34 accepted papers
In modern human-robot collaboration (HRC) applications, multiple perception modules jointly extract visual, auditory, and contextual cues to achieve comprehensive scene understanding, enabling the robot to provide appropriate assistance to human agents intelligently. While executing multiple percept…
Inspired by the human ability to selectively focus on relevant information, this paper introduces relevance, a novel dimensionality reduction process that enables robots to identify relevant scene elements in a scene and generate responses that are seamless, fast, and accurate. To accurately and eff…
Vision-Language-Action (VLA) models have become a central paradigm for embodied intelligence. However, most existing approaches are built on large-scale Transformers, resulting in substantial inference latency and energy consumption that limit their practical deployment in low-power, real-time scena…
Large language models (LLMs) have achieved remarkable success across diverse applications but remain vulnerable to jailbreak attacks, where attackers craft prompts that bypass safety alignment and elicit unsafe responses. Among existing approaches, optimization-based attacks have shown strong effect…
With the continuously expanding parameters, efficiently adapting large language models to downstream tasks is crucial in resource-limited conditions. Many parameter-efficient fine-tuning methods have emerged to address this challenge. However, they lack flexibility, like LoRA requires manually selec…
Black-box adversarial attack on vision-language pre-trained models is a practical and challenging task, as text and image perturbations need to be considered simultaneously, and only the predicted results are accessible. Research on this problem is in its infancy, and only a handful of methods are a…
Traditional unsupervised clustering methods, which often rely on contrastive training of embedders, suffer from a lack of label knowledge, resulting in suboptimal performance. Furthermore, the presence of potential false negatives can destabilize the training process. Hence, we propose to improve cl
Multi-label few-shot image classification is a crucial and challenging task due to limited annotated data and elusive category specificity. However, research on this topic is still in the rudimentary stage and few methods are available. Existing methods either leverage data augmentation to alleviate…
Most current image captioning models rely on the autoregressive approach, which unfortunately results in significant inference delays that hinder their practical use. In contrast, non-autoregressive methods show promising potential for increasing inference speeds. However, there is often a performan…
Generalized zero-shot intent detection (GZID) aims to recognize the labels of utterances from both seen and unseen intents by utilizing the knowledge learned from seen intents. Enhancing the generalization ability from seen intents to unseen intents is a key challenge in the GZID setting. Existing m…
Human brain possesses the ability to effectively focus on important environmental components, which enhances perception, learning, reasoning, and decision-making. Inspired by this cognitive mechanism, we introduced a novel concept termed relevance for Human-Robot Collaboration (HRC). Relevance is a
Multi-label document classification (MLDC) aims to allocate more than one label to each document and attracts increasing attention in many practical applications. However, previous studies have failed to pay sufficient attention to the lack of semantic information on labels and the long-tail problem…
Graph data augmentation proves to be an effective approach for enhancing the performance of graph classification. However, due to the complex structure of graphs, the semantic meanings of graphs are sensitive to minor modifications, while the labels of augmented graphs remain identical, thus limitin…
Few-shot intent detection is a challenging task, particularly in scenarios involving multiple labels and diverse domains. This paper presents a novel prototype learning approach that combines the label synset augmentation and the coarse-to-fine prototype distillation for multi-label few-shot intent…
Multi-goal conversational recommender system (MG-CRS) which is more in line with realistic scenarios has attracted a lot of attention. MG-CRS can dynamically capture the demands of users in conversation, continuously engage their interests, and make recommendations. The key of accomplishing these ta…
Catastrophic forgetting has become an intractable problem in the continual learning setting because previous data is not accessible when training. To mitigate this problem, memory-based continual learning methods replay previous data from a fixed-size memory buffer. Reservoir sampling, which can sam…
This letter focuses on the multiple nonholonomic robots motion planning (MRMP) problem in congested and complex environments, where the complexity escalates dramatically with the increase in the number of robots, frequently leading to deadlocks. We present the <italic xmlns:mml="http://www.w3.org/19
Depression detection is a challenging and crucial task in psychological illness diagnosis. Utilizing online user posts to predict whether a user suffers from depression seems an effective and promising direction. However, existing methods suffer from either poor interpretability brought by the black…
Perception plays a pivotal role in enhancing the functionality of autonomous agents. However, the intricate relationship between robotic perception metrics and actuation metrics remains unclear, leading to ambiguity in the development and fine-tuning of perception algorithms. In this paper, we intro…
Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen classes to unseen classes, they are still limited by (1) In…
New intent discovery aims to identify new intents from unlabeled utterances in the open-world scenario. As the fundamental and challenging problem in dialogue systems, new intent discovery attracts increasing attention but is still under exploration. In this paper, we propose a simple and effective…
Accurate and real-time location tracking is vital for various applications in public safety and the military, particularly in search and rescue missions. Traditional filtering localization algorithms are more effective in linear environments and require precise initial estimates and system noise for…
Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficie…
Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred across different tasks in computer vision domain. However, directly applying this ap…
Velocity planning is an important module of autonomous driving, which aims to generate the velocity profile given a reference path. However, most existing algorithms fail to adequately address the uncertainty inherent in driving contexts, leading to potentially risky situations. To this end, we prop
Black-box hard-label adversarial attack on text is a practical and challenging task, as the text data space is inherently discrete and non-differentiable, and only the predicted label is accessible. Research on this problem is still in the embryonic stage and only a few methods are available. Nevert…
Emotion recognition in conversation (ERC) enables a deeper understanding of emotion for each utterance within a conversation. Recent progress on ERC has proved that using Graph Neural Networks (GNN) to model conversational context is effective for identifying emotions. However, existing GNN-based ap…
Hard-label textual adversarial attack is a challenging task, as only the predicted label information is available, and the text space is discrete and non-differentiable. Relevant research work is still in fancy and just a handful of methods are proposed. However, existing methods suffer from either…
A class-incremental learning agent learns online with a neverending stream of data in one training epoch. In this setting, the agent suffers from severe catastrophic forgetting due to the absence of data from the observed classes after learning data from new classes. Besides, the prototypes rapidly…
This paper focuses on problems associated with the deployment of automatic agents for last-mile delivery. We propose a framework and methodology to systematically evaluate and compare different hybrid strategies. Performance metrics in agent noise, delivery time, energy consumption, coverage rate, p…
Intent classification (IC) and slot filling (SF) are critical building blocks in task-oriented dialogue systems. These two tasks are closely-related and can flourish each other. Since only a few utterances can be utilized for identifying fast-emerging new intents and slots, data scarcity issue often…
Existing deep graph clustering methods usually rely on neural language models to learn graph embeddings. However, these methods either ignore node feature information or fail to learn cluster-oriented graph embeddings. In this paper, we propose a novel deep graph clustering framework to tackle these…
Sufficient real information in generator is a critical point for the generation ability of GAN. However, GAN and its variants suffer from lack of this point, resulting in brittle training processes. In this paper, we propose a novel variant of GAN, Posterior Promoted GAN (P2GAN), which promotes gene…
Graph-based methods have been demonstrated as one of the most effective approaches for semi-supervised learning, as they can exploit the connectivity patterns between labeled and unlabeled data samples to improve learning performance. However, existing graph-based methods either are limited in their…