21 accepted papers
Group-based reinforcement learning (RL), such as GRPO, has advanced the capabilities of large language models on long-horizon agentic tasks. To enable more fine-grained policy updates, recent research has increasingly shifted toward stepwise group-based policy optimization, which treats each step in…
General SVG modeling remains challenging due to fragmented datasets, limited transferability of methods across tasks, and the difficulty of handling structural complexity. In response, we leverage the strong transfer and generalization capabilities of multimodal large language models (MLLMs) to achi…
Recent benchmarks and datasets have been proposed to improve spatial reasoning in vision-language models (VLMs), yet existing open resources remain limited in scale, visual diversity, and instruction expressiveness. In this work, we introduce InternSpatial, the largest open-source dataset for spatia…
In order to provide natural and immersive interactive experience for teleoperation in the context of human-robot collaboration and interaction, this work introduces a natural human-robot interaction system for teleoperation based on ultrasonic haptic feedback. Specifically, our system can accurately
Backdoor attacks have posed a serious threat in machine learning models, wherein adversaries can poison training samples with maliciously crafted triggers to compromise the victim model. Advanced backdoor attack methods have focused on selectively poisoning more vulnerable training samples, achievin…
Model merging aims to achieve multitask performance by merging multiple expert models without the need to access the raw training data. Recent research identified the \textit{representation bias} of model merging, characterized by a discrepancy in the representation distribution between the merged a…
In order to obtain a good tactile sensing, traditional dexterous hands always enable all the sensing units installed on them all the time, even if just a few sensor units are actually used, which make the tactile sensing system resource-wasting and energy consuming. In order to reduce their complexi
While multimodal contrastive learning methods (e.g., CLIP) can achieve impressive zero-shot classification performance, recent research has revealed that these methods are vulnerable to backdoor attacks. To defend against backdoor attacks on CLIP, existing defense methods focus on either the pre-tra…
Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs exhibit low zero-shot performance in downstream tasks. To al…
The prevalence of ineffective corrective surgeries for ocular motor disorders calls for a robotic eye platform in aiding ophthalmologists to better understand the biomechanisms of human eye movement. This letter presents the first hardware design and implementation of a 2-DOF robotic eye driven by s
Learning with noisy labels (LNL) aims to ensure model generalization given a label-corrupted training set. In this work, we investigate a rarely studied scenario of LNL on fine-grained datasets (LNL-FG), which is more practical and challenging as large inter-class ambiguities among fine-grained clas…
Ocular mobility disorders such as strabismus af-fect millions of people. Patients' descriptions of their symptoms, such as what they see and how their vision has changed, are important for ophthalmologists to diagnose, monitor pro-gression, and evaluate treatment effectiveness. However, such verbal…
As the focus on highly intelligent robots continues, a problem that cannot be ignored has emerged: resource con-straints. Considering the game problem of resource limitation and the level of intelligence, we focus on lightweight intelligence. This work is a further refinement of our previous work, a…
"Sample selection is an effective strategy to mitigate the effect of label noise in robust learning. Typical strategies commonly apply the small-loss criterion to identify clean samples. However, those samples lying around the decision boundary with large losses usually entangle with noisy examples,…
Feature extraction plays an important role in visual localization. Unreliable features on dynamic objects or repetitive regions will interfere with feature matching and challenge indoor localization greatly. To address the problem, we propose a novel network, RaP-Net, to simultaneously predict regio…
A robust and efficient Simultaneous Localization and Mapping (SLAM) system is essential for robot autonomy. For visual SLAM algorithms, though the theoretical framework has been well established for most aspects, feature extraction and association is still empirically designed in most cases, and can…
Approximate computing has drawn considerable attention to both academia and industry in the area of DNN hardware. Despite substantial efforts to design approximate circuits and building blocks, the resilience of DNN layers and structures remains an untapped field to explore. This paper presents an e…
Simultaneous Localization and Mapping (SLAM) is considered to be a fundamental capability for intelligent mobile robots. Over the past decades, many impressed SLAM systems have been developed and achieved good performance under certain circumstances. However, some problems are still not well solved,…
We propose a new method that uses deep learning techniques to accelerate the popular alternating direction method of multipliers (ADMM) solution for inverse problems. The ADMM updates consist of a proximity operator, a least squares regression that includes a big matrix inversion, and an explicit so…
This paper proposes a robust fusion-based strategy to detect changes between two multi-band optical images with different spatial and spectral resolutions, e.g., a multispectral high spatial resolution image and a hyperspectral low spatial resolution image. The dissimilarity between sensor resolutio…
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…