100 accepted papers
This paper studies active regression for single-index models under general $\ell_p$-loss with an unknown $1$-Lipschitz link function $f$, formulated as $\min_{f,x} \Vert f(Ax)-b\Vert_p^p$ with full access to $A$ but coordinate-query access to $b$. Prior work established upper bounds for known link f…
Multimodal Large Language Models (MLLMs) have demonstrated exceptional capabilities in high-level visual understanding. However, extending these models to fine-grained dense prediction tasks, such as semantic segmentation and depth estimation, typically necessitates the incorporation of complex, tas…
Test-time prompt tuning for vision-language models has demonstrated impressive generalization capabilities under zero-shot settings. However, tuning the learnable prompts solely based on unlabeled test data may induce prompt optimization bias, ultimately leading to suboptimal performance on downstre
Federated learning (FL) on graphs shows promise for distributed time-series forecasting. Yet, existing methods rely on static topologies and struggle with client heterogeneity. We propose Fed-GAME, a framework that models personalized aggregation as message passing over a learnable dynamic implicit…
Despite the recent advancements of vision-language-action (VLA) models on a variety of robotics tasks, they suffer from critical issues such as poor generalizability to unseen tasks, due to their reliance on behavior cloning exclusively from successful rollouts. Furthermore, they are typically fine-…
Federated learning (FL) allows for collaborative model training while preserving data privacy, but its distributed nature makes it vulnerable to poisoning attacks. Existing defense methods typically rely on using gradients from multiple clients to define a trusted region, selecting only the trustwor
Large Language Models (LLMs) achieve remarkable success, but their massive parameter counts present significant deployment challenges. Post-training tensor decomposition offers a promising, data-free compression strategy by exploiting structural redundancies within the model weights. However, existi…
Selective prediction aims to endow predictors with a reject option, to avoid low confidence predictions. However, existing literature has primarily focused on closed-set tasks, such as visual question answering with predefined options or fixed-category classification. This paper considers selective…
Retrieval-Augmented Generation (RAG) systems are widely adopted in question answering, yet they often fail to satisfy complex multi-constraint queries, leading to constraint violations, factual inconsistencies, or hallucinations. We present Structure-Driven RAG System for Multi-Constraint Queries(MC
Multi-objective protein design is essential for meeting the complex demands of synthetic biology. To adapt to shifting multi-functional targets without the prohibitive cost of retraining, test-time scaling has emerged as a flexible, training-free alternative. However, current test-time diffusion met…
Multi-modal test-time adaptation (TTA) enhances the resilience of benchmark multi-modal models against distribution shifts by leveraging the unlabeled target data during inference. Despite the documented success, the advancement of multi-modal TTA methodologies has been impeded by a persistent limit
Speech translation (ST) aims to translate speech from a source language into text in the target language. Naturally, speech signals contain paralinguistic cues beyond linguistic content, which could influence or even alter the interpretation of a lexically identical sentence, thereby yielding distin
The four-wheel-independent-drive electric vehicle (4WID-EV) with typical redundancy characteristics provide a flexible control scheme, including functions such as active front steering (AFS), active rear steering (ARS) and direct yaw moment control (DYC). However, existing work lacks a reasonable me
In environments where robots operate with limited global navigation satellite system accessibility, ultra-wideband (UWB) localization technology is a popular auxiliary solution to assist visual–inertial odometry systems. However, current UWB approaches lack 3-D pairwise localization capability and s…
Based on the prevalent intermediate fusion (IF) and late fusion (LF) frameworks, multimodal representation learning (MML) demonstrates its superiority over unimodal representation learning. To investigate the intrinsic factors underlying the empirical success of MML, research grounded in theoretical…
TIPO (Text-to-Image Prompt Optimization) introduces an efficient approach for automatic prompt refinement in text-to-image (T2I) generation. Starting from simple user prompts, TIPO leverages a lightweight pre-trained model to expand these prompts into richer, detailed versions. Conceptually, TIPO sa…
Temporal graphs are essential for modeling complex real-world systems, such as social interactions, financial transactions, and recommendation systems, but the high computational cost and model complexity of dynamic graph neural networks (DGNNs) pose significant challenges for practical deployment.
In multi-agent systems, the hybrid active-silent relative localization framework is widely employed, where only active nodes transmit signals. The selection of active nodes, known as node activation, significantly impacts the positioning accuracy. This paper investigates the node activation in ancho…
Path planners are widely used in many different fields to determine a sequence of valid configurations for an object, such as a robot arm, between a start configuration and a goal configuration, where a valid configuration must be a collision-free one. However, sometimes configurations that are in c
Change captioning aims to describe differences between a pair of images using natural language. However, learning effective difference representations is highly challenging due to distractors such as illumination and viewpoint changes. To address this, we propose a change-entity-guided disentangleme…
Graph unlearning technology has become increasingly important since the advent of the `right to be forgotten' and the growing concerns about the privacy and security of artificial intelligence. Graph unlearning aims to quickly eliminate the effects of specific data on graph neural networks (GNNs). H…
In this paper, we present a novel diffusion model-based monaural speech enhancement method. Our approach incorporates the separate estimation of speech spectra's magnitude and phase in two diffusion networks. Throughout the diffusion process, noise clips from real-world noise interferences are added…
Facial beautification removal presents a formidable inverse challenge due to the inherent diversity and unpredictability of beautification processes. Current methodologies often fall short in effectively restoring facial structural alterations and preserving texture features during makeup removal. T…
Code Large Language Models (Code LLMs) have opened a new era in programming with their impressive capabilities. However, recent research has revealed critical limitations in their ability to reason about runtime behavior and understand the actual functionality of programs, which poses significant ch
The pre-trained models contain multitudinous knowledge from huge amount of data. However, when applying these models to downstream tasks, they may mis-locate to wrong knowledge distribution due to a lack of domain or contextual knowledge. To address the distribution bias between the pre-trained mode…
Style transfer is a challenging task in computer vision, aiming to blend the stylistic features of one image with the content of another while preserving the content details. Traditional methods often face challenges in terms of computational efficiency and fine-grained content preservation. In this
Large Multimodal Models (LMMs) extend Large Language Models (LLMs) by handling diverse inputs such as images, audio, and video, but at the cost of adding a multimodal encoding stage that increases both computational and memory overhead. This step negatively affects key Service Level Objectives (SLOs…
While the rapid proliferation of wearable cameras has raised significant concerns about egocentric video privacy, prior work has largely overlooked the unique privacy threats posed to the camera wearer. This work investigates the core question: How much privacy information about the camera wearer ca…
We study efficient algorithms for the Euclidean $k$-Center problem, focusing on the regime of large $k$. We take the approach of data reduction by considering $\alpha$-coreset, which is a small subset $S$ of the dataset $P$ such that any $\beta$-approximation on $S$ is an $(\alpha + \beta)$-approxim…
Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics. One fundamental challenge is the lack of robotic data, which are typically obtained through expensive on-robot ope…
Accurate dynamic modeling and external force estimation are crucial for high-precision robot control and applications. However, model incompleteness and external disturbances inevitably lead to a residual between the actual joint torque and the torque calculated by the identified dynamic model. To a
Human pose estimation in computer vision predominantly focuses on the visible modality, with limited research on the infrared modality. No existing methods demonstrate robust performance across both modalities, missing their complementary strengths. This gap arises from the lack of a multimodal benc…
Multimodal knowledge graphs (KGs) have found widespread applications in data integration and processing, yet existing multimodal knowledge graphs are often highly incomplete, which impedes their wide adoption. Thereby multimodal knowledge graph completion (MKGC) has attracted widespread attention. H…
This study presents a novel environment-aware reinforcement learning (RL) framework designed to augment the operational capabilities of autonomous underwater vehicles (AUVs) in underwater environments. Departing from traditional RL architectures, the proposed framework integrates an environment-awar
The active regression problem of the single-index model is to solve $\min_x \lVert f(Ax)-b\rVert_p$, where $A$ is fully accessible and $b$ can only be accessed via entry queries, with the goal of minimizing the number of queries to the entries of $b$. When $f$ is Lipschitz, previous results only obt…
The adaptivity and maneuvering capabilities of Autonomous Underwater Vehicles (AUVs) have drawn significant attention in oceanic research, due to the unpredictable disturbances and strong coupling among the AUV’s degrees of freedom. In this paper, we developed large language model (LLM)-enhanced rei
In warehouse environments, robots require robust picking capabilities to manage a wide variety of objects. Effective deployment demands minimal hardware, strong generalization to new products, and resilience in diverse settings. Current methods often rely on depth sensors for structural information,
As privacy protection gains momentum, federated learning has emerged as a cutting-edge approach in medical image analysis. However, the intricacies of medical image segmentation task have led to a dearth of research in this domain, with existing studies falling short in tackling two pivotal challeng…
Current lidar and camera-based solutions for low-cost indoor mobile robots have limitations such as poor performance in visually obscured environments, high computational overhead for data processing, and high costs for lidars. In contrast, mmWave radar sensors offer a cost-effective and lightweight
Urban computing harnesses big data to decode complex urban dynamics and revolutionize location-based services. Traditional approaches have treated geospatial prediction tasks (e.g., estimating socio-economic indicators) and retrieval tasks (e.g., querying geographic objects) as isolated challenges,…
Robustness to outliers is important in machine learning. Many classical problems, including subspace embedding, clustering, and low-rank approximation, lack scalable, outlier-resilient algorithms. This paper considers machine learning problems of the form $\min_{x\in \mathbb{R}^d} F(x)$, where $F(x)…
In scoliosis surgery, the limited field of view of the C-arm Xray machine restricts the surgeons’ holistic analysis of spinal structures. This paper presents an end-to-end efficient and robust intraoperative X-ray image stitching method for scoliosis surgery, named SX-Stitch. The method is divided i…
Generative models have recently gained attention in recommendation systems by directly predicting item identifiers from user interaction sequences. However, existing methods suffer from significant information loss due to the separation of stages such as quantization and sequence modeling, hindering…
Vision Transformers (ViTs), extensively pre-trained on large-scale datasets, have become fundamental to foundation models, enabling adaptation to diverse downstream tasks. Existing adaptation methods typically require direct data access, rendering them infeasible in privacy-sensitive domains where c…
Distribution shifts in recommender systems between training and testing in user-item interactions lead to inaccurate recommendations. Despite the promising performance of test-time adaptation technology in various domains, it still faces challenges in recommender systems due to the impracticality of
Multimodal large language models (MLLMs) are broadly empowering various fields. Despite their advancements, the explainability of MLLMs remains less explored, hindering deeper understanding, model credibility, and effective visualization. Unlike conventional vision models (e.g., CNNs, ViTs, CLIP) th…
Training Graph Neural Networks (GNNs) often relies on repeated, irregular, and expensive message-passing operations over all nodes (e.g., $N$), leading to high computational overhead. To alleviate this inefficiency, we revisit the GNNs training from a spectral perspective. In many real-world graphs,…
Semi-supervised semantic segmentation (SSSS) has been proposed to alleviate the burden of time-consuming pixel-level manual labeling which leverages limited labeled data along with larger amounts of unlabeled data. Current state-of-the-art methods train the labeled data with ground truths and unlabe…
Vision Language Models (VLMs), which extend Large Language Models (LLM) by incorporating visual understanding capability, have demonstrated significant advancements in addressing open-ended visual question-answering (VQA) tasks. However, these models cannot accurately interpret images infused with t…
Ultra-wide band (UWB) systems are gaining popularity for multi-robot localization benefiting from their high-accuracy ranging capabilities. However, current UWB systems fall short in determining orientations and realizing pair-wise localization for neglecting bearing information. Given the importanc…
We propose Deep Longitudinal Targeted Minimum Loss-based Estimation (Deep LTMLE), a novel approach to estimate the counterfactual mean of outcome under dynamic treatment policies in longitudinal problem settings. Our approach utilizes a transformer architecture with heterogeneous type embedding trai…
To help researchers find papers of interest quickly and accurately, paper recommendations are widely deployed. However, they face unique challenges, including the exploitation of rich multi-modal features and the modeling of complex relationships. In terms of multi-modal features, previous work has…
Active learning (AL) for multiple target models aims to reduce labeled data querying while effectively training multiple models concurrently. Existing AL algorithms often rely on iterative model training, which can be computationally expensive, particularly for deep models. In this paper, we propose…
We study the problem of residual error estimation for matrix and vector norms using a linear sketch. Such estimates can be used, for example, to quickly assess how useful a more expensive low-rank approximation computation will be. The matrix case concerns the Frobenius norm and the task is to appro…
While impressive performance has been achieved in image captioning, the limited diversity of the generated captions and the large parameter scale remain major barriers to the real-word application of these systems. In this work, we propose a lightweight image captioning network in combination with c…
Spiking Neural Networks (SNNs) have gained attention for their apparent energy efficiency and significant biological interpretability, although they also face significant challenges such as prolonged latency and suboptimal tracking accuracy. Recent studies have explored the application of SNNs in ob…
Out-of-distribution (OOD) detection refers to training the model on in-distribution (ID) dataset to classify if the input images come from unknown classes. Considerable efforts have been invested in designing various OOD detection methods based on either convolutional neural networks or transformers…
We consider sketching algorithms which first compress data by multiplication with a random sketch matrix, and then apply the sketch to quickly solve an optimization problem, e.g., low-rank approximation and regression. In the learning-based sketching paradigm proposed by Indyk et al., the sketch mat…
Segmentation and tracking of unseen object instances in discrete frames pose a significant challenge in dynamic industrial robotic contexts, such as distribution warehouses. Here, robots must handle object rearrangements, including shifting, removal, and partial occlusion by new items, and track the…
Do video-text transformers learn to model temporal relationships across frames? Despite their immense capacity and the abundance of multimodal training data, recent work has revealed the strong tendency of video-text models towards frame-based spatial representations, while temporal reasoning remain…
Style transfer has been well studied in recent years with excellent performance processed. While existing methods usually choose CNNs as the powerful tool to accomplish superb stylization, less attention was paid to the latent style space. Rare exploration of underlying dimensions results in the poo…
"While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc. Orthogonal to them, this work presents a category-level object pose…
In this work, we focus on a very practical problem: image segmentation under rain conditions. Image deraining is a classic low-level restoration task, while image segmentation is a typical high-level understanding task. Most of the existing methods intuitively employ the bottom-up paradigm by taking…
Despite achieving superior performance in human-level control problems, unlike humans, deep reinforcement learning (DRL) lacks high-order intelligence (e.g., logic deduction and reuse), thus it behaves ineffectively than humans regarding learning and generalization in complex problems. Previous work…
Temporal modeling is an essential element in video understanding. While deep convolution-based architectures have been successful at solving large-scale video recognition datasets, recent work has pointed out that they are biased towards modeling short-range relations, often failing to capture long-…
Though existing researches have achieved impressive results in controlled text generation, they focus mainly on single-attribute control. However, in applications like automatic comments, the topic and sentiment need to be controlled simultaneously. In this work, we propose a new framework for multi…
Active regression considers a linear regression problem where the learner receives a large number of data points but can only observe a small number of labels. Since online algorithms can deal with incremental training data and take advantage of low computational cost, we consider an online extensio…
Learning-based image dehazing methods have achieved marvelous progress during the past few years. On one hand, most approaches heavily rely on synthetic data and may face difficulties to generalize well in real scenes, due to the huge domain gap between synthetic and real images. On the other hand,…
Weakly-Supervised Semantic Segmentation (WSSS) segments objects without heavy burden of dense annotation. While as a price, generated pseudo-masks exist obvious noisy pixels, which result in sub-optimal segmentation models trained over these pseudo-masks. But rare studies notice or work on this prob…
Designing better machine translation systems by considering auxiliary inputs such as images has attracted much attention in recent years. While existing methods show promising performance over the conventional text-only translation systems, they typically require paired text and image as input durin…
ocial distancing, an essential public health measure to limit the spread of contagious diseases, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas, with wide field-of-view cam…
Heterogeneous information networks (HINs) are ideal for describing real-world data with different types of entities and relationships. To carry out machine learning on HINs, meta-paths are widely utilized to extract semantics with pre-defined patterns, and models such as graph convolutional networks…
Oil and gas pipelines are known as the backbone of global energy, and securing their safety is crucial for energy supply. In this study, we utilized a novel machine learning method based on the spatiotemporal features of distributed optical fiber sensor signals to monitor the safety of oil and gas p…
Most weakly supervised semantic segmentation (WSSS) methods follow the pipeline that generates pseudo-masks initially and trains the segmentation model with the pseudo-masks in fully supervised manner after. However, we find some matters related to the pseudo-masks, including high quality pseudo-mas…
In applications such as natural language processing or computer vision, one is given a large $n \times n$ matrix $A = (a_{i,j})$ and would like to compute a matrix decomposition, e.g., a low rank approximation, of a function $f(A) = (f(a_{i,j}))$ applied entrywise to $A$. A very important special ca…
Multi-task learning (MTL) has been widely used in representation learning. However, naively training all tasks simultaneously may lead to the partial training issue, where specific tasks are trained more adequately than others. In this paper, we propose to learn multiple tasks impartially. Specifica…
Talking face generation aims to synthesize a face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video via the given speech clip and facial image. Most existing methods mainly focus on either disentangling the information in a single image or l…
The problem of learning an image classifier that allows detection of out-of-distribution (OOD) examples, with the help of auxiliary background datasets, is studied. While training with background has been shown to improve OOD detection performance, the optimal choice of such dataset remains an open…
We consider the problem of creating tighter-fitting bounding volumes (more specifically rectangular swept spheres) when constructing bounding volume hierarchies (BVHs) for complex 3D geometries given in the form of unstructured triangle meshes/soups with the aim of speeding up our IPS Path Planner f…
Path planning of an object which is allowed to be in contact with other objects during assembly process is a significant challenge due to the variety of permitted or forbidden collisions between the distinct parts of the objects to be assembled. In order to put objects together in real-life scenario…
The cross-sensor gap is one of the challenges that have aroused much research interests in Heterogeneous Face Recognition (HFR). Although recent methods have attempted to fill the gap with deep generative networks, most of them suffer from the inevitable misalignment between different face modalitie…
The performance of multi-domain image-to-image translation has been significantly improved by recent progress in deep generative models. Existing approaches can use a unified model to achieve translations between all the visual domains. However, their outcomes are far from satisfying when there are…
We give the first input-sparsity time algorithms for the rank-$k$ low rank approximation problem in every Schatten norm. Specifically, for a given $n\times n$ matrix $A$, our algorithm computes $Y,Z\in \R^{n\times k}$, which, with high probability, satisfy $\|A-YZ^T\|_p \leq (1+\eps)\|A-A_k\|_p$, wh…
We introduce a novel self-supervised pretext task for learning representations from audio-visual content. Prior work on audio-visual representation learning leverages correspondences at the video level. Approaches based on audio-visual correspondence (AVC) predict whether audio and video clips origi…
The data stream model is a fundamental model for processing massive data sets with limited memory and fast processing time. Recently Hsu et al. (2019) incorporated machine learning techniques into the data stream model in order to learn relevant patterns in the input data. Such techniques were encap…
We give a row sampling algorithm for the quantile loss function with sample complexity nearly linear in the dimensionality of the data, improving upon the previous best algorithm whose sampling complexity has at least cubic dependence on the dimensionality. Based upon our row sampling algorithm, we…
Successful visual recognition networks benefit from aggregating information spanning from a wide range of scales. Previous research has investigated information fusion of connected layers or multiple branches in a block, seeking to strengthen the power of multi-scale representations. Despite their g…
Modern machine learning datasets can have biases for certain representations that are leveraged by algorithms to achieve high performance without learning to solve the underlying task. This problem is referred to as "representation bias". The question of how to reduce the representation biases of a…
Estimating the 6D pose of objects from images is an important problem in various applications such as robot manipulation and virtual reality. While direct regression of images to object poses has limited accuracy, matching rendered images of an object against the input image can produce accurate res…
A central problem in mining massive data streams is characterizing which functions of an underlying frequency vector can be approximated efficiently. Given the prevalence of large scale linear algebra problems in machine learning, recently there has been considerable effort in extending this data st…
While large datasets have proven to be a key enabler for progress in computer vision, they can have biases that lead to erroneous conclusions. The notion of the representation bias of a dataset is proposed to combat this problem. It captures the fact that representations other than the ground-truth…
Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. In this work, we introduce two new modules to enhance the transformation modeling capacity of CNNs, namely, deformable convolution and deforma…
We present the first fully convolutional end-to-end solution for instance-aware semantic segmentation task. It inherits all the merits of FCNs for semantic segmentation and instance mask proposal. It performs instance mask prediction and classification jointly. The underlying convolutional represent…
Feature selection aims to select relevant features to improve the performance of predictors. Many feature selection methods depend on the choice of dependence measures. To select features that have complex nonlinear relationships with the response variable, the dependence measure should be equitable…
A precision-improved processing architecture of physical computing for energy-efficient SIFT feature extraction algorithm has been proposed in this paper. With the novel physical computing technology of active resistor network (PC: ARN), the SIFT algorithm could be processed in analog signal domain…
We present region-based, fully convolutional networks for accurate and efficient object detection. In contrast to previous region-based detectors such as Fast/Faster R-CNN that apply a costly per-region subnetwork hundreds of times, our region-based detector is fully convolutional with almost all co…
We have developed a contraction and expansion-type artificial muscle by using the plasticized polyvinyl chloride (PVC) gel and mesh electrodes. The PVC gel artificial muscle exhibits a fast response in air, large deformation, variable stiffness, high output force and low power consumption under an e…
The grasp type provides crucial information about human action. However, recognizing the grasp type in unconstrained scenes is challenging because of the large variations in appearance, occlusions and geometric distortions. In this paper, first we present a convolutional neural network to classify…
We propose a perceptual grouping framework that organizes image edges into meaningful structures and demonstrate its usefulness on various computer vision tasks. Our grouper formulates edge grouping as a graph partition problem, where a learning to rank method is developed to encode probabilities of…
Retrieving 3D models from 2D human sketches has received considerable attention in the areas of graphics, image retrieval, and computer vision. Almost always in state of the art approaches a large amount of ``best views'' are computed for 3D models, with the hope that the query sketch matches one of…