Tootfinder

Bridged Clustering for Representation Learning: Semi-Supervised Sparse Bridging
Patrick Peixuan Ye, Chen Shani, Ellen Vitercik
https://arxiv.org/abs/2510.07182 https://

Bridged Clustering for Representation Learning: Semi-Supervised Sparse Bridging
We introduce Bridged Clustering, a semi-supervised framework to learn predictors from any unpaired input $X$ and output $Y$ dataset. Our method first clusters $X$ and $Y$ independently, then learns a sparse, interpretable bridge between clusters using only a few paired examples. At inference, a new input $x$ is assigned to its nearest input cluster, and the centroid of the linked output cluster is returned as the prediction $\hat{y}$. Unlike traditional SSL, Bridged Clustering explicitly levera…

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
Zhiyuan Zhang, Can Wang, Dongdong Chen, Jing Liao
https://arxiv.org/abs/2510.08527 https://

FlexTraj: Image-to-Video Generation with Flexible Point Trajectory Control
We present FlexTraj, a framework for image-to-video generation with flexible point trajectory control. FlexTraj introduces a unified point-based motion representation that encodes each point with a segmentation ID, a temporally consistent trajectory ID, and an optional color channel for appearance cues, enabling both dense and sparse trajectory control. Instead of injecting trajectory conditions into the video generator through token concatenation or ControlNet, FlexTraj employs an efficient se…

Computation of operator exponentials using the Dunford-Cauchy integral
Alexander Tsirulev
https://arxiv.org/abs/2509.08600 https://arxiv.org/pdf/2509.08600…

Computation of operator exponentials using the Dunford-Cauchy integral
We consider an n-qubit quantum system with a Hamiltonian, defined by an expansion in the Pauli basis, and propose a new algorithm for classical computing the exponential of the Hamiltonian. The algorithm is based on the representation of the exponential by the Dunford-Cauchy integral, followed by an efficient computation of the resolvent, and is suitable for Hamiltonians that are sparse in the Pauli basis. The practical efficiency of the algorithm is demonstrated by two illustrative examples.

A James-Stein Estimator based Generalized OMP Algorithm for Robust Signal Recovery using Sparse Representation
Debraj Banerjee, Amitava Chatterjee
https://arxiv.org/abs/2509.01410

A James-Stein Estimator based Generalized OMP Algorithm for Robust Signal Recovery using Sparse Representation
In this paper, we introduce a novel algorithm named JS-gOMP, which enhances the generalized Orthogonal Matching Pursuit (gOMP) algorithm for improved noise robustness in sparse signal processing. The JS-gOMP algorithm uniquely incorporates the James-Stein estimator, optimizing the trade-off between signal recovery and noise suppression. This modification addresses the challenges posed by noise in the dictionary, a common issue in sparse representation scenarios. Comparative analyses demonstrate…

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 …

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
Cliff O'Reilly, Ernesto Jimenez-Ruiz, Tillman Weyde
https://arxiv.org/abs/2508.14275 https:…

Disentangling concept semantics via multilingual averaging in Sparse Autoencoders
Connecting LLMs with formal knowledge representation and reasoning is a promising approach to address their shortcomings. Embeddings and sparse autoencoders are widely used to represent textual content, but the semantics are entangled with syntactic and language-specific information. We propose a method that isolates concept semantics in Large Langue Models by averaging concept activations derived via Sparse Autoencoders. We create English text representations from OWL ontology classes, transla…

Sparse Recovery from Group Orbits
Timm Gilles, Hartmut F\"uhr
https://arxiv.org/abs/2507.19274 https://arxiv.org/pdf/2507.19274

Sparse Recovery from Group Orbits
While most existing sparse recovery results allow only minimal structure within the measurement scheme, many practical problems possess significant structure. To address this gap, we present a framework for structured measurements that are generated by random orbits of a group representation associated with a finite group. We differentiate between two scenarios: one in which the sampling set is fixed and another in which the sampling set is randomized. For each case, we derive an estimate for t…

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
Xiangyu Sun, Haoyi jiang, Liu Liu, Seungtae Nam, Gyeongjin Kang, Xinjie wang, Wei Sui, Zhizhong Su, Wenyu Liu, Xinggang Wang, Eunbyung Park
https://arxiv.org/abs/2508.03643

Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images
Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic understanding from reconstruction or necessitate costly per-scene optimization, thereby restricting their scalability and generalizability. In this paper, we introduce Uni3R, a novel feed-forward framework that jointly reconstructs a unified 3D scene representation enriched with open-vocabulary semantics, directly from unpos…

Contrastive Network Representation Learning
Zihan Dong, Xin Zhou, Ryumei Nakada, Lexin Li, Linjun Zhang
https://arxiv.org/abs/2509.11316 https://arxiv.org/…

Contrastive Network Representation Learning
Network representation learning seeks to embed networks into a low-dimensional space while preserving the structural and semantic properties, thereby facilitating downstream tasks such as classification, trait prediction, edge identification, and community detection. Motivated by challenges in brain connectivity data analysis that is characterized by subject-specific, high-dimensional, and sparse networks that lack node or edge covariates, we propose a novel contrastive learning-based statistic…

CASPER: Concept-integrated Sparse Representation for Scientific Retrieval
Lam Thanh Do, Linh Van Nguyen, David Fu, Kevin Chen-Chuan Chang
https://arxiv.org/abs/2508.13394 https:…

CASPER: Concept-integrated Sparse Representation for Scientific Retrieval
The exponential growth of scientific literature has made it increasingly difficult for researchers to keep up with the literature. In an attempt to alleviate this problem, we propose CASPER, a sparse retrieval model for scientific search that utilizes tokens and keyphrases as representation units (i.e. dimensions in the sparse embedding space), enabling it to represent queries and documents with research concepts and match them at both granular and conceptual levels. To overcome the lack of sui…

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Sangwoo Jeon, Juchul Shin, Gyeong-Tae Kim, YeonJe Cho, Seongwoo Kim
https://arxiv.org/abs/2508.10747

Scaling Up without Fading Out: Goal-Aware Sparse GNN for RL-based Generalized Planning
Generalized planning using deep reinforcement learning (RL) combined with graph neural networks (GNNs) has shown promising results in various symbolic planning domains described by PDDL. However, existing approaches typically represent planning states as fully connected graphs, leading to a combinatorial explosion in edge information and substantial sparsity as problem scales grow, especially evident in large grid-based environments. This dense representation results in diluted node-level infor…

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
Tomoya Yamashita, Akira Ito, Yuuki Yamanaka, Masanori Yamada, Takayuki Miura, Toshiki Shibahara
https://arxiv.org/abs/2509.15631

Sparse-Autoencoder-Guided Internal Representation Unlearning for Large Language Models
As large language models (LLMs) are increasingly deployed across various applications, privacy and copyright concerns have heightened the need for more effective LLM unlearning techniques. Many existing unlearning methods aim to suppress undesirable outputs through additional training (e.g., gradient ascent), which reduces the probability of generating such outputs. While such suppression-based approaches can control model outputs, they may not eliminate the underlying knowledge embedded in the…

Sparse Coding Representation of 2-way Data
Boya Ma, Abram Magner, Maxwell McNeil, Petko Bogdanov
https://arxiv.org/abs/2509.10033 https://arxiv.org/pdf/250…

Sparse Coding Representation of 2-way Data
Sparse dictionary coding represents signals as linear combinations of a few dictionary atoms. It has been applied to images, time series, graph signals and multi-way spatio-temporal data by jointly employing temporal and spatial dictionaries. Data-agnostic analytical dictionaries, such as the discrete Fourier transform, wavelets and graph Fourier, have seen wide adoption due to efficient implementations and good practical performance. On the other hand, dictionaries learned from data offer spar…

Multivariate Low-Rank State-Space Model with SPDE Approach for High-Dimensional Data
Jacopo Rodeschini, Lorenzo Tedesco, Francesco Finazzi, Philipp Otto, Alessandro Fass\`o
https://arxiv.org/abs/2509.12825

Multivariate Low-Rank State-Space Model with SPDE Approach for High-Dimensional Data
This paper proposes a novel low-rank approximation to the multivariate State-Space Model. The Stochastic Partial Differential Equation (SPDE) approach is applied component-wise to the independent-in-time Matérn Gaussian innovation term in the latent equation, assuming component independence. This results in a sparse representation of the latent process on a finite element mesh, allowing for scalable inference through sparse matrix operations. Dependencies among observed components are introduc…

BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots
Yufei Wei, Wangtao Lu, Sha Lu, Chenxiao Hu, Fuzhang Han, Rong Xiong, Yue Wang
https://arxiv.org/abs/2509.14636

BEV-ODOM2: Enhanced BEV-based Monocular Visual Odometry with PV-BEV Fusion and Dense Flow Supervision for Ground Robots
Bird's-Eye-View (BEV) representation offers a metric-scaled planar workspace, facilitating the simplification of 6-DoF ego-motion to a more robust 3-DoF model for monocular visual odometry (MVO) in intelligent transportation systems. However, existing BEV methods suffer from sparse supervision signals and information loss during perspective-to-BEV projection. We present BEV-ODOM2, an enhanced framework addressing both limitations without additional annotations. Our approach introduces: (1) dens…

HART: Human Aligned Reconstruction Transformer
Xiyi Chen, Shaofei Wang, Marko Mihajlovic, Taewon Kang, Sergey Prokudin, Ming Lin
https://arxiv.org/abs/2509.26621 https://…

HART: Human Aligned Reconstruction Transformer
We introduce HART, a unified framework for sparse-view human reconstruction. Given a small set of uncalibrated RGB images of a person as input, it outputs a watertight clothed mesh, the aligned SMPL-X body mesh, and a Gaussian-splat representation for photorealistic novel-view rendering. Prior methods for clothed human reconstruction either optimize parametric templates, which overlook loose garments and human-object interactions, or train implicit functions under simplified camera assumptions,…

PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representation
Mahmoud Khater, Mona Strauss, Philipp von Olshausen, Alexander Reiterer
https://arxiv.org/abs/2509.20207 htt…

PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representation
Point clouds produced by 3D sensors are often sparse and noisy, posing challenges for tasks requiring dense and high-fidelity 3D representations. Prior work has explored both implicit feature-based upsampling and distance-function learning to address this, but often at the expense of geometric interpretability or robustness to input sparsity. To overcome these limitations, we propose PU-Gaussian, a novel upsampling network that models the local neighborhood around each point using anisotropic 3…

ColdPress: Efficient Quantile-Based Compression of Photometric Redshift PDFs
Antonio Hern\'an-Caballero
https://arxiv.org/abs/2507.12481 https://

ColdPress: Efficient Quantile-Based Compression of Photometric Redshift PDFs
ColdPress is a Python module that compresses photometric redshift probability distribution functions (PDFs) by encoding quantiles of their cumulative distribution. For a fixed packet size (the default is 80 bytes per PDF), ColdPress attains a reconstruction accuracy comparable to the sparse-basis representation method implemented in the pdf_storage module of Carrasco-Kind & Brunner (2014), yet reduces the computational cost by a factor of ~7000. I describe the implementation and quantify its co…

An Enhanced Model-based Approach for Short Text Clustering
Enhao Cheng, Shoujia Zhang, Jianhua Yin, Xuemeng Song, Tian Gan, Liqiang Nie
https://arxiv.org/abs/2507.13793

An Enhanced Model-based Approach for Short Text Clustering
Short text clustering has become increasingly important with the popularity of social media like Twitter, Google+, and Facebook. Existing methods can be broadly categorized into two paradigms: topic model-based approaches and deep representation learning-based approaches. This task is inherently challenging due to the sparse, large-scale, and high-dimensional characteristics of the short text data. Furthermore, the computational intensity required by representation learning significantly increa…

Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
Fernando Martinez, Tao Li, Yingdong Lu, Juntao Chen
https://arxiv.org/abs/2508.07452 https://…

Stackelberg Coupling of Online Representation Learning and Reinforcement Learning
Integrated, end-to-end learning of representations and policies remains a cornerstone of deep reinforcement learning (RL). However, to address the challenge of learning effective features from a sparse reward signal, recent trends have shifted towards adding complex auxiliary objectives or fully decoupling the two processes, often at the cost of increased design complexity. This work proposes an alternative to both decoupling and naive end-to-end learning, arguing that performance can be signif…

E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mapping
Junyoung Kim, Minsik Jeon, Jihong Min, Kiho Kwak, Junwon Seo
https://arxiv.org/abs/2509.11964

E2-BKI: Evidential Ellipsoidal Bayesian Kernel Inference for Uncertainty-aware Gaussian Semantic Mapping
Semantic mapping aims to construct a 3D semantic representation of the environment, providing essential knowledge for robots operating in complex outdoor settings. While Bayesian Kernel Inference (BKI) addresses discontinuities of map inference from sparse sensor data, existing semantic mapping methods suffer from various sources of uncertainties in challenging outdoor environments. To address these issues, we propose an uncertainty-aware semantic mapping framework that handles multiple sources…

Representation Quantization for Collaborative Filtering Augmentation
Yunze Luo, Yinjie Jiang, Gaode Chen, Jingchi Wang, Shicheng Wang, Ruina Sun, Jiang Yuezihan, Jun Zhang, Jian Liang, Han Li, Kun Gai, Kaigui Bian
https://arxiv.org/abs/2508.11194

Representation Quantization for Collaborative Filtering Augmentation
As the core algorithm in recommendation systems, collaborative filtering (CF) algorithms inevitably face the problem of data sparsity. Since CF captures similar users and items for recommendations, it is effective to augment the lacking user-user and item-item homogeneous linkages. However, existing methods are typically limited to connecting through overlapping interacted neighbors or through similar attributes and contents. These approaches are constrained by coarse-grained, sparse attributes…

EIFNet: Leveraging Event-Image Fusion for Robust Semantic Segmentation
Zhijiang Li, Haoran He
https://arxiv.org/abs/2507.21971 https://arxiv.org/pdf/2507.2…

EIFNet: Leveraging Event-Image Fusion for Robust Semantic Segmentation
Event-based semantic segmentation explores the potential of event cameras, which offer high dynamic range and fine temporal resolution, to achieve robust scene understanding in challenging environments. Despite these advantages, the task remains difficult due to two main challenges: extracting reliable features from sparse and noisy event streams, and effectively fusing them with dense, semantically rich image data that differ in structure and representation. To address these issues, we propose…

Joint space-time wind field data extrapolation and uncertainty quantification using nonparametric Bayesian dictionary learning
George D. Pasparakis, Ioannis A. Kougioumtzoglou, Michael D. Shields
https://arxiv.org/abs/2507.11385

Joint space-time wind field data extrapolation and uncertainty quantification using nonparametric Bayesian dictionary learning
A methodology is developed, based on nonparametric Bayesian dictionary learning, for joint space-time wind field data extrapolation and estimation of related statistics by relying on limited/incomplete measurements. Specifically, utilizing sparse/incomplete measured data, a time-dependent optimization problem is formulated for determining the expansion coefficients of an associated low-dimensional representation of the stochastic wind field. Compared to an alternative, standard, compressive sam…

LLM-Enhanced Linear Autoencoders for Recommendation
Jaewan Moon, Seongmin Park, Jongwuk Lee
https://arxiv.org/abs/2508.13500 https://arxiv.org/pdf/2508.135…

LLM-Enhanced Linear Autoencoders for Recommendation
Large language models (LLMs) have been widely adopted to enrich the semantic representation of textual item information in recommender systems. However, existing linear autoencoders (LAEs) that incorporate textual information rely on sparse word co-occurrence patterns, limiting their ability to capture rich textual semantics. To address this, we propose L3AE, the first integration of LLMs into the LAE framework. L3AE effectively integrates the heterogeneous knowledge of textual semantics and us…

RadarGaussianDet3D: An Efficient and Effective Gaussian-based 3D Detector with 4D Automotive Radars
Weiyi Xiong, Bing Zhu, Tao Huang, Zewei Zheng
https://arxiv.org/abs/2509.16119

RadarGaussianDet3D: An Efficient and Effective Gaussian-based 3D Detector with 4D Automotive Radars
4D automotive radars have gained increasing attention for autonomous driving due to their low cost, robustness, and inherent velocity measurement capability. However, existing 4D radar-based 3D detectors rely heavily on pillar encoders for BEV feature extraction, where each point contributes to only a single BEV grid, resulting in sparse feature maps and degraded representation quality. In addition, they also optimize bounding box attributes independently, leading to sub-optimal detection accur…

Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
Abdul Rehman Antall, Naveed Akhtar
https://arxiv.org/abs/2508.09865 https://

Assessing the Feasibility of Lightweight Whisper Models for Low-Resource Urdu Transcription
This study evaluates the feasibility of lightweight Whisper models (Tiny, Base, Small) for Urdu speech recognition in low-resource settings. Despite Urdu being the 10th most spoken language globally with over 230 million speakers, its representation in automatic speech recognition (ASR) systems remains limited due to dialectal diversity, code-switching, and sparse training data. We benchmark these models on a curated Urdu dataset using word error rate (WER), without fine-tuning. Results show Wh…