62 accepted papers
Existing polar robots are constrained by limited energy supply, making it difficult to carry out long-term scientific exploration missions, which highlights an urgent demand for energy conservation. An energy-efficient multi-mode motion polar robot is proposed to address this challenge. Both increas…
Bipeds have demonstrated high agility and mobility in unstructured environments such as sand. The yielding of such granular media brings significant sinkage and slip of the bipedal feet, leading to uncertainty and instability of walking locomotion. We present a new dynamics-modeling approach to capt…
This paper investigates the ambiguity function (AF) of communication signals carrying random data payloads, which is a fundamental metric characterizing sensing capability in ISAC systems. We first develop a unified analytical framework to evaluate the AF of communication-centric ISAC signals constr…
Recent advances in large multimodal models have leveraged image-based tools with reinforcement learning to tackle visual problems. However, existing open-source approaches often exhibit monotonous reasoning patterns and allow only a limited number of interaction turns, making them inadequate for dif…
We propose a novel unsupervised framework for online video stabilization. Unlike deep learning-based stabilizers that require paired stable/unstable datasets, our method models the classical three-stage stabilization pipeline and integrates a multithreaded buffering mechanism, effectively addressing
Human feet are crucial for supporting body weight and adapting to complex terrains. Adult-acquired flatfoot deformity (AAFD) arises from congenital or acquired causes, impairing the foot's ability to transition between flexible and rigid states, known as the lock-unlock mechanism during the stance a…
This position paper argues that the machine learning community should prioritize early-stage quality assurance in annotation pipelines over the prevailing practice of late-stage validation. Data quality bottlenecks increasingly limit foundation model improvement, yet quality assurance research focus…
Sustainability is becoming increasingly critical in the maritime transport, encompassing both environmental and social impacts, such as Greenhouse Gas (GHG) emissions and navigational safety. Traditional vessel navigation heavily relies on human experience, often lacking autonomy and emission awaren
The efficiency of GPU kernels is central to the progress of modern AI, yet optimizing them remains a difficult and labor-intensive task due to complex interactions between memory hierarchies, thread scheduling, and hardware-specific characteristics. While recent advances in large language models (LL…
Incorporating human feedback to optimize text-to-image models has demonstrated significant effectiveness. However, the process of collecting high-quality human preference labels is both resource-intensive and time-consuming. To address this challenge, we propose a novel approach that leverages a lar…
Offline reinforcement learning (RL) heavily relies on the coverage of pre-collected data over the target policy’s distribution. Existing studies aim to improve data-policy coverage to mitigate distributional shifts, but overlook security risks from insufficient coverage, and the single-step analysis
LLM-based agents have demonstrated remarkable capabilities in multi-step reasoning and task execution across domains such as robotics and autonomous systems. However, deploying these agents on resource-constrained platforms presents a fundamental challenge: minimizing latency while optimizing memory
Human feet are crucial for supporting body weight and adapting to complex terrains. Adult-acquired flatfoot deformity (AAFD) arises from congenital or acquired causes, impairing the foot's ability to transition between flexible and rigid states, known as the lock-unlock mechanism during the stance a
As the potential of multi-robot systems continues to be explored and validated across various real-world applications, such as package delivery, search and rescue, and autonomous exploration, the need to improve the efficiency and quality of task and path planning has become increasingly urgent, par
With the rapid development of rehabilitation robotics, there is a pressing need for efficient and accurate gait prediction methods. However, due to the complexity and variability of individual gait characteristics and external disturbances, accurately predicting gait in real time remains a significa
Recent advances in 3D Gaussian Splatting (3DGS) have demonstrated significant potential over traditional rendering techniques, attracting widespread attention from both industry and academia. However, real-time rendering with 3DGS remains a challenging problem, particularly in large-scale, high-reso…
Compression artifacts removal (CAR), an effective post-processing method to reduce compression distortion in edge-side codecs, demonstrates remarkable results by utilizing convolutional neural networks (CNNs) on high computational power cloud side. Traditional image compression reduces redundancy in…
Face aging has become a crucial task in computer vision, with applications ranging from entertainment to healthcare. However, existing methods struggle with achieving a realistic and seamless transformation across the entire lifespan, especially when handling large age gaps or extreme head poses. Th…
Reliable self-localization is a foundational skill for many intelligent mobile platforms. This paper explores the use of event cameras for motion tracking thereby providing a solution with inherent robustness under difficult dynamics and illumination. In order to circumvent the challenge of event ca
While Multimodal Large Language Models (MLLMs) have advanced GUI navigation agents, current approaches face limitations in cross-domain generalization and effective history utilization. We present a reasoning-enhanced framework that systematically integrates structured reasoning, action prediction,…
As the ubiquity of smart mobile devices continues to rise, Optical Camera Communication systems have gained more attention as a solution for efficient and private data streaming. This system utilizes optical cameras to receive data from digital screens via visible light. Despite their promise, most
Text-to-image generation models can create high-quality images from input prompts. However, they struggle to support the consistent generation of identity-preserving requirements for storytelling. Existing approaches to this problem typically require extensive training in large datasets or additiona…
Text-to-Image (T2I) diffusion models have made remarkable advancements in generative modeling; however, they face a trade-off between inference speed and image quality, posing challenges for efficient deployment. Existing distilled T2I models can generate high-fidelity images with fewer sampling ste…
Open-vocabulary Scene Graph Generation (OV-SGG) overcomes the limitations of the closed-set assumption by aligning visual relationship representations with open-vocabulary textual representations. This enables the identification of novel visual relationships, making it applicable to real-world scena…
Deep neural networks are vulnerable to adversarial examples which fool model predictions by adding imperceptible perturbations to natural examples. Adversarial training is effective in defending against adversarial attacks but faces a challenge with long-tailed data, where the over-compression of ta…
We present VQTalker, a Vector Quantization-based framework for multilingual talking head generation that addresses the challenges of lip synchronization and natural motion across diverse languages. Our approach is grounded in the phonetic principle that human speech comprises a finite set of distinc…
Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Give…
Generating high-quality and person-generic visual dubbing remains a challenge. Recent innovation has seen the advent of a two-stage paradigm, decoupling the rendering and lip synchronization process facilitated by intermediate representation as a conduit. Still, previous methodologies rely on rough…
Event cameras are an interesting visual exteroceptive sensor that reacts to brightness changes rather than integrating absolute image intensities. Owing to this design, the sensor exhibits strong performance in situations of challenging dynamics and illumination conditions. While event-based simulta…
One of the main drawback of diffusion models is the slow inference time for image generation. Among the most successful approaches to addressing this problem are distillation methods. However, these methods require considerable computational resources. In this paper, we take another approach to diff…
The human foot arch plays a significant role in bearing weight, keeping balance, and walking efficiently. In this study, we present a pneumatic arch support insole (PASI) and a foot arch stiffness-based dynamic plantar support control to reduce the metabolic cost of walking. We first obtain the foot…
Legged robots have demonstrated high efficiency and effectiveness in unstructured and dynamic environments. However, it is still challenging for legged robots to achieve rapid and efficient locomotion on deformable, yielding substrates, such as granular terrains. We present an enhanced resistive for…
It is especially challenging to achieve real-time human motion tracking on a standalone VR Head-Mounted Display (HMD) such as Meta Quest and PICO. In this paper we propose HMD-Poser the first unified approach to recover full-body motions using scalable sparse observations from HMD and body-worn IMUs…
This letter proposes a novel mechanical structure for traditional articulated-legged robots that uses a linkage-based approach and hydrostatic transmission to reduce the joint load caused by gravity. The wide application of legged robots is limited by their weight-bearing capacity and low energy eff
"With the development of neural radiance fields and generative models, numerous methods have been proposed for learning 3D human generation from 2D images. These methods allow control over the pose of the generated 3D human and enable rendering from different viewpoints. However, none of these metho…
"This work aims to generate natural and diverse group motions of multiple humans from textual descriptions. While single-person text-to-motion generation is extensively studied, it remains challenging to synthesize motions for more than one or two subjects from in-the-wild prompts, mainly due to the…
Audio-driven talking face has attracted broad interest from academia and industry recently. However, data acquisition and labeling in audio-driven talking face are labor-intensive and costly. The lack of data resource results in poor synthesis effect. To alleviate this issue, we propose to use TTS (…
This paper presents the design and implementation of our system for Track 1 of the Multi-modal Information based Speech Processing (MISP) 2022 Challenge. We design an end-to-end transformer-based multi-talker system. The transformer backbone is well-suited to capture long-term features, which is cru…
We study robust reinforcement learning (RL) with the goal of determining a well-performing policy that is robust against model mismatch between the training simulator and the testing environment. Previous policy-based robust RL algorithms mainly focus on the tabular setting under uncertainty sets th…
The marriage of Graph Convolutional Network (GCN) and Homomorphic Encryption (HE) enables the inference of graph data on the cloud with significantly enhanced client data privacy. However, the tremendous computation and memory overhead associated with HE operations challenges the practicality of HE-…
This work studies an independent natural policy gradient (NPG) algorithm for the multi-agent reinforcement learning problem in Markov potential games. It is shown that, under mild technical assumptions and the introduction of the \textit{suboptimality gap}, the independent NPG method with an oracle…
Real-world single image denoising is crucial and practical in computer vision. Bayesian inversions combined with score priors now have proven effective for single image denoising but are limited to white Gaussian noise. Moreover, applying existing score-based methods for real-world denoising require…
Homomorphic Encryption (HE) is a promising technology to protect clients' data privacy for Machine Learning as a Service (MLaaS) on public clouds. However, HE operations can be orders of magnitude slower than their counterparts for plaintexts and thus result in prohibitively high inference latency,…
Recently deep learning techniques have significantly advanced image super-resolution (SR). Due to the black-box nature, quantifying reconstruction uncertainty is crucial when employing these deep SR networks. Previous approaches for SR uncertainty estimation mostly focus on capturing pixel-wise unce…
We study policy optimization for Markov decision processes (MDPs) with multiple reward value functions, which are to be jointly optimized according to given criteria such as proportional fairness (smooth concave scalarization), hard constraints (constrained MDP), and max-min trade-off. We propose an…
We present Falconn++, a novel locality-sensitive filtering (LSF) approach for approximate nearest neighbor search on angular distance. Falconn++ can filter out potential far away points in any hash bucket before querying, which results in higher quality candidates compared to other hashing-based so…
Motivated by the problem of learning with small sample sizes, this paper shows how to incorporate into support-vector machines (SVMs) those properties that have made convolutional neural networks (CNNs) successful. Particularly important is the ability to incorporate domain knowledge of invariances,…
Load-carrying capability is an essential criterion in legged robots' practical application. This paper proposes an unpowered hydraulic auxiliary system to improve the legged robot's loading capability and energy efficiency. For humans, it has been widely hypothesized that intra-abdominal pressure ca…
To fulfill the need for reliable and consistent medical training of the neurological examination technique to assess ankle clonus, a series elastic actuator (SEA) based haptic training simulator was proposed and developed. The simulator's mechanism (a hybrid of belt and linkage drive) and controller
We address the issue of safety in reinforcement learning. We pose the problem in an episodic framework of a constrained Markov decision process. Existing results have shown that it is possible to achieve a reward regret of $\tilde{\mathcal{O}}(\sqrt{K})$ while allowing an $\tilde{\mathcal{O}}(\sqrt{…
Real-time lower limbs motion or gait measurement is an important part in human-robotic interaction for the control of robotic walkers and rehabilitation devices. Laser range finder or infrared sensor that is mounted on the device has been widely used in applications. Although these sensors can provi…
It is inevitable for human to bear the gravitational and inertial force when carrying loads. The impact force exerted on human body is originated from the inertial force which can increase the energy expenditure and cause injury to human body. This paper proposes a semi-active hover backpack with co…
Egocentric action anticipation aims at predicting the near future based on past observation in first-person vision. While future actions may be wrongly predicted due to the dataset bias, we present a counterfactual analysis framework for egocentric action anticipation (CA-EAA) to enhance the capacit…
Sentence matching aims to identify the special relationship between two sentences, and plays a key role in many natural language processing tasks. However, previous studies mainly focused on exploiting either syntactic or semantic information for sentence matching, and no studies consider integratin…
Scene text image contains two levels of contents: visual texture and semantic information. Although the previous scene text recognition methods have made great progress over the past few years, the research on mining semantic information to assist text recognition attracts less attention, only RNN-l…
Automatic gait measurement and analysis is an enabling tool for intelligent healthcare and robotics-assisted rehabilitation. This letter proposes a novel two shank-mounted inertial measurement units (IMU)-based method on gait analysis and classification for three different neurological diseases. The
Image compression-based approaches for defending against the adversarial-example attacks, which threaten the safety use of deep neural networks (DNN), have been investigated recently. However, prior works mainly rely on directly tuning parameters like compression rate, to blindly reduce image featur…
Cloud based medical image analysis has become popular recently due to the high computation complexities of various deep neural network (DNN) based frameworks and the increasingly large volume of medical images that need to be processed. It has been demonstrated that for medical images the transmissi…
This letter presents a novel robotic mechanism inspired by origami and its fabrication method using three-dimensional (3D) printing. The selected twisted tower design shows unique structural and geometrical properties that enable bending and linear motions, and therefore, can be suitable for various
We present trajectory tracking and balance control of an autonomous bikebot. The bikebot is a single-track autonomous mobile robot that is designed to study unstable physical human-robot interactions. The controller is built on the property of the external-internal convertible (EIC) structure for th…
Slip is the major cause of falls in human locomotion. We present a new bipedal modeling approach to capture and predict human walking locomotion with slips. Compared with the existing bipedal models, the proposed slip walking model includes the human foot rolling effects, the existence of the double…