43 accepted papers
Open-set text classification (OSTC) requires models to correctly classify in-distribution (ID) samples while reliably rejecting out-of-distribution (OOD) inputs—an essential capability for real-world NLP systems. Most OSTC methods train on ID data under the closed assumption that all outputs belong…
The endurance and energy efficiency of drones remain critical challenges in their design and operation. To extend mission duration, numerous studies explored perching mechanisms that enable drones to conserve energy by temporarily suspending flight. This paper presents a new perching drone that util…
As multimodal LLM-driven agents advance in autonomy and generalization, traditional static datasets face inherent scalability limitations and are insufficient for fully assessing their capabilities in increasingly complex and diverse tasks. Existing studies have attempted to generate agent tasks usi
While continual visual instruction tuning (CVIT) has shown promise in adapting multimodal large language models (MLLMs), existing studies predominantly focus on models without safety alignment. This critical oversight ignores the fact that real-world MLLMs inherently require such mechanisms to mitig
Low-Light Image Enhancement (LLIE) has long been a challenging problem in low-level vision, as insufficient illumination often leads to low contrast, detail loss, and noise. Recent studies show that deep learning-based Retinex theory can effectively decouple illumination and reflectance. However, ex
Continual Visual Instruction Tuning (CVIT) enables Multimodal Large Language Models (MLLMs) to incrementally learn new tasks over time. However, this process is challenged by catastrophic forgetting, where performance on previously learned tasks deteriorates as the model adapts to new ones. A common
Mixture-of-Experts (MoE) language models dramatically expand model capacity and achieve remarkable performance without increasing per-token compute. However, can MoEs surpass dense architectures under strictly equal resource constraints — that is, when the total parameter count, training compute, an…
Vision-language-action (VLA) models unify perception, language, and control for embodied agents but face significant challenges in practical deployment due to rapidly increasing compute and memory demands, especially as models scale to longer horizons and larger backbones. To address these bottlenec
Reward modeling is essential for aligning large language models with human preferences through reinforcement learning. To provide accurate reward signals, a reward model (RM) should stimulate deep thinking and conduct interpretable reasoning before assigning a score or a judgment. Inspired by recent…
Visual Place Recognition (VPR) based on Dynamic Vision Sensors (DVSs) has gained attention due to their high temporal resolution and robustness under challenging lighting conditions. However, the sparse and asynchronous event stream output of DVS introduces unique challenges for effective VPR. In th…
Position bias has proven to be a prevalent issue of modern language models (LMs), where the models prioritize content based on its position within the given context. This bias often leads to unexpected model failures and hurts performance, robustness, and reliability across various applications. A s…
First-order logic (FOL) is often used to represent logical entailment, but determining natural language (NL) entailment using FOL remains a challenge. To address this, we propose the Entailment-Preserving FOL representations (EPF) task and introduce reference-free evaluation metrics for EPF (Entailm…
Large Language Models (LLMs) have revolutionized artificial intelligence with capabilities in reasoning, coding, and communication, driving innovation across industries. Their true potential depends on effective alignment to ensure correct, trustworthy and ethical behavior, addressing challenges lik…
Traditional continuous deep reinforcement learning (RL) algorithms employ deterministic or unimodal Gaussian actors, which cannot express complex multimodal decision distributions. This limitation can hinder their performance in diversity-critical scenarios. There have been some attempts to design o…
Image fusion, a fundamental low-level vision task, aims to integrate multiple image sequences into a single output while preserving as much information as possible from the input. However, existing methods face several significant limitations: 1) requiring task- or dataset-specific models; 2) neglec…
Given the high computational cost of preference alignment training of large language models (LLMs), exploring efficient methods to reduce the training overhead remains an important and compelling research problem. Motivated by the observation that alignment training typically involves only small par…
Transcatheter tricuspid valve replacement (TTVR) has emerged as a promising minimally invasive procedure for treating severe tricuspid regurgitation (TR). However, accurate catheter delivery remains a significant challenge, primarily due to the reliance on 2D vision feedback, complex catheter kinema
When performing total hip replacement (THR) surgery, high-quality preparation of acetabulum is critical as it contributes to the patient’s recovery speed and the consistency of bone ingrowth. Conventionally, surgeons prepare the acetabulum manually by reaming it with a handheld electric drill and a
Visual instruction tuning (VIT) enables multimodal large language models (MLLMs) to effectively handle a wide range of vision tasks by framing them as language-based instructions. Building on this, continual visual instruction tuning (CVIT) extends the capability of MLLMs to incrementally learn new…
Visual object tracking has gained promising progress in past decades. Most of the existing approaches focus on learning target representation in well-conditioned daytime data, while for the unconstrained real-world scenarios with adverse weather conditions, e.g. nighttime or foggy environment, the t…
Exoskeleton technology holds significant promise within the human-centric paradigm of Industry 5.0 for mitigating work-related musculoskeletal disorders (WMSDs). However, existing systems often struggle with mismatched assistive torque and inefficient human-machine collaboration under dynamic loadin
In the current environment, psychological issues are prevalent and widespread, with social media serving as a key outlet for individuals to share their feelings. This results in the generation of vast quantities of data daily, where negative emotions have the potential to precipitate crisis situatio…
The Rating Scale method has been long deemed the standard for measuring subjective perceptions. However, in the field of physical human-robot collaboration (pHRC), its aptness should be put under scrutiny due to inherent challenges such as response bias, between-subject variations, and the granulari…
Quantization for model compression can efficiently reduce the network complexity and storage requirement but the original training data is necessary to remedy the performance loss caused by quantization. The Data-Free Quantization (DFQ) methods have been proposed to handle the absence of original tr…
Previous research has shown that load-bearing with elastic suspension backpacks improves human biomechanics and reduces human energy expenditure. Constant-force suspension backpacks (CFSB) with zero stiffness were developed to minimize the inertial force of loads. However, there is a mismatch betwee
Large Language Models (LLMs) have demonstrated remarkable capabilities in open-ended text generation tasks. However, the inherent open-ended nature of these tasks implies that there is always room for improvement in the quality of model responses. To address this challenge, various approaches have b…
Mobile physical human-robot collaboration (pHRC) using collaborative robots (cobots) and mobile robots has attracted much research attention. Many researchers have focused on improving the control performance to comply with human intentions. However, a problem that generally exists with mobile pHRC…
Localization is a critical technology for various applications ranging from navigation and surveillance to assisted living. Localization systems typically fuse information from sensors viewing the scene from different perspectives to estimate the target location while also employing multiple modalit…
Multimodal Named Entity Recognition and Grounding (MNERG) aims to extract paired textual and visual entities from texts and images. It has been well explored through a two-step paradigm: initially identifying potential visual entities using object detection methods and then aligning the extracted te…
Preference-based optimizing methods have shown their advantages and potential in exploring individual, comfortable, and effective control strategies and assistance parameters of exoskeletons during locomotion. Research indicates that compared with naive wearers, knowledgeable wearers with abundant e…
This paper studies the theoretical framework of the alignment process of generative models with Reinforcement Learning from Human Feedback (RLHF). We consider a standard mathematical formulation, the reverse-KL regularized contextual bandit for RLHF. Despite its widespread practical application, a r…
Deep reinforcement learning has recently been successfully applied to online procedural content generation in which a policy determines promising game-level segments. However, existing methods can hardly discover diverse level patterns, while the lack of diversity makes the gameplay boring. This pa…
Instruction tuning enhances the instruction following ability of large language models by finetuning with supervised instruction data. Previous work proposes in-context instruction tuning (ICIT) where specific positive or negative examples are incorporated into the prompt for better performance. In…
Research has indicated that exoskeletons can assist human movement, but due to the influence of additional weight and challenges in control strategy design, only a few exoskeletons effectively reduce the wearers’ metabolic costs during running. This paper proposes an innovative and efficient hip-ass…
Knowledge distillation is one of the primary methods of transferring knowledge from large to small models. However, it requires massive task-specific data, which may not be plausible in many real-world applications. Data augmentation methods such as representation interpolation, token replacement, o…
Visual object tracking has seen significant progress in recent years. However, the vast majority of this work focuses on tracking objects within the image plane of a single camera and ignores the uncertainty associated with predicted object locations. In this work, we focus on the geospatial object…
Due to the limited resolution of 3D sensors and the inevitable mutual occlusion between objects, 3D scans of real scenes are commonly incomplete. Previous scene completion methods struggle to capture long-range spatial feature, resulting in unsatisfactory completion results. To alleviate the pro…
High-dimensional expensive problems are often encountered in the design and optimization of complex robotic and automated systems and distributed computing systems, and they suffer from a time-consuming fitness evaluation process. It is extremely challenging and difficult to produce promising soluti…
Evolutionary algorithms are commonly used to solve many complex optimization problems in such fields as robotics, industrial automation, and complex system design. Yet, their performance is limited when dealing with high-dimensional complex problems because they often require enormous computational…
We illustrate the detrimental effect, such as overconfident decisions, that exponential behavior can have in methods like classical LDA and logistic regression. We then show how polynomiality can remedy the situation. This, among others, leads purposefully to random-level performance in the tails, a…
We present a meta-learning framework for learning new visual concepts quickly, from just one or a few examples, guided by multiple naturally occurring data streams: simultaneously looking at images, reading sentences that describe the objects in the scene, and interpreting supplemental sentences tha…
We introduce RESIN-11, a new schema-guided event extraction&prediction framework that can be applied to a large variety of newsworthy scenarios. The framework consists of two parts: (1) an open-domain end-to-end multimedia multilingual information extraction system with weak-supervision and zero-sho…
Event extraction (EE) has considerably benefited from pre-trained language models (PLMs) by fine-tuning. However, existing pre-training methods have not involved modeling event characteristics, resulting in the developed EE models cannot take full advantage of large-scale unsupervised data. To this…