Search

This paper aims to provide a series of characterizations of the robust isolated calmness of the Karush-Kuhn-Tucker (KKT) mapping for spectral norm regularized convex optimization problems. By establishing the variational properties of the spectral norm function, we directly prove that the KKT mapping is isolated calm if and only if the strict Robinson constraint qualification (SRCQ) and the second order sufficient condition (SOSC) hold. Furthermore, we obtain the crucial result that the SRCQ for the primal problem and the SOSC for the dual problem are equivalent. The obtained results can derive more equivalent or sufficient conditions of the robust isolated calmness of the KKT mapping, thereby enriching the stability theory of spectral norm regularized optimization problems and enhancing the usability of isolated calmness in algorithm applications.

Enabling mobile robots to perform long-term tasks in dynamic real-world environments is a formidable challenge, especially when the environment changes frequently due to human-robot interactions or the robot's own actions. Traditional methods typically assume static scenes, which limits their applicability in the continuously changing real world. To overcome these limitations, we present DovSG, a novel mobile manipulation framework that leverages dynamic open-vocabulary 3D scene graphs and a language-guided task planning module for long-term task execution. DovSG takes RGB-D sequences as input and utilizes vision-language models (VLMs) for object detection to obtain high-level object semantic features. Based on the segmented objects, a structured 3D scene graph is generated for low-level spatial relationships. Furthermore, an efficient mechanism for locally updating the scene graph, allows the robot to adjust parts of the graph dynamically during interactions without the need for full scene reconstruction. This mechanism is particularly valuable in dynamic environments, enabling the robot to continually adapt to scene changes and effectively support the execution of long-term tasks. We validated our system in real-world environments with varying degrees of manual modifications, demonstrating its effectiveness and superior performance in long-term tasks. Our project page is available at: https://bjhyzj.github.io/dovsg-web., Comment: 8 pages, 5 figures

As telecommunications systems progress to support diverse use cases with heterogeneous and dynamic Quality of Service (QoS) requirements, it becomes an increasingly complex task to automatically manage various resources involved -- from radio, compute, to X-haul network, which are distributed from the edge to the cloud. Intent-driven network automation can play an important role in NextG networks to meet this need. Towards this, we have developed INA-Infra, an open, extensible, and end-to-end 5G/beyond 5G network infrastructure with intent-driven network automation and end-to-end network slicing capability. INA-Infra is designed using open-source components and is based on O-RAN architecture. INA-Infra manages the network infrastructure, various resources, and (virtualized / containerized) network functions using Nephio -- a cloud-native intent automation solution. It also incorporates intent-driven intelligent control using a Resource Management rApp and a Network Slicing xApp. We demonstrate that INA-Infra can manage the 5G network in a highly automatic and optimized manner, allowing the mobile network operators to focus on specifying the intents of different traffic classes., Comment: Preprint version, published at workshop OpenRIT-6G, part of IEEE GLOBECOM 2024

Ice nucleation and growth are critical in many fields, including atmospheric science, cryobiology, and aviation. However, understanding the detailed mechanisms of ice crystal growth remains challenging. In this work, crystallization at the ice/quasi-liquid layer (QLL) interface of the basal and primary prism (prism1) surfaces of hexagonal ice (Ih) was investigated using molecular dynamics simulations across a wide range of temperatures for the TIP4P/Ice model, with comparisons to the mW coarse-grained model. Together with elucidating the temperature-dependent mechanisms of crystallization, face-specific growth rates were systematically estimated. While the prism surface generally exhibits faster growth rates than the basal surface, a temperature-dependent crossover in growth rates between the basal and prism surfaces is observed in TIP4P/Ice simulations, which correlates with a crossover in QLL thickness and with the well-known column to platelets transition in ice-crystal habits at low vapour pressure. This observation helps decode the complex dependence between crystal morphology and temperature in ice crystals., Comment: 12 pages, 6 figures

Large language models (LLMs) have demonstrated remarkable performance on various tasks. However, it remains an open question whether the default Euclidean space is the most suitable choice for embedding tokens in LLMs. In this study, we first investigate the non-Euclidean characteristics of LLMs. Our findings reveal that token frequency follows a power-law distribution, with high-frequency tokens clustering near the origin and low-frequency tokens positioned farther away. Additionally, token embeddings exhibit a high degree of hyperbolicity, indicating a latent tree-like structure in the embedding space. Building on the observation, we propose to efficiently fine-tune LLMs in hyperbolic space to better exploit the underlying complex structures. However, we found that this fine-tuning in hyperbolic space cannot be achieved with naive application of exponential and logarithmic maps, when the embedding and weight matrices both reside in Euclidean space. To address this technique issue, we introduce a new method called hyperbolic low-rank efficient fine-tuning, HypLoRA, that performs low-rank adaptation directly on the hyperbolic manifold, avoiding the cancellation effect caused by the exponential and logarithmic maps, thus preserving the hyperbolic modeling capabilities. Through extensive experiments, we demonstrate that HypLoRA significantly enhances the performance of LLMs on reasoning tasks, particularly for complex reasoning problems. In particular, HypLoRA improves the performance in the complex AQuA dataset by up to 13.0%, showcasing its effectiveness in handling complex reasoning challenges, Comment: The preliminary work was accepted for the ICML 2024 LLM Cognition Workshop, and this version includes new investigations, analyses, experiments, and results

In this paper, we study the Cauchy problem of the classical incompressible Navier-Stokes equations and the parabolic-elliptic Keller-Segel system in the framework of the Fourier-Besov spaces with variable regularity and integrability indices. By fully using some basic properties of these variable function spaces, we establish the linear estimates in variable Fourier-Besov spaces for the heat equation. Such estimates are fundamental for solving certain PDE's of parabolic type. As an applications, we prove global well-posedness in variable Fourier-Besov spaces for the 3D classical incompressible Navier-Stokes equations and the 3D parabolic-elliptic Keller-Segel system., Comment: 20 pages. arXiv admin note: substantial text overlap with arXiv:2410.00060

In this paper, we are concerned with the well-posed issues of the fractional dissipative system in the framework of the Fourier--Besov spaces with variable regularity and integrability indices. By fully using some basic properties of these variable function spaces, we establish the linear estimates in variable Fourier--Besov spaces for the fractional heat equation. Such estimates are fundamental for solving certain dissipative PDE's of fractional type. As an applications, we prove global well-posedness in variable Fourier--Besov spaces for the 3D generalized incompressible Navier--Stokes equations and the 3D fractional Keller--Segel system., Comment: 21 pages. arXiv admin note: text overlap with arXiv:2405.01209

Low Probability of Detection (LPD) communication aims to obscure the presence of radio frequency (RF) signals to evade surveillance. In the context of mobile surveillance utilizing unmanned aerial vehicles (UAVs), achieving LPD communication presents significant challenges due to the UAVs' rapid and continuous movements, which are characterized by unknown nonlinear dynamics. Therefore, accurately predicting future locations of UAVs is essential for enabling real-time LPD communication. In this paper, we introduce a novel framework termed predictive covert communication, aimed at minimizing detectability in terrestrial ad-hoc networks under multi-UAV surveillance. Our data-driven method synergistically integrates graph neural networks (GNN) with Koopman theory to model the complex interactions within a multi-UAV network and facilitating long-term predictions by linearizing the dynamics, even with limited historical data. Extensive simulation results substantiate that the predicted trajectories using our method result in at least 63%-75% lower probability of detection when compared to well-known state-of-the-art baseline approaches, showing promise in enabling low-latency covert operations in practical scenarios.

Six-dimensional movable antenna (6DMA) is an innovative technology to improve wireless network capacity by adjusting 3D positions and 3D rotations of antenna surfaces based on channel spatial distribution. However, the existing works on 6DMA have assumed a central processing unit (CPU) to jointly process the signals of all 6DMA surfaces to execute various tasks. This inevitably incurs prohibitively high processing cost for channel estimation. Therefore, we propose a distributed 6DMA processing architecture to reduce processing complexity of CPU by equipping each 6DMA surface with a local processing unit (LPU). In particular, we unveil for the first time a new \textbf{\textit{directional sparsity}} property of 6DMA channels, where each user has significant channel gains only for a (small) subset of 6DMA position-rotation pairs, which can receive direct/reflected signals from users. In addition, we propose a practical three-stage protocol for the 6DMA-equipped base station (BS) to conduct statistical CSI acquisition for all 6DMA candidate positions/rotations, 6DMA position/rotation optimization, and instantaneous channel estimation for user data transmission with optimized 6DMA positions/rotations. Specifically, the directional sparsity is leveraged to develop distributed algorithms for joint sparsity detection and channel power estimation, as well as for directional sparsity-aided instantaneous channel estimation. Using the estimated channel power, we develop a channel power-based optimization algorithm to maximize the ergodic sum rate of the users by optimizing the antenna positions/rotations. Simulation results show that our channel estimation algorithms are more accurate than benchmarks with lower pilot overhead, and our optimization outperforms fluid/movable antennas optimized only in two dimensions (2D), even when the latter have perfect instantaneous CSI., Comment: 14 pages, double-column

While humans naturally identify novel objects and understand their relationships, deep learning-based object detectors struggle to detect and relate objects that are not observed during training. To overcome this issue, Open World Object Detection(OWOD) has been introduced to enable models to detect unknown objects in open-world scenarios. However, OWOD methods fail to capture the fine-grained relationships between detected objects, which are crucial for comprehensive scene understanding and applications such as class discovery and tracking. In this paper, we propose a method to train an object detector that can both detect novel objects and extract semantically rich features in open-world conditions by leveraging the knowledge of Vision Foundation Models(VFM). We first utilize the semantic masks from the Segment Anything Model to supervise the box regression of unknown objects, ensuring accurate localization. By transferring the instance-wise similarities obtained from the VFM features to the detector's instance embeddings, our method then learns a semantically rich feature space of these embeddings. Extensive experiments show that our method learns a robust and generalizable feature space, outperforming other OWOD-based feature extraction methods. Additionally, we demonstrate that the enhanced feature from our model increases the detector's applicability to tasks such as open-world tracking., Comment: Our project website can be found at https://sunohlee.github.io/OWODRep/

Scene text recognition (STR) from high-resolution (HR) images has been significantly successful, however text reading on low-resolution (LR) images is still challenging due to insufficient visual information. Therefore, recently many scene text image super-resolution (STISR) models have been proposed to generate super-resolution (SR) images for the LR ones, then STR is done on the SR images, which thus boosts recognition performance. Nevertheless, these methods have two major weaknesses. On the one hand, STISR approaches may generate imperfect or even erroneous SR images, which mislead the subsequent recognition of STR models. On the other hand, as the STISR and STR models are jointly optimized, to pursue high recognition accuracy, the fidelity of SR images may be spoiled. As a result, neither the recognition performance nor the fidelity of STISR models are desirable. Then, can we achieve both high recognition performance and good fidelity? To this end, in this paper we propose a novel method called IMAGE (the abbreviation of Iterative MutuAl GuidancE) to effectively recognize and recover LR scene text images simultaneously. Concretely, IMAGE consists of a specialized STR model for recognition and a tailored STISR model to recover LR images, which are optimized separately. And we develop an iterative mutual guidance mechanism, with which the STR model provides high-level semantic information as clue to the STISR model for better super-resolution, meanwhile the STISR model offers essential low-level pixel clue to the STR model for more accurate recognition. Extensive experiments on two LR datasets demonstrate the superiority of our method over the existing works on both recognition performance and super-resolution fidelity.

A fast multipole method (FMM)-accelerated surface integral equation (SIE) simulator, called XRL, is proposed for broadband resistance/inductance (RL) extraction under the magneto-quasi-static assumption. The proposed XRL has three key attributes that make it highly efficient and accurate for broadband RL extraction of complicated 3-D geometries: (i) The XRL leverages a novel centroid-midpoint basis transformation while discretizing surface currents, which allows converting edge-based vector potential computations to panel-based scalar potential computations. Such conversion makes the implementation of FMM straightforward and allows for drastically reducing the memory and computational time requirements of the simulator. (ii) The XRL employs a highly accurate equivalent surface impedance model that allows extracting RL parameters at low frequencies very accurately. (iii) The XRL makes use of a novel preconditioner, effectively including both diagonal entries and some near-field entries of the system matrix; such preconditioner significantly accelerates the iterative solution of SIE. The proposed XRL can accurately compute broadband RL parameters of arbitrarily shaped and large-scale structures on a desktop computer. It has been applied to RL parameter extraction of various practical structures, including two parallel square coils, a ball grid array (BGA) package and a high brand package on package. Its application to the parameter extraction of the BGA shows that the XRL requires 93.2x and 14.2x less computational time and memory resources compared to the commercial simulator Ansys Q3D for the same level of accuracy, respectively.

Symmetry control is essential for realizing unconventional properties, such as ferroelectricity, nonlinear optical responses, and complex topological order, thus it holds promise for the design of emerging quantum and photonic systems. Nevertheless, fast and reversible control of symmetry in materials remains a challenge, especially for nanoscale systems. Here, we unveil reversible symmetry changes in colloidal lead chalcogenide quantum dots on picosecond timescales. Using a combination of ultrafast electron diffraction and total X-ray scattering, in conjunction with atomic-scale structural modeling and first-principles calculations, we reveal that symmetry-broken lead sulfide quantum dots restore to a centrosymmetric phase upon photoexcitation. The symmetry restoration is driven by photoexcited electronic carriers, which suppress lead off-centering for about 100 ps. Furthermore, the change in symmetry is closely correlated with the electronic properties as shown by transient optical measurements. Overall, this study elucidates reversible symmetry changes in colloidal quantum dots, and more broadly defines a new methodology to optically control symmetry in nanoscale systems on ultrafast timescales., Comment: 19 pages, 5 figures

The Koopman autoencoder, a data-driven technique, has gained traction for modeling nonlinear dynamics using deep learning methods in recent years. Given the linear characteristics inherent to the Koopman operator, controlling its eigenvalues offers an opportunity to enhance long-term prediction performance, a critical task for forecasting future trends in time-series datasets with long-term behaviors. However, controlling eigenvalues is challenging due to high computational complexity and difficulties in managing them during the training process. To tackle this issue, we propose leveraging the singular value decomposition (SVD) of the Koopman matrix to adjust the singular values for better long-term prediction. Experimental results demonstrate that, during training, the loss term for singular values effectively brings the eigenvalues close to the unit circle, and the proposed approach outperforms existing baseline methods for long-term prediction tasks., Comment: 6 pages, 5 figures, to be presented at IEEE MLSP 2024

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses.

In recent years, large-scale multimodal models have demonstrated impressive capabilities across various domains. However, enabling these models to effectively perform multiple multimodal tasks simultaneously remains a significant challenge. To address this, we introduce a novel tuning method called neural tuning, designed to handle diverse multimodal tasks concurrently, including reasoning segmentation, referring segmentation, image captioning, and text-to-image generation. Neural tuning emulates sparse distributed representation in human brain, where only specific subsets of neurons are activated for each task. Additionally, we present a new benchmark, MMUD, where each sample is annotated with multiple task labels. By applying neural tuning to pretrained large models on the MMUD benchmark, we achieve simultaneous task handling in a streamlined and efficient manner. All models, code, and datasets will be publicly available after publication, facilitating further research and development in this field.

While it seems counterintuitive to think of degradation within an operating device as beneficial, one may argue that when rationally designed, the controlled breakdown of materials can be harnessed for specific functions. To apply this principle to the design of morphing devices, we introduce the concept of Degrade to Function (DtF). This concept aims to create eco-friendly and self-contained morphing devices that operate through a sequence of environmentally-triggered degradations. We explore its design considerations and implementation techniques by identifying environmental conditions and degradation types that can be exploited, evaluating potential materials capable of controlled degradation, suggesting designs for structures that can leverage degradation to achieve various transformations and functions, and developing sequential control approaches that integrate degradation triggers. To demonstrate the viability and versatility of this design strategy, we showcase several application examples across a range of environmental conditions., Comment: 24 pages, 24 figures, The 37th Annual ACM Symposium on User Interface Software and Technology (UIST 24)

In computer vision, the vision transformer (ViT) has increasingly superseded the convolutional neural network (CNN) for improved accuracy and robustness. However, ViT's large model sizes and high sample complexity make it difficult to train on resource-constrained edge devices. Split learning (SL) emerges as a viable solution, leveraging server-side resources to train ViTs while utilizing private data from distributed devices. However, SL requires additional information exchange for weight updates between the device and the server, which can be exposed to various attacks on private training data. To mitigate the risk of data breaches in classification tasks, inspired from the CutMix regularization, we propose a novel privacy-preserving SL framework that injects Gaussian noise into smashed data and mixes randomly chosen patches of smashed data across clients, coined DP-CutMixSL. Our analysis demonstrates that DP-CutMixSL is a differentially private (DP) mechanism that strengthens privacy protection against membership inference attacks during forward propagation. Through simulations, we show that DP-CutMixSL improves privacy protection against membership inference attacks, reconstruction attacks, and label inference attacks, while also improving accuracy compared to DP-SL and DP-MixSL., Comment: 23 pages, 11 figures, 8 tables, to be published in Transactions on Machine Learning Research (TMLR)

Quality assessment and aesthetics assessment aim to evaluate the perceived quality and aesthetics of visual content. Current learning-based methods suffer greatly from the scarcity of labeled data and usually perform sub-optimally in terms of generalization. Although masked image modeling (MIM) has achieved noteworthy advancements across various high-level tasks (e.g., classification, detection etc.). In this work, we take on a novel perspective to investigate its capabilities in terms of quality- and aesthetics-awareness. To this end, we propose Quality- and aesthetics-aware pretraining (QPT V2), the first pretraining framework based on MIM that offers a unified solution to quality and aesthetics assessment. To perceive the high-level semantics and fine-grained details, pretraining data is curated. To comprehensively encompass quality- and aesthetics-related factors, degradation is introduced. To capture multi-scale quality and aesthetic information, model structure is modified. Extensive experimental results on 11 downstream benchmarks clearly show the superior performance of QPT V2 in comparison with current state-of-the-art approaches and other pretraining paradigms. Code and models will be released at \url{https://github.com/KeiChiTse/QPT-V2}., Comment: 8 pages, 6 figures

In this paper, we examine the possibility that massive neutrinos are unstable due to their invisible decays $\nu^{}_i \to \nu^{}_j + \phi$, where $\nu^{}_i$ and $\nu^{}_j$ (for $i, j = 1, 2, 3$) are any two of neutrino mass eigenstates with masses $m^{}_i > m^{}_j$ and $\phi$ is a massless Nambu-Goldstone boson, and explore the implications for the detection of cosmological relic neutrinos in the present Universe. First, we carry out a complete calculation of neutrino decay rates in the general case where the individual helicities of parent and daughter neutrinos are specified. Then, the invisible decays of cosmological relic neutrinos are studied and their impact on the capture rates on the beta-decaying nuclei (e.g., $\nu^{}_e + {^3{\rm H}} \to {^3{\rm He}} + e^-$) is analyzed. The invisible decays of massive neutrinos could substantially change the capture rates in the PTOLEMY-like experiments when compared to the case of stable neutrinos. In particular, we find that the helicity-changing decays of Dirac neutrinos play an important role whereas those of Majorana neutrinos have no practical effects. However, if a substantial fraction of heavier neutrinos decay into the lightest one, the detection of relic neutrinos will require a much higher energy resolution and thus be even more challenging., Comment: 29 pages, 7 figures, more discussions and references added, version accepted by JCAP

Temporal causal discovery is a crucial task aimed at uncovering the causal relations within time series data. The latest temporal causal discovery methods usually train deep learning models on prediction tasks to uncover the causality between time series. They capture causal relations by analyzing the parameters of some components of the trained models, e.g., attention weights and convolution weights. However, this is an incomplete mapping process from the model parameters to the causality and fails to investigate the other components, e.g., fully connected layers and activation functions, that are also significant for causal discovery. To facilitate the utilization of the whole deep learning models in temporal causal discovery, we proposed an interpretable transformer-based causal discovery model termed CausalFormer, which consists of the causality-aware transformer and the decomposition-based causality detector. The causality-aware transformer learns the causal representation of time series data using a prediction task with the designed multi-kernel causal convolution which aggregates each input time series along the temporal dimension under the temporal priority constraint. Then, the decomposition-based causality detector interprets the global structure of the trained causality-aware transformer with the proposed regression relevance propagation to identify potential causal relations and finally construct the causal graph. Experiments on synthetic, simulated, and real datasets demonstrate the state-of-the-art performance of CausalFormer on discovering temporal causality. Our code is available at https://github.com/lingbai-kong/CausalFormer.

Despite their impressive capabilities, large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content. Enhancing LLMs with retrieval mechanisms to fetch relevant information from external sources offers a promising solution. Inspired by the proverb "Think twice before you act," we propose a dual-angle evaluated retrieval-augmented generation framework \textit{Think-then-Act}. Unlike previous approaches that indiscriminately rewrite queries or perform retrieval regardless of necessity, or generate temporary responses before deciding on additional retrieval, which increases model generation costs, our framework employs a two-phase process: (i) assessing the input query for clarity and completeness to determine if rewriting is necessary; and (ii) evaluating the model's capability to answer the query and deciding if additional retrieval is needed. Experimental results on five datasets show that the \textit{Think-then-Act} framework significantly improves performance. Our framework demonstrates notable improvements in accuracy and efficiency compared to existing baselines and performs well in both English and non-English contexts. Ablation studies validate the optimal model confidence threshold, highlighting the resource optimization benefits of our approach., Comment: 12 pages, 8 figures

We point out that the observed pattern of lepton flavor mixing can be well described by a proper nearest-neighbor expansion of a constant $3\times 3$ unitary matrix in powers of a small parameter characterizing the fine effect of $\mu$-$\tau$ permutation symmetry breaking. We take an example of this kind for illustration, and provide complete discussions on the usefulness in the study of leptonic CP violation and unitarity triangles in matter., Comment: 18 pages, 3 figures, 2 tables, more discussions and references added, version accepted by PLB

In the new paradigm of semantic communication (SC), the focus is on delivering meanings behind bits by extracting semantic information from raw data. Recent advances in data-to-text models facilitate language-oriented SC, particularly for text-transformed image communication via image-to-text (I2T) encoding and text-to-image (T2I) decoding. However, although semantically aligned, the text is too coarse to precisely capture sophisticated visual features such as spatial locations, color, and texture, incurring a significant perceptual difference between intended and reconstructed images. To address this limitation, in this paper, we propose a novel language-oriented SC framework that communicates both text and a compressed image embedding and combines them using a latent diffusion model to reconstruct the intended image. Experimental results validate the potential of our approach, which transmits only 2.09\% of the original image size while achieving higher perceptual similarities in noisy communication channels compared to a baseline SC method that communicates only through text.The code is available at https://github.com/ispamm/Img2Img-SC/ ., Comment: Under review at IEEE International Workshop on Machine Learning for Signal Processing (MLSP) 2024

In recent years, novel communication strategies have emerged to face the challenges that the increased number of connected devices and the higher quality of transmitted information are posing. Among them, semantic communication obtained promising results especially when combined with state-of-the-art deep generative models, such as large language or diffusion models, able to regenerate content from extremely compressed semantic information. However, most of these approaches focus on single-user scenarios processing the received content at the receiver on top of conventional communication systems. In this paper, we propose to go beyond these methods by developing a novel generative semantic communication framework tailored for multi-user scenarios. This system assigns the channel to users knowing that the lost information can be filled in with a diffusion model at the receivers. Under this innovative perspective, OFDMA systems should not aim to transmit the largest part of information, but solely the bits necessary to the generative model to semantically regenerate the missing ones. The thorough experimental evaluation shows the capabilities of the novel diffusion model and the effectiveness of the proposed framework, leading towards a GenAI-based next generation of communications., Comment: Under review in IEEE Journal on Selected Areas in Communications

We present Hunyuan-DiT, a text-to-image diffusion transformer with fine-grained understanding of both English and Chinese. To construct Hunyuan-DiT, we carefully design the transformer structure, text encoder, and positional encoding. We also build from scratch a whole data pipeline to update and evaluate data for iterative model optimization. For fine-grained language understanding, we train a Multimodal Large Language Model to refine the captions of the images. Finally, Hunyuan-DiT can perform multi-turn multimodal dialogue with users, generating and refining images according to the context. Through our holistic human evaluation protocol with more than 50 professional human evaluators, Hunyuan-DiT sets a new state-of-the-art in Chinese-to-image generation compared with other open-source models. Code and pretrained models are publicly available at github.com/Tencent/HunyuanDiT, Comment: Project Page: https://dit.hunyuan.tencent.com/

In this paper, we are mainly concerned with the well-posed problem of the fractional Keller--Segel system in the framework of variable Lebesgue spaces. Based on carefully examining the algebraical structure of the system, we reduced the fractional Keller--Segel system into the generalized nonlinear heat equation to overcome the difficulties caused by the boundedness of the Riesz potential in a variable Lebesgue spaces, then by mixing some structural properties of the variable Lebesgue spaces with the optimal decay estimates of the fractional heat kernel, we were able to establish two well-posedness results of the fractional Keller--Segel system in this functional setting., Comment: arXiv admin note: substantial text overlap with arXiv:2404.05127

Large Language Models (LLMs) have been widely utilized to perform complex robotic tasks. However, handling external disturbances during tasks is still an open challenge. This paper proposes a novel method to achieve robotic adaptive tasks based on LLMs and Behavior Trees (BTs). It utilizes ChatGPT to reason the descriptive steps of tasks. In order to enable ChatGPT to understand the environment, semantic maps are constructed by an object recognition algorithm. Then, we design a Parser module based on Bidirectional Encoder Representations from Transformers (BERT) to parse these steps into initial BTs. Subsequently, a BTs Update algorithm is proposed to expand the initial BTs dynamically to control robots to perform adaptive tasks. Different from other LLM-based methods for complex robotic tasks, our method outputs variable BTs that can add and execute new actions according to environmental changes, which is robust to external disturbances. Our method is validated with simulation in different practical scenarios., Comment: 7 pages, 11figures, WILL PUBLISHED ON ICRA 2024

In this paper, we are mainly concerned with the well-posedness of the dissipative surface quasi-geostrophic equation in the framework of variable Lebesgue spaces. Based on some analytical results developed in the variable Lebesgue spaces and the $L^{p}$-$L^{q}$ decay estimates of the fractional heat kernel, we establish the local existence and regularity of solutions to the 2D dissipative surface quasi-geostrophic equation in the variable Lebesgue space., Comment: 11 pages

Semantic communication, emerging as a promising paradigm for data transmission, offers an innovative departure from the constraints of Shannon theory, heralding significant advancements in future communication technologies. Despite the proliferation of proposed approaches, there are still numerous challenges. In this paper, we review current semantic communication methodologies and shed light on pivotal issues and addressing certain discrepancies that exist within the field. By elucidating both dos and don'ts, we aim to provide valuable insights into the emerging landscape of semantic communication., Comment: 5 pages, IEEE vehicular technology conference, Spring 2023

Digitising the 3D world into a clean, CAD model-based representation has important applications for augmented reality and robotics. Current state-of-the-art methods are computationally intensive as they individually encode each detected object and optimise CAD alignments in a second stage. In this work, we propose FastCAD, a real-time method that simultaneously retrieves and aligns CAD models for all objects in a given scene. In contrast to previous works, we directly predict alignment parameters and shape embeddings. We achieve high-quality shape retrievals by learning CAD embeddings in a contrastive learning framework and distilling those into FastCAD. Our single-stage method accelerates the inference time by a factor of 50 compared to other methods operating on RGB-D scans while outperforming them on the challenging Scan2CAD alignment benchmark. Further, our approach collaborates seamlessly with online 3D reconstruction techniques. This enables the real-time generation of precise CAD model-based reconstructions from videos at 10 FPS. Doing so, we significantly improve the Scan2CAD alignment accuracy in the video setting from 43.0% to 48.2% and the reconstruction accuracy from 22.9% to 29.6%.

Robotic mapping with Bayesian Kernel Inference (BKI) has shown promise in creating semantic maps by effectively leveraging local spatial information. However, existing semantic mapping methods face challenges in constructing reliable maps in unstructured outdoor scenarios due to unreliable semantic predictions. To address this issue, we propose an evidential semantic mapping, which can enhance reliability in perceptually challenging off-road environments. We integrate Evidential Deep Learning into the semantic segmentation network to obtain the uncertainty estimate of semantic prediction. Subsequently, this semantic uncertainty is incorporated into an uncertainty-aware BKI, tailored to prioritize more confident semantic predictions when accumulating semantic information. By adaptively handling semantic uncertainties, the proposed framework constructs robust representations of the surroundings even in previously unseen environments. Comprehensive experiments across various off-road datasets demonstrate that our framework enhances accuracy and robustness, consistently outperforming existing methods in scenes with high perceptual uncertainties., Comment: Our project website can be found at https://kjyoung.github.io/Homepage/#/Projects/Evidential-Semantic-Mapping

This paper is an extended abstract of our original work published in KDD23, where we won the best research paper award (Xiangguo Sun, Hong Cheng, Jia Li, Bo Liu, and Jihong Guan. All in one: Multi-task prompting for graph neural networks. KDD 23) The paper introduces a novel approach to bridging the gap between pre-trained graph models and the diverse tasks they're applied to, inspired by the success of prompt learning in NLP. Recognizing the challenge of aligning pre-trained models with varied graph tasks (node level, edge level, and graph level), which can lead to negative transfer and poor performance, we propose a multi-task prompting method for graphs. This method involves unifying graph and language prompt formats, enabling NLP's prompting strategies to be adapted for graph tasks. By analyzing the task space of graph applications, we reformulate problems to fit graph-level tasks and apply meta-learning to improve prompt initialization for multiple tasks. Experiments show our method's effectiveness in enhancing model performance across different graph tasks. Beyond the original work, in this extended abstract, we further discuss the graph prompt from a bigger picture and provide some of the latest work toward this area., Comment: submitted to IJCAI 2024 Sister Conferences Track. The original paper can be seen at arXiv:2307.01504

Multi-Source cross-lingual transfer learning deals with the transfer of task knowledge from multiple labelled source languages to an unlabeled target language under the language shift. Existing methods typically focus on weighting the predictions produced by language-specific classifiers of different sources that follow a shared encoder. However, all source languages share the same encoder, which is updated by all these languages. The extracted representations inevitably contain different source languages' information, which may disturb the learning of the language-specific classifiers. Additionally, due to the language gap, language-specific classifiers trained with source labels are unable to make accurate predictions for the target language. Both facts impair the model's performance. To address these challenges, we propose a Disentangled and Adaptive Network (DA-Net). Firstly, we devise a feedback-guided collaborative disentanglement method that seeks to purify input representations of classifiers, thereby mitigating mutual interference from multiple sources. Secondly, we propose a class-aware parallel adaptation method that aligns class-level distributions for each source-target language pair, thereby alleviating the language pairs' language gap. Experimental results on three different tasks involving 38 languages validate the effectiveness of our approach., Comment: AAAI 2024