18 accepted papers
Recent advances in Vision-Language Models (VLMs) and large language models (LLMs) have greatly enhanced visual reasoning, a key capability for embodied AI agents like robots. However, existing visual reasoning benchmarks often suffer from several limitations: they lack a clear definition of reasonin
Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to the downstream tasks. However, most existing approaches rely on conventional TopK routing, which requires careful hyperp…
Learning to cooperate in distributed partially observable environments with no communication abilities poses significant challenges for multi-agent deep reinforcement learning (MARL). This paper addresses key concerns in this domain, focusing on inferring state representations from individual agent…
Soft manipulators (SMs) have shown great potential for interactive tasks in confined environments. However, avoiding obstacles of SMs may conflict with the manipulator’s configuration, the planned trajectory for tracking control, and the target position for grasping. To coordinate configuration plan
Despite their impressive capacities, Large language models (LLMs) often struggle with the hallucination issue of generating inaccurate or fabricated content even when they possess correct knowledge. In this paper, we extend the exploration of the correlation between hidden-state prediction changes a…
Advancements in deep multi-agent reinforcement learning (MARL) have positioned it as a promising approach for decision-making in cooperative games. However, it still remains challenging for MARL agents to learn cooperative strategies for some game environments. Recently, large language models (LLMs)
Although soft manipulators are endowed with compliance and flexibility, most control strategies focus on end-effector control and lack shape control ability. This letter aims to design a shape controller for the soft manipulator. Firstly, we establish a modified forward kinematics model (FKM) based
Distributionally Robust Optimization (DRO) accounts for uncertainty in data distributions by optimizing the model performance against the worst possible distribution within an ambiguity set. In this paper, we propose a DRO framework that relies on a new distance inspired by Unbalanced Optimal Transp…
Tactile object recognition is vital for robotic handling systems; however, existing technologies that concentrate on tactile sensors with high modulus are not suitable for soft grippers to classify deformable objects. In this letter, we integrated an indenter layer into the traditional microfluidic
Emotion recognition in conversation (ERC) aims to detect the emotion label for each utterance. Motivated by recent studies which have proven that feeding training examples in a meaningful order rather than considering them randomly can boost the performance of models, we propose an ERC-oriented hyb…
We consider an online stochastic game with risk-averse agents whose goal is to learn optimal decisions that minimize the risk of incurring significantly high costs. Specifically, we use the Conditional Value at Risk (CVaR) as a risk measure that the agents can estimate using bandit feedback in the f…
Perception and portability are critical issues for wearable gloves in hand assistive engineering. However, available wearable gloves either lack flexible sensing or are bulky. In this paper, we present a tendon-driven lightweight wearable glove with soft joint sensing, Sen-Glove. Sen-Glove is equipp…
Aspect-based sentiment analysis (ABSA) tasks aim to extract sentiment tuples from a sentence. Recent generative methods such as Seq2Seq models have achieved good performance by formulating the output as a sequence of sentiment tuples. However, the orders between the sentiment tuples do not naturally…
Aspect based sentiment analysis (ABSA) involves three fundamental subtasks: aspect term extraction, opinion term extraction, and aspect-level sentiment classification. Early works only focused on solving one of these subtasks individually. Some recent work focused on solving a combination of two sub…
Predicting the future behavior of moving agents is essential for real world applications. It is challenging as the intent of the agent and the corresponding behavior is unknown and intrinsically multimodal. Our key insight is that for prediction within a moderate time horizon, the future modes can b
Behavior prediction in dynamic, multi-agent systems is an important problem in the context of self-driving cars, due to the complex representations and interactions of road components, including moving agents (e.g. pedestrians and vehicles) and road context information (e.g. lanes, traffic lights).…
In this paper, we study the cooperative path planning and motion coordination problems of the multi-robot system with large number of robots, aiming for practical applications in robotic warehouses and automated transportation systems. Particularly, we solve the life-long planning problem and guaran…
Many speech enhancement algorithms have been proposed over the years and it has been shown that deep neural networks can lead to significant improvements. These algorithms, however, have not been validated for hearing-impaired listeners. Additionally, these algorithms are often evaluated under a lim…