51 accepted papers
Centralized training with decentralized execution (CTDE) is a framework for MARL with wide applications. In the CTDE paradigm, agents leverage global state information during training to mitigate the non-stationarity of the MARL environment, but must rely solely on partial observations during execut
We propose DialoGen, a novel framework for generating realistic gestures for both interlocutors in dialog scenarios, conditioned on conversational audios. Unlike most existing methods that focus solely on a single speaker, DialoGen simultaneously generates synchronized gestures for both participants
Recently, a line of works can generate impressive 3D objects from a single image, but they are limited by restricted representation resolution, making them unsuitable for 3D scene generation. In this work, we introduce \name, a novel method for high-quality 3D scene generation based on hierarchical …
The longitudinal management of blinding fundus diseases constitutes a Partially Observable Markov Decision Process (POMDP) necessitating a critical precision-risk trade-off between intervention and over-treatment, as true pathology is often obscured in static observations. However, existing paradigm…
Text-to-multiview (T2MV) diffusion models have shown great promise in generating multiple views of a scene from a single text prompt. While few-step backbones enable real-time T2MV generation, they often compromise key aspects of generation quality, such as per-view fidelity and cross-view consisten
Generalizing robotic manipulation across object poses, viewpoints, and dynamic disturbances is difficult, especially with only a few demonstrations. End-to-end visuomotor policies are expressive but data-hungry, while planning and optimization satisfy explicit constraints but do not directly capture…
Enabling robots to perform tool manipulation like humans remains a great challenge. A semantic understanding of tool affordances and precise spatial localization is essential for this task. Conventional methods relying on RGB-D cameras for affordance detection and tool manipulation have been proven
Automatic sleep staging is crucial for sleep assessment and diagnosis. Signals of different modalities, such as electroencephalogram (EEG) and electrooculogram (EOG), are of crucial importance for sleep staging. Therefore, effective fusion of different modal signals is the key to improve sleep stagi…
With the increasing complexity of pipeline systems in various industrial and environmental applications, there is a critical need for flexible and efficient robotic solutions that can navigate and inspect confined spaces. This paper introduces a lightweight pipeline crawling robot based on spring-ro
Multimodal large language models (MLLMs) have experienced significant advancements recently, but still struggle to recognize and interpret intricate details in high-resolution (HR) images effectively. While state-of-the-art (SOTA) MLLMs claim to process images at 4K resolution, existing MLLM benchma…
Active Speaker Detection (ASD) aims to determine whether each candidate in a video frame is speaking. The egocentric dataset Ego4D introduces unique challenges for this task, such as dynamic shooting angles that cause candidates to frequently leave the sight, leading to temporal discontinuities. Add…
Recent advancements in video diffusion models have established a strong foundation for developing world models with practical applications. The next challenge lies in exploring how an agent can leverage these foundation models to understand, interact with, and plan within observed environments. This…
Anomaly detection on attributed graphs has applications in various domains such as finance and email spam detection, thus gaining substantial attention. Distributed scenarios can also involve issues related to anomaly detection in attribute graphs, such as in medical scenarios. However, most of the…
Lip-reading is to utilize the visual information of the speaker’s lip movements to recognize words and sentences. Existing event-based lip-reading solutions integrate different frame rate branches to learn spatio-temporal features of varying granularities. However, aggregating events into event fram…
Remote sensing image fusion aims to reconstruct a high spatial and spectral resolution image by integrating the spatial and spectral information from multiple remote sensing sensor data. Despite the remarkable progress of deep learning-based fusion methods, most existing methods rely on manual netwo…
Video virtual try-on aims to seamlessly dress a subject in a video with a specific garment. The primary challenge involves preserving the visual authenticity of the garment while dynamically adapting to the pose and physique of the subject. While existing methods have predominantly focused on image-…
Recent Multimodal Large Language Models(MLLMs) often use a large number of visual tokens to compensate their visual shortcoming, leading to excessive computation and obvious visual redundancy. In this paper, we investigate what kind of visual tokens are needed for MLLMs, and reveal that both foregro…
The long-term consistent visual tracking of large-scale moving swarms of animals or autonomous moving robots (AMR) is extremely challenging when the three factors are involved: 1) similar appearance of animals or AMR, 2) frequent and unpredictable occlusions, and 3) non-linear maneuvers. When facing
Incremental learning is nontrivial due to severe catastrophic forgetting. Although storing a small amount of data on old tasks during incremental learning is a feasible solution, current strategies still do not 1) adequately address the class bias problem, and 2) alleviate the mutual interference be…
Existing event-based motion deblurring methods mostly focus on restoring images with the same spatial and temporal scales as events. However, the unknown scales of images and events in the real world pose great challenges and have rarely been explored. To address this gap, we propose a novel Scale-A…
Efficient computation or approximation of Levenshtein distance, a widely-used metric for evaluating sequence similarity, has attracted significant attention with the emergence of DNA storage and other biological applications. Sequence embedding, which maps Levenshtein distance to a conventional dist…
Existing super-resolution (SR) methods optimize all model weights equally using $\mathcal{L}_1$ or $\mathcal{L}_2$ losses by uniformly sampling image patches without considering dataset imbalances or parameter redundancy, which limits their performance. To address this, we formulate the image SR tas…
In topical domain generalization (DG), trained models are asked to perform well on an unknown target domain with different data statistics. In order to improve domain generalization, adversarial learning has proven to be one of the most effective methods. Existing approaches, however, rely primarily…
The chain-of-thought technique has been received well in multi-modal tasks. It is a step-by-step linear reasoning process that adjusts the length of the chain to improve the performance of generated prompts. However, human thought processes are predominantly non-linear, as they encompass multiple as…
Recent research on mobile robots has focused on increasing their adaptability to unpredictable and unstructured environments using soft materials and structures. However, the determination of key design parameters and control over these compliant robots are predominantly iterated through experiments…
This paper studies a beam tracking problem in a reconfigurable intelligent surface (RIS)-assisted communication system, in which a single antenna access point (AP) tracks a single-antenna mobile user equipment (UE) through actively reconfiguring the RIS. To maintain beam alignment over time, the mob…
Recent studies on the network of multi-vehicle systems have shown that the system performance can be improved comprehensively by actively using historical information without changing the network connectivity. Motivated by this observation, we aim to improve the performance of affine formation maneu
We study causal, low-latency, sequential video compression when the output is subjected to both a mean squared-error (MSE) distortion loss as well as a perception loss to target realism. Motivated by prior approaches, we consider two different perception loss functions (PLFs). The first, PLF-JD, co…
With ever increasing parameters and computation, vision-language pre-trained (VLP) models exhibit prohibitive expenditure in downstream task adaption. Recent endeavors mainly focus on parameter efficient transfer learning (PETL) for VLP models by only updating a small number of parameters. However,…
Residual Hybrid Attention Network (RHAN) can restore images of arbitrary compression quality through flexibly fusing high-frequency features in the spatial and frequency domains based on the input quality factor. Specifically, to remove the compression artifacts, we propose a hybrid attention block…
This paper studies the covariance based activity detection problem in a multi-cell massive multiple-input multiple-output (MIMO) system, where the active devices transmit their signature sequences to multiple base stations (BSs), and the BSs cooperatively detect the active devices based on the recei…
With the rapid development of vision-based deep learning (DL), it is an effective method to generate large-scale synthetic data to supplement real data to train the DL models for domain adaptation. However, previous vanilla domain adaptation methods generally assume the same label space, and such an…
This paper proposes a data-driven architecture for zero-delay lossy source coding with side information (i.e., Wyner-Ziv coding) for sources with memory. The overall architecture involves designing suitable filters at the encoder and the decoder and performing fixed-rate scalar quantization followed…
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents and objects. We introduce the task of semantic action-conditional video prediction, which uses semantic action labels to…
Reconfigurable intelligent surface (RIS) is capable of intelligently manipulating the phases of the incident electromagnetic wave to improve the wireless propagation environment between the base station (BS) and the users. This paper addresses the joint user scheduling, RIS configuration, and BS bea…
This paper proposes a computationally efficient algorithm to solve the joint data and activity detection problem for massive random access with massive multiple-input multiple-output (MIMO). The BS acquires the active devices and their data by detecting the transmitted preassigned nonorthogonal sign…
This paper proposes a deep learning approach to the adaptive and sequential beamforming design problem for the initial access phase in a mmWave environment with a single-path channel model. In particular, for a single-user scenario where the problem is equivalent to designing the sequence of sensing…
This work proposes a novel and scalable reinforcement learning approach for routing in ad-hoc wireless networks. In most previous reinforcement learning based routing methods, the links in the network are assumed to be fixed, and a different agent is trained for each transmission node — this limits…
Robust optimization is an important task in wireless communications, because due to fading and feedback delay there is inherent uncertainty in channel state information in a wireless environment. This paper aims to show that a deep learning approach for network utility maximization can produce more…
Applying resolution-preserving blocks is a common practice to maximize information preservation in video prediction, yet their high memory consumption greatly limits their application scenarios. We propose CrevNet, a Conditionally Reversible Network that uses reversible architectures to build a bije…
This paper proposes an autoencoder-based symbol-level precoding (SLP) scheme for a massive multiple-input multiple-output (MIMO) system operating in a limited-scattering environment. By recognizing that only imperfect channel state information (CSI) is available in practice, the goal of the proposed…
Pilot contamination is a main limiting factor in multi-cell massive multiple-input multiple-output (MIMO) systems due to the non-orthogonality of pilot sequences which can seriously impair the channel measurement. Recent work has suggested coordinating pilot sequence design across multiple cells by…
The orthogonal matching pursuit (OMP) algorithm is a commonly used algorithm for recovering K-sparse signals x ∈ ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">n</sup> from linear model y = Ax, where A ∈ ℝ <sup xmlns:mml="http://www.w3.org/1998/Math/…
The performance of cloud radio access networks (C-RAN) is limited by the finite capacities of the backhaullinks connecting the cloud with the base-stations (BSs). A promising approach to improving the performance of C-RAN is to augment the backhaul through BS caching, where the BSs pre-store some of…
Sparse device activity detection for machine-type communications has attracted increasing attention in recent studies. However, most of the previous works focus on the single-cell case. This paper studies the impact of the inter-cell interference on the device activity detection problem with non-ort…
User activity detection is a central problem in massive device communication scenarios in which an access point needs to detect active devices among large number of potential devices each transmitting sporadically. By exploiting sparsity in user activity, the detection problem can be formulated as a…
This paper presents a novel deep regression network to extract geometric information from Light Field (LF) data. Our network builds upon u-shaped network architectures. Those networks involve two symmetric parts, an encoding and a decoding part. In the first part the network encodes relevant informa…
This paper proposes a joint uplink user scheduling and beam-forming algorithm for a multiple-antenna wireless cellular network. We show that coordinated optimization across the cells can significantly alleviate intercell interference, thereby improving the cell-edge rates in a multicell network. Unl…
This paper considers the optimal placement of content in cache-enabled base-stations (BSs) for reducing backhaul traffic in a densely deployed wireless access network. By caching popular files, users requesting these files can be served directly by their associated BSs without needing to fetch conte…
Large-scale multiple-input multiple-output (MIMO) systems enable high spectral efficiency by employing large antenna arrays at both the transmitter and the receiver of a wireless communication link. In traditional MIMO systems, full digital beamforming is done at the baseband; one distinct radio-fre…
For several decades, image restoration remains an active research topic in low-level computer vision and hence new approaches are constantly emerging. However, many recently proposed algorithms achieve state-of-the-art performance only at the expense of very high computation time, which clearly limi…