source domain (e.g., actigraphy) to a target domain (e.g., Apple Watch) without requiring paired data. Instead of working with raw time-series signals, we project both domains into a shared latent embedding space using t…

MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Yi Xu, Moyu Zhang, Chenxuan Li, Zhihao Liao, Haibo Xing, Hao Deng, Jinxin Hu, Yu Zhang, Xiaoyi Zeng, Jing Zhang
https://arxiv.org/abs/2508.15281

MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation
Recommender systems traditionally represent items using unique identifiers (ItemIDs), but this approach struggles with large, dynamic item corpora and sparse long-tail data, limiting scalability and generalization. Semantic IDs, derived from multimodal content such as text and images, offer a promising alternative by mapping items into a shared semantic space, enabling knowledge transfer and improving recommendations for new or rare items. However, existing methods face two key challenges: (1) …

Unbounded: Object-Boundary Interactions in Mixed Reality
Zhuoyue Lyu, Per Ola Kristensson
https://arxiv.org/abs/2509.10750 https://arxiv.org/pdf/2509.10750…

Unbounded: Object-Boundary Interactions in Mixed Reality
Boundaries such as walls, windows, and doors are ubiquitous in the physical world, yet their potential in Mixed Reality (MR) remains underexplored. We present Unbounded, a Research through Design inquiry into Object-Boundary Interactions (OBIs). Building on prior work, we articulate a design space aimed at providing a shared language for OBIs. To demonstrate its potential, we design and implement eight examples across productivity and art exploration scenarios, showcasing how boundaries can enr…

Real Preferences Under Arbitrary Norms
Joshua Zeitlin, Corinna Coupette
https://arxiv.org/abs/2508.09046 https://arxiv.org/pdf/2508.09046

Real Preferences Under Arbitrary Norms
Whether the goal is to analyze voting behavior, locate facilities, or recommend products, the problem of translating between (ordinal) rankings and (numerical) utilities arises naturally in many contexts. This task is commonly approached by representing both the individuals doing the ranking (voters) and the items to be ranked (alternatives) in a shared metric space, where ordinal preferences are translated into relationships between pairwise distances. Prior work has established that any colle…

Co-Located VR with Hybrid SLAM-based HMD Tracking and Motion Capture Synchronization
Carlos A. Pinheiro de Sousa, Niklas Gr\"one, Mathias G\"unther, Oliver Deussen
https://arxiv.org/abs/2509.06582

Co-Located VR with Hybrid SLAM-based HMD Tracking and Motion Capture Synchronization
We introduce a multi-user VR co-location framework that synchronizes users within a shared virtual environment aligned to physical space. Our approach combines a motion capture system with SLAM-based inside-out tracking to deliver smooth, high-framerate, low-latency performance. Previous methods either rely on continuous external tracking, which introduces latency and jitter, or on one-time calibration, which cannot correct drift over time. In contrast, our approach combines the responsiveness …

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Sangmin Bae, Bilge Acun, Haroun Habeeb, Seungyeon Kim, Chien-Yu Lin, Liang Luo, Junjie Wang, Carole-Jean Wu
https://arxiv.org/abs/2510.04800

Hybrid Architectures for Language Models: Systematic Analysis and Design Insights
Recent progress in large language models demonstrates that hybrid architectures--combining self-attention mechanisms with structured state space models like Mamba--can achieve a compelling balance between modeling quality and computational efficiency, particularly for long-context tasks. While these hybrid models show promising performance, systematic comparisons of hybridization strategies and analyses on the key factors behind their effectiveness have not been clearly shared to the community.…

Revisiting Cross-View Localization from Image Matching
Panwang Xia, Qiong Wu, Lei Yu, Yi Liu, Mingtao Xiong, Lei Liang, Yongjun Zhang, Yi Wan
https://arxiv.org/abs/2508.10716 ht…

Revisiting Cross-View Localization from Image Matching
Cross-view localization aims to estimate the 3 degrees of freedom pose of a ground-view image by registering it to aerial or satellite imagery. It is essential in GNSS-denied environments such as urban canyons and disaster zones. Existing methods either regress poses directly or align features in a shared bird's-eye view (BEV) space, both built upon accurate spatial correspondences between perspectives. However, these methods fail to establish strict cross-view correspondences, yielding only co…

MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization
Haochen You, Baojing Liu
https://arxiv.org/abs/2508.12149 https://arxiv.org/…

MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization
Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structure in high-dimensional spaces. In this paper, we propose MOVER, a novel framework that combines optimal transport-based soft alignment with volume-based geometric regularization t…

Cheat-Penalised Quantum Weak Coin-Flipping
Atul Singh Arora, Carl A. Miller, Mauro E. S. Morales, Jamie Sikora
https://arxiv.org/abs/2510.03218 https://arx…

Cheat-Penalised Quantum Weak Coin-Flipping
Coin-flipping is a fundamental task in two-party cryptography where two remote mistrustful parties wish to generate a shared uniformly random bit. While quantum protocols promising near-perfect security exist for weak coin-flipping -- when the parties want opposing outcomes -- it has been shown that they must be inefficient in terms of their round complexity, and it is an open question of how space efficient they can be. In this work, we consider a variant called cheat-penalised weak coin-flipp…

Boosting Data Utilization for Multilingual Dense Retrieval
Chao Huang, Fengran Mo, Yufeng Chen, Changhao Guan, Zhenrui Yue, Xinyu Wang, Jinan Xu, Kaiyu Huang
https://arxiv.org/abs/2509.09459

Boosting Data Utilization for Multilingual Dense Retrieval
Multilingual dense retrieval aims to retrieve relevant documents across different languages based on a unified retriever model. The challenge lies in aligning representations of different languages in a shared vector space. The common practice is to fine-tune the dense retriever via contrastive learning, whose effectiveness highly relies on the quality of the negative sample and the efficacy of mini-batch data. Different from the existing studies that focus on developing sophisticated model arc…

LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation
Xuqin Wang, Tao Wu, Yanfeng Zhang, Lu Liu, Dong Wang, Mingwei Sun, Yongliang Wang, Niclas Zeller, Daniel Cremers
https://arxiv.org/abs/2509.08628

LADB: Latent Aligned Diffusion Bridges for Semi-Supervised Domain Translation
Diffusion models excel at generating high-quality outputs but face challenges in data-scarce domains, where exhaustive retraining or costly paired data are often required. To address these limitations, we propose Latent Aligned Diffusion Bridges (LADB), a semi-supervised framework for sample-to-sample translation that effectively bridges domain gaps using partially paired data. By aligning source and target distributions within a shared latent space, LADB seamlessly integrates pretrained source…

Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks
Bart Kuipers, Freek Byrman, Daniel Uyterlinde, Alejandro Garc\'ia-Castellanos
https://arxiv.org/abs/2510.08300 …

Symmetry-Aware Fully-Amortized Optimization with Scale Equivariant Graph Metanetworks
Amortized optimization accelerates the solution of related optimization problems by learning mappings that exploit shared structure across problem instances. We explore the use of Scale Equivariant Graph Metanetworks (ScaleGMNs) for this purpose. By operating directly in weight space, ScaleGMNs enable single-shot fine-tuning of existing models, reducing the need for iterative optimization. We demonstrate the effectiveness of this approach empirically and provide a theoretical result: the gauge …

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
Ara Seo, Bryan Sangwoo Kim, Hyungjin Chung, Jong Chul Ye
https://arxiv.org/abs/2510.02789 h…

Align Your Query: Representation Alignment for Multimodality Medical Object Detection
Medical object detection suffers when a single detector is trained on mixed medical modalities (e.g., CXR, CT, MRI) due to heterogeneous statistics and disjoint representation spaces. To address this challenge, we turn to representation alignment, an approach that has proven effective for bringing features from different sources into a shared space. Specifically, we target the representations of DETR-style object queries and propose a simple, detector-agnostic framework to align them with modal…