31 accepted papers
Scaling real robot data is a key bottleneck in imitation learning, leading to the use of auxiliary data for policy training. While other aspects of robotic manipulation such as image or language understanding may be learned from internet-based datasets, acquiring motion knowledge remains challenging…
Zeroth-order optimization is widely used when gradients are unavailable, but the standard two-point estimator suffers from $\mathcal{O}(r^2)$ truncation bias at smoothing radius $r$. Existing bias-reduction schemes typically increase the leading directional variance under a fixed number of function …
Multi-target domain adaptation (MTDA) trains a model using a labeled source domain and several unlabeled target domains, aiming to enhance performance across all targets. However, existing methods lack a principled causal formulation and often rely on empirical domain-invariance enforcement, which c…
Diffusion Language Models (DLMs) have shown strong potential for text generation and are becoming a competitive alternative to autoregressive models. The denoising strategy plays an important role in determining the quality of their outputs. Mainstream denoising strategies include Standard Diffusio…
Open-Set Domain Adaptation (OSDA) aims to transfer knowledge from the labeled source domain to the unlabeled target domain that contains unknown categories, thus facing the challenges of domain shift and unknown category recognition. While recent works have demonstrated the potential of causality fo…
Autonomous driving represents a prominent application of artificial intelligence. Recent approaches have shifted from focusing solely on common scenarios to addressing complex, long-tail situations such as subtle human behaviors, traffic accidents, and non-compliant driving patterns. Given the demon…
Learning 3D parametric shape models of objects has gained popularity in vision and graphics and has showed broad utility in 3D reconstruction, generation, understanding, and simulation. While powerful models exist for humans and animals, equally expressive approaches for modeling plants are lacking.…
Radio map estimation (RME) is crucial for effective planning and optimization of wireless networks. Traditional approaches such as interpolation excel at capturing local smoothness in densely populated data but struggle with sparse or irregular data. Conversely, matrix completion (MC) approaches uti…
Although Multi-Agent Reinforcement Learning (MARL) is effective for complex multi-robot tasks, it suffers from low sample efficiency and requires iterative manual reward tuning. Large Language Models (LLMs) have shown promise in single-robot settings, but their application in multi-robot systems rem
Constructing online High-Definition (HD) maps is crucial for the static environment perception of autonomous driving systems (ADS). Existing solutions typically attempt to detect vectorized HD map elements with unified models; however, these methods often overlook the distinct characteristics of dif…
Multi-task multi-agent reinforcement learning (M T-MARL) has recently gained attention for its potential to enhance MARL's adaptability across multiple tasks. However, it is challenging for existing multi-task learning methods to handle complex problems, as they are unable to handle unrelated tasks
Safe navigation of self-driving cars and robots requires a precise understanding of their environment. Training data for perception systems cannot cover the wide variety of objects that may appear during deployment. Thus, reliable identification of unknown objects, such as wild animals and untypical
Existing sensor-based global localization methods limit the miniaturization potential of magnetically-actuated endoscopes (MAE) while localization based on external medical imaging demands accurate registration and imposes a variety of modality-specific challenges during continuous image acquisition
Cooperative sensing, a technique employed in cognitive radio (CR) networks for spectrum sensing, exhibits promising potential in bolstering spectrum utilization and enhancing network performance. This approach leverages the information captured by distributed CR users, which is subsequently aggregat…
Decentralized computation has received considerable research interest lately, due to its wide applications in information processing systems. However, one key requirement to establish convergence for almost all decentralized algorithms, for convex and non-convex problems alike, is that the loss func…
Shape formation of robot swarms is quite challenging when the robot number varies, as the number often needs to match the number of goal locations in the shape. For this challenge, state-of-the-art methods characterize the shape as a continuous region and distribute robots in the region. However, su
Sequential recommendation (SR) aims to predict items that users may be interested in based on their historical behavior sequences. We revisit SR from a novel information-theoretic perspective and find that conventional sequential modeling methods fail to adequately capture the randomness and unpredi…
A fundamental problem in cognitive radio is spectrum sensing, which detects the presence of the primary users in a licensed spectrum. To boost the detection performance and robustness, the multiantenna detector has been investigated and various related methods have been developed, e.g., the energy d…
Federated learning (FL) inevitably confronts the challenge of system heterogeneity in practical scenarios. To enhance the capabilities of most model-homogeneous FL methods in handling system heterogeneity, we propose a training scheme that can extend their capabilities to cope with this challenge. I…
Data-driven methods have great advantages in modeling complicated human behavioral dynamics and dealing with many human-robot interaction applications. However, collecting massive and annotated real-world human datasets has been a laborious task, especially for highly interactive scenarios. On the o…
The methods of shape formation in robot swarms are usually classified into two categories by whether assignment is used or not. The first is to use target assignment to assemble precise formation. However, the additional algorithm for re-assignment is required to handle unreasonable situations, whic
Most existing reflection removal methods pay too much attention to the transmission layer and ignore the mutual complementary mechanisms between the transmission layer and the reflection layer. To make full use of the complementarity and distinction between the reflection and transmission layers in…
As the number of vulnerabilities increases day by day, security management requires more and more structured data. In addition to textual descriptions of vulnerabilities, security engineers must classify and assess vulnerabilities and clarify their associated techniques. Vulnerability Description Ma…
This work proposes a new learning target based on reverberation time shortening (RTS) for speech dereverberation. The learning target for dereverberation is usually set as the direct-path speech or optionally with some early reflections. This type of target suddenly truncates the reverberation, and…
Accurate, long-term forecasting of pedestrian trajectories in highly dynamic and interactive scenes is a longstanding challenge. Recent advances in using data-driven approaches have achieved significant improvements in terms of prediction accuracy. However, the lack of group-aware analysis has limit…
En route travel time estimation (ER-TTE) aims to predict the travel time on the remaining route. Since the traveled and remaining parts of a trip usually have some common characteristics like driving speed, it is desirable to explore these characteristics for improved performance via effective adapt…
The vector autoregressive (VAR) models provide a significant tool for multivariate time series analysis. Most existing works on VAR modeling are based on the multivariate Gaussian distribution. However, heavy-tailed distributions are suggested more reasonable for capturing the real-world phenomena,…
The heuristic 1/N (equally weighted) portfolio and long-only quintile portfolio are both popular simple strategies in financial investment. In the 1/N portfolio, a fraction of 1/N of wealth is allocated to each of the N available assets. In the long-only quintile portfolio, first the assets are sort…
All animals and robots that move in the world must navigate to a goal while clearing obstacles. Using vision to accomplish such task has several advantages in cost and payload, which explains the prevalence of biological visual guidance. However, the computational overhead has been an obvious concer…
Enumerating maximal bicliques in a bipartite graph is an important problem in data mining, with innumerable real-world applications across different domains such as web community, bioinformatics, etc. Although substantial research has been conducted on this problem, surprisingly, we find that pivot-…
Minimax multiple-input multiple-output (MIMO) transmit beampattern matching is a fundamental and important problem in many MIMO systems. The problem is formulated to minimize the maximum beampattern matching error as well as suppress the cross-correlation beampatterns while taking different practica…