54 accepted papers
High-dimensional data visualization (HDV) plays an important role in data science and engineering applications. Traditional HDV methods, such as Autoencoder and t-SNE, require hyperparameter tuning and iterative optimization on every dataset and cannot effectively utilize the knowledge from historic…
Visual attribute imbalance is a common yet underexplored issue in image classification, significantly impacting model performance and generalization. In this work, we first define the first-level and second-level attributes of images and then introduce a CLIP-based framework to construct a visual at
Data heterogeneity in Federated Learning (FL) leads to significant bias in local training. While recent efforts to introduce distributional statistics as priors have shown progress, they universally rely on a flawed global linearity assumption, failing to capture the nonlinear manifold structures pr…
Existing GUI grounding methods often struggle with fine-grained localization in high-resolution screenshots. To address this, we propose GUI-ARP, a novel framework that enables adaptive multi-stage inference. Equipped with the proposed Adaptive Region Perception (ARP) and Adaptive Stage Controlling…
Using intelligent systems to perceive psychological and social behaviors, that is, the underlying affective, cognitive, and pathological states that are manifested through observable behaviors and social interactions, remains a challenge due to their complex, multifaceted, and personalized nature. E…
A significant bottleneck in humanoid policy learning is the acquisition of large-scale, diverse datasets, as collecting reliable real-world data remains both difficult and cost-prohibitive. To address this limitation, we introduce HumanoidExo, a novel system that transfers human motion to whole-body…
Puzzlehunts are a genre of complex, multi-step puzzles lacking well-defined problem definitions. In contrast to conventional reasoning benchmarks consisting of tasks with clear instructions and constrained environments, puzzlehunts requires discovering the underlying problem structure from multimoda…
The ability of AI to sense and identify various substances based on their smell alone can have profound impacts on allergen detection (e.g., smelling gluten or peanuts in a cake), monitoring the manufacturing process, and sensing hormones that indicate emotional states, stress levels, and diseases.…
Generating a class integration test order (CITO) is essential to reduce the overhead of test stub construction (the primary cost in integration testing) and to ensure system reliability in complex software systems. Although reinforcement learning (RL) has shown promise in automating CITO generation,
Lateral connections (LCs) are ubiquitous in the cortical circuits. While modern deep learning architectures have rich intralayer interactions (e.g., convolutional mixing, normalization, or attention) to support feature selectivity and contextual modulation, explicit excitatory and inhibitory (E-I) L…
This work focuses on enhancing computational efficiency in wide-band radio frequency (RF) imaging. Specifically, we aim to efficiently generate multispectral RF images that contain information on range, angle, and frequency-selected responses, employing wide-band frequency-modulated continuous wave…
Unsupervised anomaly detection (UAD) has important applications in diverse fields such as manufacturing industry and medical diagnosis. In the past decades, although numerous insightful and effective UAD methods have been proposed, it remains a huge challenge to tune the hyper-parameters of each met…
Recent advances in clinical AI have enabled remarkable progress across many clinical domains. However, existing benchmarks and models are primarily limited to a small set of modalities and tasks, which hinders the development of large-scale multimodal methods that can make holistic assessments of pa…
Large Language Models (LLMs) have gained significant popularity due to their remarkable capabilities in text understanding and generation. However, despite their widespread deployment in inference services such as ChatGPT, concerns about the potential leakage of sensitive user data have arisen. Exis…
Although large language models (LLMs) show promise in solving complex mathematical tasks, existing evaluation paradigms rely solely on a coarse measure of overall answer accuracy, which are insufficient for assessing their authentic capabilities. In this paper, we propose \textbf{CogMath}, which com…
In recent years, there has been a significant amount of research on algorithms and control methods for distributed collaborative robots. However, the emergence of collective behavior in a swarm is still difficult to predict and control. Nevertheless, human interaction with the swarm helps render the
This paper addresses the challenges of automating vibratory sieve shaker operations in a materials laboratory, focusing on three critical tasks: 1) dual-arm lid manipulation in 3 cm clearance spaces, 2) bimanual handover in overlapping workspaces, and 3) obstructed powder sample container delivery w
This paper addresses gridless direction-of-arrival (DOA) estimation for unknown source signals across a wide frequency range. While processing signals jointly across multiple frequencies can improve DOA estimation accuracy, it significantly increases computational complexity as the model size expand…
Data heterogeneity in federated learning, characterized by a significant misalignment between local and global distributions, leads to divergent local optimization directions and hinders global model training. Existing studies mainly focus on optimizing local updates or global aggregation, but these…
Understanding the interactions between the central nervous system and muscular responses is essential for developing effective strategies to diagnose and manage movement disorders such as dystonia. This study addresses these complex interactions by introducing a novel non-linear forecasting method f…
Aligning Large Language Models (LLMs) with human feedback is crucial for their development. Existing preference optimization methods such as DPO and KTO, while improved based on Reinforcement Learning from Human Feedback (RLHF), are inherently derived from PPO, requiring a reference model that adds…
The evolution from motion capture and teleoperation to robot skill learning has emerged as a hotspot and critical pathway for advancing embodied intelligence. However, existing systems still face a persistent gap in simultaneously achieving four objectives: accurate tracking of full upper limb movem
Diffusion Models have gained significant popularity due to their remarkable capabilities in image generation, albeit at the cost of intensive computation requirement. Meanwhile, despite their widespread deployment in inference services such as Midjourney, concerns about the potential leakage of sens…
Large language models (LLMs) have made significant advancements, but their increasing capabilities present serious risks of misuse, particularly in open-weight models where direct access to the model’s parameters is possible. Current safeguards, designed for closed-weight API models, are inadequate…
In object detection, the number of instances is commonly used to determine whether a dataset follows a long-tailed distribution, implicitly assuming that the model will perform poorly on categories with fewer instances. This assumption has led to extensive research on category bias in datasets with…
Clinical decision‑making routinely demands reasoning over heterogeneous data, yet existing multimodal language models (MLLMs) remain largely vision‑centric and fail to generalize across clinical specialties. To bridge this gap, we introduce QoQ-Med-7B/32B, the first open generalist clinical foundati…
Naturalistic driving action recognition is essential for vehicle cabin monitoring systems. However, the complexity of real-world backgrounds presents significant challenges for this task, and previous approaches have struggled with practical implementation due to their limited ability to observe sub…
Unsupervised anomaly detection (UAD) plays an important role in modern data analytics and it is crucial to provide simple yet effective and guaranteed UAD algorithms for real applications. In this paper, we present a novel UAD method for tabular data by evaluating how much noise is in the data. Spec…
We study the reconstruction of an n-size r-spectrally-sparse signal from its m-size subset, with a specific focus on addressing the challenges arising from low sampling density. This recovery task can be transformed into a low-rank Hankel matrix completion problem in array form. Existing approaches…
Unbiased measurement of sperm morphometric and motility parameters is essential for assessing fertility potential and guiding visual feedback for microrobotic manipulation. Automated analysis of multiple sperms and selection of an optimal sperm is crucial for in vitro fertilisation treatment such as…
Class-incremental learning (CIL) aims to train a model to learn new classes from non-stationary data streams without forgetting old ones. In this paper, we propose a new kind of connectionist model by tailoring neural unit dynamics that adapt the behavior of neural networks for CIL. In each training…
To address wideband direction of arrival (DOA) estimation problems, this paper proposes a gridless and covariance-free joint multi-band (JMB) DOA estimation method using low-rank matrix recovery. In contrast with subspace methods and sparse array-based methods, a unified frequency grid is establishe…
Although there are commercial platforms with large antenna arrays operating over wide bands, narrow-band signals remain favored due to the hardware complexity and maximum unambiguous range considerations. This paper introduces a radio frequency (RF) imaging method employing multiple narrow-band freq…
Cortico-muscular communication patterns reveal important information about motor control. However, inferring significant causal relationships between motor cortex electroencephalogram (EEG) and surface electromyogram (sEMG) of concurrently active muscles is challenging since relevant processes invol…
Functional coupling between the cortex and muscle is commonly quantified by cortico-muscular coherence (CMC) between electroencephalogram (EEG) and electromyogram (EMG) signals. However, the presence of noise in EEG and EMG often degrades CMC, making it challenging to detect: some healthy subjects w…
Human brains are commonly modeled as networks of Regions of Interest (ROIs) and their connections for the understanding of brain functions and mental disorders. Recently, Transformer-based models have been studied over different types of data, including graphs, shown to bring performance gains widel…
Short-and-sparse deconvolution (SaSD) aims to recover a short kernel and a long and sparse signal from their convolution. In the literature, formulation of blind deconvolution is either a convex programming via a matrix lifting of convolution, or a bilinear Lasso. Optimization solvers are typically…
With the rapid development of multi-robot systems (MRSs), they can be widely used to perform various tasks in typical environments. However, the inevitable disadvantages of onboard sensor errors, communication delays, and underspecified environmental factors seriously affect the operation of MRSs. T
Though the blind super-resolution problem is nonconvex in nature, recent advance shows the feasibility of a convex formulation which gives the unique recovery guarantee. However, the convexification procedure is coupled with a huge computational cost and is therefore of great interests to investigat…
Typical methods for localisation in multipath environments focus on separating line-of-sight (LoS) from non-line-of-sight (NLoS) paths and only using LoS paths for localisation. A few works exploit NLoS paths but the methods are designed for some special settings. This paper presents a localisation…
Currently, distributed multi-robot systems (MRSs) can meet the requirements of various tasks in complex environments. Nevertheless, the inevitable disadvantages of robot sensor errors, communication delays, and obstructive environmental factors hinder the operation of MRSs. Therefore, a shared contr
In this work, we develop a new framework for denoising in blind two-dimensional (2D) super-resolution that recovers a set of 2D continuous parameters as well as unknown waveforms from noisy samples. We apply the atomic norm to de-noise a weighted sum of time-delayed and frequency-shifted unknown wav…
Retrieving relevant targets from an extremely large target set under computational limits is a common challenge for information retrieval and recommendation systems. Tree models, which formulate targets as leaves of a tree with trainable node-wise scorers, have attracted a lot of interests in tackli…
Algorithms for dictionary learning aim to learn a dictionary under which training data have sparse representations. This paper addresses the dictionary update sub-problem, the goal of which is to update the dictionary and the corresponding sparse coefficients given a fixed sparsity pattern. It is a…
In this paper, we provide a new mathematical framework for identifying the parameters of a linear system from its response to multiple unknown waveforms. We assume that the system response is given by an unknown number of scaled versions of time-delayed and frequency-shifted unknown waveforms. Then,…
Most distributed machine learning (ML) systems store a copy of the model parameters locally on each machine to minimize network communication. In practice, in order to reduce synchronization waiting time, these copies of the model are not necessarily updated in lock-step, and can become stale. Despi…
Identifiction of specific cortico-muscular interactions is essential for understanding sensorimotor control. These interactions are commonly studied by analyzing cortico-muscular coherence (CMC) between electroencephalogram (EEG) and surface electromyogram (sEMG) recorded synchronously under a motor…
Environmental sound detection is a challenging application of machine learning because of the noisy nature of the signal, and the small amount of (labeled) data that is typically available. This work thus presents a comparison of several state-of-the-art Deep Learning models on the IEEE challenge on…
Future frame prediction in videos is a promising avenue for unsupervised video representation learning. Video frames are naturally generated by the inherent pixel flows from preceding frames based on the appearance and motion dynamics in the video. However, existing methods focus on directly halluci…
Learning acoustic models directly from the raw waveform data with minimal processing is challenging. Current waveform-based models have generally used very few (~2) convolutional layers, which might be insufficient for building high-level discriminative features. In this work, we propose very deep c…
This paper concerns sparse Bayesian learning (SBL) problem for group sparse signals. Group sparsity means that the signal components can be divided into groups, and the entries in one group are simultaneously zero or nonzero. In SBL, each group is controlled by a hyper-parameter. The marginal likeli…
The paper quantifies and compares the exact asymptotic performance of multiple measurement vector (MMV) and distributed sensing (DS) models. Both models assume multiple measurement instances y <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">k</sub> = A…
With ever growing data volume and model size, an error-tolerant, communication efficient, yet versatile parallel algorithm has become a vital part for the success of many large-scale applications. In this work we propose mspg, an extension of the flexible proximal gradient algorithm to the model par…
We study parallel and distributed Frank-Wolfe algorithms; the former on shared memory machines with mini-batching, and the latter in a delayed update framework. In both cases, we perform computations asynchronously whenever possible. We assume block-separable constraints as in Block-Coordinate Frank…