51 accepted papers
Layer dropout (a.k.a.\ stochastic depth) has been shown to enable faster training, higher accuracy, and robustness to zero-shot layer pruning in both language and vision transformers. However, as models and datasets have scaled, dropout---particularly layer dropout---has largely disappeared from LLM…
Parameter sharing is a central design choice in cooperative multi-agent reinforcement learning, yet it fundamentally conflicts with the need for role specialization in heterogeneous cooperative environments. Existing role-based methods typically learn monolithic role representations, which often suf
Verifying the complex and multi-step reasoning of Large Language Models (LLMs) is a critical challenge, as holistic methods often overlook localized flaws. Step-by-step validation is a promising alternative, yet existing methods are often rigid. They struggle to adapt to diverse reasoning structur
The lactation performance of Saanen dairy goats, renowned for their high milk yield, is intrinsically linked to their body size, making accurate 3D body measurement essential for assessing milk production potential, yet existing reconstruction methods lack goat-specific authentic 3D data. To address
Offline reinforcement learning enables policy learning solely from fixed datasets, without costly or risky environment interactions, making it highly valuable for real-world applications. While Transformer-based approaches have recently demonstrated strong sequence modeling capabilities, they typica…
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…
Privacy-preserving Transformer inference has gained attention due to the potential leakage of private information. Despite recent progress, existing frameworks still fall short of practical model scales, with gaps up to a hundredfold. A possible way to close this gap is the Mixture of Experts (MoE)
Three-dimensional scene reconstruction from sparse-view satellite images is a long-standing and challenging task. While 3D Gaussian Splatting (3DGS) and its variants have recently attracted attention for its high efficiency, existing methods remain unsuitable for satellite images due to incompatibil
The branch-and-bound (B\&B) method is a dominant exact algorithm for solving Mixed-Integer Linear Programming problems (MILPs). While recent deep learning approaches have shown promise in learning branching policies using instance-independent features, they often struggle to capture the sequential d…
With growing real-world demands, efficient tracking has received increasing attention. However, most existing methods are limited to RGB inputs and struggle in multi-modal scenarios. Moreover, current multi-modal tracking approaches typically use complex designs, making them too heavy and slow for r
Stock trend prediction involves forecasting the future price movements by analyzing historical data and various market indicators. With the advancement of machine learning, graph neural networks (GNNs) have been extensively employed in stock prediction due to their powerful capability to capture spa…
In recent years, Neural Radiance Fields (NeRF) has revolutionized three-dimensional (3D) reconstruction with its implicit representation. Building upon NeRF, 3D Gaussian Splatting (3D-GS) has departed from the implicit representation of neural networks and instead directly represents scenes as point
The simple and modular structure of cable-driven parallel robots (CDPRs) can enable effective real-time reconfiguration. In this paper, an online reconfiguration strategy is proposed for a 3-DOF point-mass CDPR to adjust the cable anchor positions and enhance its performance in physical human-robot
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
A key challenge in multi-agent collaborative tasks is reducing uncertainty about teammates to enhance cooperative performance. Explicit communication methods can reduce uncertainty about teammates, but the associated high communication costs limit their practicality. Alternatively, implicit consensu…
Low stiffness in 7-DOF cable-driven humanoid manipulators limits their precision, posing a significant challenge in complex human-robot interaction (HRI) scenarios. This paper presents a motion planning framework to enhance manipulator stiffness for both single and dual-arm configurations. For a sin
The Spiking Neural Network (SNN) has drawn increasing attention for its energy-efficient, event-driven processing and biological plausibility. To train SNNs via backpropagation, surrogate gradients are used to approximate the non-differentiable spike function, but they only maintain nonzero derivati
3D Gaussian Splatting (3DGS) has shown impressive performance in scene reconstruction, offering high rendering quality and rapid rendering speed with short training time. However, it often yields unsatisfactory results when applied to indoor scenes due to its poor ability to learn geometries without…
One of the primary challenges in optimizing large language models (LLMs) for long-context inference lies in the high memory consumption of the Key-Value (KV) cache. Existing approaches, such as quantization, have demonstrated promising results in reducing memory usage. However, current quantization…
Open-domain timeline summarization (TLS) faces challenges from information overload and data sparsity when processing large-scale textual streams. Existing methods struggle to capture coherent event narratives due to fragmented descriptions and often accumulate noise through iterative retrieval stra
Enabling object detectors to recognize out-of-distribution (OOD) objects is vital for building reliable systems. A primary obstacle stems from the fact that models frequently do not receive supervisory signals from unfamiliar data, leading to overly confident predictions regarding OOD objects. Despi…
Generalizing multi-agent reinforcement learning (MARL) to accommodate variations in problem configurations remains a critical challenge in real-world applications, where even subtle differences in task setups can cause pre-trained policies to fail. To address this, we propose Context-Aware Identity…
As object detectors are increasingly deployed as black-box cloud services or pre-trained models with restricted access to the original training data, the challenge of zero-shot object-level out-of-distribution (OOD) detection arises. This task becomes crucial in ensuring the reliability of detectors…
Parameter sharing, as an important technique in multi-agent systems, can effectively solve the scalability issue in large-scale agent problems. However, the effectiveness of parameter sharing largely depends on the environment setting. When agents have different identities or tasks, naive parameter…
Electroencephalography (EEG) has proven to be effective in emotion analysis. However, current methods struggle with individual variations, complicating the generalization of models trained on data from source subjects to unseen target subjects. To tackle this issue, we propose the Denoising Mixed Mu…
Correlation filter (CF)-based approaches have gained widespread attention in the field of unmanned aerial vehicle (UAV) visual tracking due to their light-weight characteristics. However, CFs are prone to generating low-quality response in challenging UAV scenarios, e.g., fast motion and background…
In this letter, we propose a novel formation controller for nonholonomic agents to form general parametric curves. First, we derive a unified parametric representation for both open and closed curves. Then, a leader-follower formation controller is designed to drive agents to form the desired parame
This letter presents a new method to automatically transport objects with mobile robots via non-prehensile actions. Our proposed approach utilizes a pair of nonholonomic robots connected by a deformable tube to efficiently manipulate objects of irregular shapes toward target locations. To autonomous
Multistream classification poses significant challenges due to the necessity for rapid adaptation in dynamic streaming processes with concept drift. Despite the growing research outcomes in this area, there has been a notable oversight regarding the temporal dynamic relationships between these strea…
Centralized Training with Decentralized Execution (CTDE) has emerged as a widely adopted paradigm in multi-agent reinforcement learning, emphasizing the utilization of global information for learning an enhanced joint Q-function or centralized critic. In contrast, our investigation delves into harne…
Asynchronous action coordination presents a pervasive challenge in Multi-Agent Systems (MAS), which can be represented as a Stackelberg game (SG). However, the scalability of existing Multi-Agent Reinforcement Learning (MARL) methods based on SG is severely restricted by network architectures or env…
Large Language Models (LLMs) have demonstrated proficiency in addressing tasks that necessitate a combination of task planning and the usage of external tools, such as weather and calculator APIs. However, real-world industrial systems present prevalent challenges in task planning and tool usage: nu…
Task-oriented matching is one of the core aspects of few-shot Action Recognition. Most previous works leverage the metric features within the support and query sets of individual tasks, without considering the metric information across different matching tasks. This oversight represents a significan…
Almost all multi-agent reinforcement learning algorithms without communication follow the principle of centralized training with decentralized execution. During the centralized training, agents can be guided by the same signals, such as the global state. However, agents lack the shared signal and ch…
Five-hundred-meter aperture spherical radio telescope (FAST) is a very famous large-scale scientific facility with excellent performance for astronomical observation in the world, but it currently fails to observe the center of the Milky Way Galaxy due to the limited observation angle that is affect…
Value decomposition methods have gained popularity in the field of cooperative multi-agent reinforcement learning. However, almost all existing methods follow the principle of Individual Global Max (IGM) or its variants, which limits their problem-solving capabilities. To address this, we propose a…
Recently, some challenging tasks in multi-agent systems have been solved by some hierarchical reinforcement learning methods. Inspired by the intra-level and inter-level coordination in the human nervous system, we propose a novel value decomposition framework HAVEN based on hierarchical reinforceme…
In multi-agent reinforcement learning (MARL), self-interested agents attempt to establish equilibrium and achieve coordination depending on game structure. However, existing MARL approaches are mostly bound by the simultaneous actions of all agents in the Markov game (MG) framework, and few works co…
Weather forecasting is one of the cornerstones of meteorological work. In this paper, we present a new benchmark dataset named Weather2K, which aims to make up for the deficiencies of existing weather forecasting datasets in terms of real-time, reliability, and diversity, as well as the key bottlene…
The lightweight design of robots is an important factor in the field of human-robot interaction. Thus, a lightweight 7-DOF cable-driven manipulator is proposed and manufactured, including a shoulder joint with 3-DOF, an elbow joint with 1-DOF, and a wrist joint with 3-DOF. The offset design of the s
Three-dimensional (3D) line segments are helpful for scene reconstruction. Most of the existing 3D-line-segment-reconstruction algorithms deal with two views or dozens of small-size images; while in practice there are usually hundreds or thousands of large-size images. In this paper, we propose an e…
Recently, model-based agents have achieved better performance than model-free ones using the same computational budget and training time in single-agent environments. However, due to the complexity of multi-agent systems, it is tough to learn the model of the environment. The significant compounding…
Zero/few-shot transfer to unseen services is a critical challenge in task-oriented dialogue research. The Schema-Guided Dialogue (SGD) dataset introduced a paradigm for enabling models to support any service in zero-shot through schemas, which describe service APIs to models in natural language. We…
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…
Generally, the existing graph-based multi-view clustering models consists of two steps: (1) graph construction; (2) eigen-decomposition on the graph Laplacian matrix to compute a continuous cluster assignment matrix, followed by a post-processing algorithm to get the discrete one. However, both the…
Superpixel is generated by automatically clustering pixels in an image into hundreds of compact partitions, which is widely used to perceive the object contours for its excellent contour adherence. Although some works use the Convolution Neural Network (CNN) to generate high-quality superpixel, we c…
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…
Cable-driven parallel robots (CDPRs) are robots with novel structures, wherein flexible cables, instead of rigid links, are employed to pull mobile platforms. This structural change enables CDPRs to not only offer potential advantages, but also introduces control challenges with regard to frictional
Deep learning based image denoising methods have been extensively investigated. In this paper, attention mechanism enhanced kernel prediction networks (AME-KPNs) are proposed for burst image denoising, in which, nearly cost-free attention modules are adopted to first refine the feature maps and to f…
Deep neural networks (DNNs) have been applied in class incremental learning, which aims to solve common real-world problems of learning new classes continually. One drawback of standard DNNs is that they are prone to catastrophic forgetting. Knowledge distillation (KD) is a commonly used technique t…
Principal Component Analysis (PCA) is a popular tool for dimension reduction and feature extraction in data analysis. Probabilistic PCA (PPCA) extends the standard PCA by using a probabilistic model. However, both standard PCA and PPCA are not robust, as they are sensitive to outliers. To alleviate…