72 accepted papers
Inductive knowledge graph completion (KGC) aims to predict missing links involving unseen entities, making it a particularly challenging task for knowledge representation learning. Traditional embedding-based methods often fall short in this setting due to their limited structural reasoning capabili
Existing proxy-based hashing methods optimize samples toward independently learned proxies using isolated similarity constraints. Although efficient, this design overlooks the fact that proxies are learned jointly but lack explicit relational or competitive interactions during optimization. Conseque…
Hard negative generation (HNG) provides valuable signals for deep learning, but existing methods mostly rely on local correlations while neglecting the global geometry of the embedding space. This limitation often leads to weak discrimination, particularly in cross-modal hashing, which obtains compa…
Recent cross-modal hashing methods have introduced sample generation strategies to enrich training signals. Despite these advances, sample generation-driven hashing still faces two major challenges: (1) Interpolation-based methods adopt deterministic and class-independent generation that restricts s
Joint multilingual instruction tuning is a widely adopted approach to improve the multilingual instruction-following ability and downstream performance of large language models (LLMs), but the resulting multilingual capability remains highly sensitive to the composition and selection of the training
Hashing techniques are widely adopted in large-scale cross-modal retrieval due to their efficiency and low storage cost. However, semantic ambiguities, including polysemy, multi-object images, and missing semantic descriptions, significantly degrade the accuracy of alignment and retrieval performanc
Large language models (LLMs) have shown promising capabilities in hardware description language (HDL) generation. However, existing approaches often rely on free-form natural language descriptions that are often ambiguous, redundant, and unstructured, which poses significant challenges for downstrea
Cross-modal Hashing (CMH) typically assumes a perfectly complete data annotation, whereas noisy labels are unavoidable in practical scenarios. Existing CMH methods often overlook the uncertainty introduced by noise or semantic ambiguity, making models susceptible to overfitting noisy labels and yiel…
Degraded steering performance and increased energy consumption present significant barriers to deploying wheeled mobile robots (WMRs) in granular media such as sand and lunar regolith. This study presents and experimentally validates a systematic optimization framework based on Dynamic Resistive For…
Degraded steering performance and increased energy consumption present significant barriers to deploying wheeled mobile robots (WMRs) in granular media such as sand and lunar regolith. This study presents and experimentally validates a systematic optimization framework based on Dynamic Resistive For
Large language models (LLMs) are known to suffer from severe hallucination issues. One of the main causes lies in the knowledge misalignment between the pre-training stage and the supervised fine-tuning stage. The unfamiliar knowledge encountered during fine-tuning may encourage LLMs to generate fac…
Current large language models (LLMs) often exhibit imbalanced multilingual capabilities due to their English-centric training corpora. To address this, existing fine-tuning approaches operating at the data-level (e.g., through data augmentation or distillation) typically introduce implicit cross-lin…
Self-supervised learning (SSL) methods via joint embedding architectures have proven remarkably effective at capturing semantically rich representations with strong clustering properties, magically in the absence of label supervision. Despite this, few of them have explored leveraging these untapped…
The rapid growth of scientific literature demands efficient methods to organize and synthesize research findings. Existing taxonomy construction methods, leveraging unsupervised clustering or direct prompting of large language models (LLMs), often lack coherence and granularity. We propose a novel c
Research is a fundamental process driving the advancement of human civilization, yet it demands substantial time and effort from researchers. In recent years, the rapid development of artificial intelligence (AI) technologies has inspired researchers to explore how AI can accelerate and enhance rese
Ensuring contextual faithfulness in retrieval-augmented large language models (LLMs) is crucial for building trustworthy information-seeking systems, particularly in long-form question-answering (LFQA) scenarios. In this work, we identify a salient correlation between LFQA faithfulness and retrieval…
Large vision-language models (LVLMs) have demonstrated exceptional capabilities in understanding visual information with human languages but also exhibit an imbalance in multilingual capabilities. In this work, we delve into the multilingual working pattern of LVLMs and identify a salient correlatio
Large language models (LLMs) have demonstrated impressive instruction following capabilities, while still struggling to accurately manage the length of the generated text, which is a fundamental requirement in many real-world applications. Existing length control methods involve fine-tuning the para…
Large language models (LLMs) encode vast world knowledge but struggle to stay up-to-date, often leading to errors and hallucinations. Knowledge editing offers an efficient alternative to retraining, enabling targeted modifications by updating specific model parameters. However, existing methods prim…
Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training paradigm to teach models to first understand non-English questions…
Knowledge Graphs (KGs) are structured data presented as directed graphs. Due to the common issues of incompleteness and inaccuracy encountered during construction and maintenance, completing KGs becomes a critical task. Inductive Knowledge Graph Completion (KGC) excels at inferring patterns or model…
Large language model unlearning has garnered increasing attention due to its potential to address security and privacy concerns, leading to extensive research in the field. However, existing studies have predominantly focused on instance-level unlearning, specifically targeting the removal of predef…
The rapid advancement of single-cell ATAC sequencing (scATAC-seq) technologies holds great promise for investigating the heterogeneity of epigenetic landscapes at the cellular level. The amplification process in scATAC-seq experiments often introduces noise due to dropout events, which results in ex…
Teaching large language models (LLMs) to generate text with citations to evidence sources can mitigate hallucinations and enhance verifiability in information-seeking systems. However, improving this capability requires high-quality attribution data, which is costly and labor-intensive. Inspired by…
"3D Gaussian Splatting (3DGS) creates a radiance field consisting of 3D Gaussians to represent a scene. With sparse training views, 3DGS easily suffers from overfitting, negatively impacting rendering. This paper introduces a new co-regularization perspective for improving sparse-view 3DGS. When tra…
We present an novel framework for efficiently and effectively extending the powerful continuous diffusion processes to discrete modeling. Previous approaches have suffered from the discrepancy between discrete data and continuous modeling. Our study reveals that the absence of guidance from discrete…
Though advanced in understanding visual information with human languages, Large Vision-Language Models (LVLMs) still suffer from multimodal hallucinations. A natural concern is that during multimodal interaction, the generated hallucinations could influence the LVLMs’ subsequent generation. Thus, we…
Despite the impressive performance on information-seeking tasks, large language models (LLMs) still struggle with hallucinations. Attributed LLMs, which augment generated text with in-line citations, demonstrate potential in mitigating hallucinations and improving verifiability. However, current app…
Whitening loss offers a theoretical guarantee against feature collapse in self-supervised learning (SSL) with joint embedding architectures. Typically, it involves a hard whitening approach, transforming the embedding and applying loss to the whitened output. In this work, we introduce Spectral Tran…
Layer normalization (LN) is a ubiquitous technique in deep learning but our theoretical understanding to it remains elusive. This paper investigates a new theoretical direction for LN, regarding to its nonlinearity and representation capacity. We investigate the representation capacity of a network…
With advancements in domain generalized stereo matching networks models pre-trained on synthetic data demonstrate strong robustness to unseen domains. However few studies have investigated the robustness after fine-tuning them in real-world scenarios during which the domain generalization ability ca…
Learning dense reward functions from unlabeled videos for reinforcement learning exhibits scalability due to the vast diversity and quantity of video resources. Recent works use visual features or graph abstractions in videos to measure task progress as rewards, which either deteriorate in unseen do…
This paper addresses the challenging problem of multistatic localization of a stationary object with a set of synchronized receivers, when the transmitter position is unknown and the synchronization with the transmitter is unavailable. Using the time delay measurements from the direct and indirect p…
Molecule generation, especially generating 3D molecular geometries from scratch (i.e., 3D de novo generation), has become a fundamental task in drug design. Existing diffusion based 3D molecule generation methods could suffer from unsatisfactory performances, especially when generating large molecul…
Filter pruning has attracted increasing attention in recent years for its capacity in compressing and accelerating convolutional neural networks. Various data-independent criteria, including norm-based and relationship-based ones, were proposed to prune the most unimportant filters. However, these s…
Locomotion failure is the challenge for wheeled robots applied in granular media, which puts a high demand on the design of wheels. Due to a lack of a mechanical analysis method that can analyze the dynamic interaction between wheel and granular media, it is a challenge to seek design guidance for t
A desirable objective in self-supervised learning (SSL) is to avoid feature collapse. Whitening loss guarantees collapse avoidance by minimizing the distance between embeddings of positive pairs under the conditioning that the embeddings from different views are whitened. In this paper, we propose…
Energy-based latent variable models (EBLVMs) are more expressive than conventional energy-based models. However, its potential on visual tasks are limited by its training process based on maximum likelihood estimate that requires sampling from two intractable distributions. In this paper, we propose…
Constraint by the physical geometry, the lower and upper frequency bound and the scale of the scanning area of a microphone array are limited. Owing to its movable feature, for the service robots, achieving a wider working frequency range with a global view requires a virtually larger and denser arr
Batch normalization (BN) is a milestone technique in deep learning. It normalizes the activation using mini-batch statistics during training but the estimated population statistics during inference. This paper focuses on investigating the estimation of population statistics. We define the estimation…
Despite recent stereo matching networks achieving impressive performance given sufficient training data, they suffer from domain shifts and generalize poorly to unseen domains. We argue that maintaining feature consistency between matching pixels is a vital factor for promoting the generalization ca…
This paper addresses the multistatic localization of a moving object in position and velocity using time delay (TD) and Doppler frequency shift (DFS) measurements, where the position of the transmitter is unknown and has not yet been synchronized with the receivers. Based on the TD and DFS measureme…
It is a challenge for the state-of-the-art non-synchronous measurements beamforming method to localize multiple broa-dband sources due to the difficulty in selecting an appropriate operating frequency without any prior information about the target signals. In this paper, we propose a tensor singular…
Batch Normalization (BN) is a core and prevalent technique in accelerating the training of deep neural networks and improving the generalization on Computer Vision (CV) tasks. However, it fails to defend its position in Natural Language Processing (NLP), which is dominated by Layer Normalization (LN…
A medical imaging model is usually explored for the diagnosis of a single disease. However, with the expanding demand for multi-disease diagnosis in clinical applications, multi-function solutions need to be investigated. Previous works proposed to either exploit different disease labels to conduct…
Batch normalization (BN) is an important technique commonly incorporated into deep learning models to perform standardization within mini-batches. The merits of BN in improving a model's learning efficiency can be further amplified by applying whitening, while its drawbacks in estimating population…
Chest X-rays are an important and accessible clinical imaging tool for the detection of many thoracic diseases. Over the past decade, deep learning, with a focus on the convolutional neural network (CNN), has become the most powerful computer-aided diagnosis technology for improving disease identifi…
Knowledge graph embedding models learn the representations of entities and relations in the knowledge graphs for predicting missing links (relations) between entities. Their effectiveness are deeply affected by the ability of modeling and inferring different relation patterns such as symmetry, asymm…
Previous studies dominantly target at self-supervised learning on real-valued networks and have achieved many promising results. However, on the more challenging binary neural networks (BNNs), this task has not yet been fully explored in the community. In this paper, we focus on this more difficult…
Generative adversarial networks (GANs) have achieved remarkable progress in recent years, but the continuously growing scale of models make them challenging to deploy widely in practical applications. In particular, for real-time generation tasks, different devices require generators of different si…
Diagnosing diseases from medical radiographs and writing reports requires professional knowledge and is time-consuming. To address this, automatic medical report generation approaches have recently gained interest. However, identifying diseases as well as correctly predicting their corresponding siz…
Batch Normalization (BN) is extensively employed in various network architectures by performing standardization within mini-batches. A full understanding of the process has been a central target in the deep learning communities. Unlike existing works, which usually only analyze the standardization o…
Orthogonality is widely used for training deep neural networks (DNNs) due to its ability to maintain all singular values of the Jacobian close to 1 and reduce redundancy in representation. This paper proposes a computationally efficient and numerically stable orthogonalization method using Newton's…
Deep generative models have been successfully applied to Zero-Shot Learning (ZSL) recently. However, the underlying drawbacks of GANs and VAEs (e.g., the hardness of training with ZSL-oriented regularizers and the limited generation quality) hinder the existing generative ZSL models from fully bypas…
Conditioning analysis uncovers the landscape of an optimization objective by exploring the spectrum of its curvature matrix. This has been well explored theoretically for linear models. We extend this analysis to deep neural networks (DNNs) in order to investigate their learning dynamics. To this en…
One fundamental problem in deep learning is understanding the outstanding performance of deep Neural Networks (NNs) in practice. One explanation for the superiority of NNs is that they can realize a large class of complicated functions, i.e., they have powerful expressivity. The expressivity of a Re…
Due to the advantages of retrieval speed and storage space, deep hashing methods have become a research hotspot in the field of large-scale image retrieval. Most of existing deep hashing methods pay close attention to similarity between images without images at the top of the ranking list similar to…
Sensing matrix can be designed with low coherence with the measurement matrix to improve the sparse signal recovery performance of greedy algorithms. However, most of the sensing matrix design algorithms are computationally expensive due to large number of iterations. This paper proposes an iteratio…
Medical image analysis has two important research areas: disease grading and fine-grained lesion segmentation. Although the former problem often relies on the latter, the two are usually studied separately. Disease severity grading can be treated as a classification problem, which only requires imag…
Batch Normalization (BN) is ubiquitously employed for accelerating neural network training and improving the generalization capability by performing standardization within mini-batches. Decorrelated Batch Normalization (DBN) further boosts the above effectiveness by whitening. However, DBN relies…
Batch Normalization (BN) is capable of accelerating the training of deep models by centering and scaling activations within mini-batches. In this work, we propose Decorrelated Batch Normalization (DBN), which not just centers and scales activations but whitens them. We explore multiple whitening tec…
We consider the non-orthogonal multiple access (NOMA) design for a classical two-user multiple access channel (MAC) with finite-alphabet inputs. In contrast to the majority of existing NOMA schemes using continuous Gaussian distributed inputs, we consider practical quadrature amplitude modulation (Q…
This paper proposes a novel approach to sparse recovery assisted direction-of-arrival (SR-DOA) estimation. By exploiting the sparsity inherent in the spatial spectrum, the DOA estimation is formulated as a sparse nonnegative least squares problem. Meanwhile, in order to enhance the estimation accura…
Training deep neural networks is difficult for the pathological curvature problem. Re-parameterization is an effective way to relieve the problem by learning the curvature approximately or constraining the solutions of weights with good properties for optimization. This paper proposes to re-paramete…
John's test, which is also known as the locally most invariant test for sphericity of Gaussian variables, is one of the most frequently used methods in multichannel signal detection. The application of John's test requires closed-form and accurate formula to set threshold according to a prescribed f…
In this paper, parameter estimation for multi-dimensional sinusoids in additive impulsive noise is addressed. Our underlying idea is to minimize the ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</sub> -norm of the residual error tensor, where 1 <;…
Phase retrieval has recently attracted renewed interest. It is revisited here through a new approach based on nonconvex quadratically constrained quadratic programming (QCQP). A least-squares (LS) formulation is adopted, and a recently developed non-convex QCQP approximation technique called feasibl…
This paper considers the sparse recovery problem of multiple measurement vector (MMV) model corrupted in impulsive noise. To ensure outlier-robust sparse recovery, we formulate an MMV problem that includes the generalized ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.…
Motion compensation (MOCOMP) is a key procedure in inverse synthetic aperture radar (ISAR) imaging because the accuracy of estimated parameter has a strong influence on the imaging quality. Generally, the backscattered signal of a moving target is sampled in fast time dimension, which can be approxi…
Joint estimation of the directions-of-arrival (DOAs) and frequencies of multiple signals is addressed in this paper. By constructing a set of joint diagonalization matrices, two cost functions that do not require a priori information of the source number are devised for DOA and frequency estimation…
Recent years have witnessed the success of hashing techniques in fast nearest neighbor search. In practice many applications (e.g., visual search, object detection, image matching, etc.) have enjoyed the benefits of complementary hash tables and information fusion over multiple views. However, most…
For noncircular signals, optimal widely linear (WL) minimum variance distortionless response (MVDR) beamformer has a powerful performance by exploiting the noncircularity of the received signals. Though, the noncircularity rate can be estimated by the steering vector (SV) of the signal of interest (…