arXiv subjects

Yan Wang

Publications and source records attributed to Yan Wang.

At least 469 records · Page 26Linked to original sources

arXiv2024

STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes

We present STORM, a spatio-temporal reconstruction model designed for reconstructing dynamic outdoor scenes from sparse observations. Existing dynamic reconstruction methods often rely on per-scene optimization, dense observations across space and time, and strong motion supervision, resulting in lengthy optimization times, limited generalization to novel views or scenes, and degenerated quality caused by noisy pseudo-labels for dynamics. To address these challenges, STORM leverages a data-driven Transformer architecture that directly infers dynamic 3D scene representations--parameterized by 3D Gaussians and their velocities--in a single forward pass. Our key design is to aggregate 3D Gaussians from all frames using self-supervised scene flows, transforming them to the target timestep to enable complete (i.e., "amodal") reconstructions from arbitrary viewpoints at any moment in time. As an emergent property, STORM automatically captures dynamic instances and generates high-quality masks using only reconstruction losses. Extensive experiments on public datasets show that STORM achieves precise dynamic scene reconstruction, surpassing state-of-the-art per-scene optimization methods (+4.3 to 6.6 PSNR) and existing feed-forward approaches (+2.1 to 4.7 PSNR) in dynamic regions. STORM reconstructs large-scale outdoor scenes in 200ms, supports real-time rendering, and outperforms competitors in scene flow estimation, improving 3D EPE by 0.422m and Acc5 by 28.02%. Beyond reconstruction, we showcase four additional applications of our model, illustrating the potential of self-supervised learning for broader dynamic scene understanding.

cs.CV↗

arXiv2024

CogAgent: A Visual Language Model for GUI Agents

People are spending an enormous amount of time on digital devices through graphical user interfaces (GUIs), e.g., computer or smartphone screens. Large language models (LLMs) such as ChatGPT can assist people in tasks like writing emails, but struggle to understand and interact with GUIs, thus limiting their potential to increase automation levels. In this paper, we introduce CogAgent, an 18-billion-parameter visual language model (VLM) specializing in GUI understanding and navigation. By utilizing both low-resolution and high-resolution image encoders, CogAgent supports input at a resolution of 1120*1120, enabling it to recognize tiny page elements and text. As a generalist visual language model, CogAgent achieves the state of the art on five text-rich and four general VQA benchmarks, including VQAv2, OK-VQA, Text-VQA, ST-VQA, ChartQA, infoVQA, DocVQA, MM-Vet, and POPE. CogAgent, using only screenshots as input, outperforms LLM-based methods that consume extracted HTML text on both PC and Android GUI navigation tasks -- Mind2Web and AITW, advancing the state of the art. The model and codes are available at https://github.com/THUDM/CogVLM, with a new version of CogAgent-9B-20241220 available at https://github.com/THUDM/CogAgent.

cs.CV↗

arXiv2024

Enhancing tripartite photon-phonon-magnon entanglement by synergizing parametric amplifications

Tripartite entanglement as a remarkable resource in quantum information science has been extensively investigated in hybrid quantum systems, whereas it is generally weak and prone to be suppressed by noise, restricting its practical application in quantum technologies. Here, we propose how to enhance the tripartite entanglement among magnons, photons and phonons in a hybrid cavity-magnon optomechanical system by exploiting a synergistic effect of the optical parametric amplification (OPA) and mechanical parametric amplification (MPA). We find that in the case of individually applying the OPA or MPA, the tripartite entanglement can be enhanced by several folds. Remarkably, upon suitably tuning the phase matching of the two parametric fields presented simultaneously, the strengths of the entanglement can be further enhanced due to the constructive interference between the OPA and MPA. We also show that our method can improve the robustness of the entanglement against thermal noise. Our work provides a promising method for manipulating the entanglement with easy tunability and may serve as a useful tool for the enhancement and protection of fragile quantum resources.

quant-ph↗

arXiv2024

On Completely Edge-Independent Spanning Trees in Locally Twisted Cubes

A network can contain numerous spanning trees. If two spanning trees $T_i,T_j$ do not share any common edges, $T_i$ and $T_j$ are said to be pairwisely edge-disjoint. For spanning trees $T_1, T_2, ..., T_m$, if every two of them are pairwisely edge-disjoint, they are called completely edge-independent spanning trees (CEISTs for short). CEISTs can facilitate many network functionalities, and constructing CEISTs as maximally allowed as possible in a given network is a worthy undertaking. In this paper, we establish the maximal number of CEISTs in the locally twisted cube network, and propose an algorithm to construct $\lfloor \frac{n}{2} \rfloor$ CEISTs in $LTQ_n$, the $n$-dimensional locally twisted cube. The proposed algorithm has been actually implemented, and we present the outputs. Network broadcasting in the $LTQ_n$ was simulated using $\lfloor\frac{n}{2}\rfloor$ CEISTs, and the performance compared with broadcasting using a single tree.

cs.DC↗

arXiv2024

Multimodal Hypothetical Summary for Retrieval-based Multi-image Question Answering

Retrieval-based multi-image question answering (QA) task involves retrieving multiple question-related images and synthesizing these images to generate an answer. Conventional "retrieve-then-answer" pipelines often suffer from cascading errors because the training objective of QA fails to optimize the retrieval stage. To address this issue, we propose a novel method to effectively introduce and reference retrieved information into the QA. Given the image set to be retrieved, we employ a multimodal large language model (visual perspective) and a large language model (textual perspective) to obtain multimodal hypothetical summary in question-form and description-form. By combining visual and textual perspectives, MHyS captures image content more specifically and replaces real images in retrieval, which eliminates the modality gap by transforming into text-to-text retrieval and helps improve retrieval. To more advantageously introduce retrieval with QA, we employ contrastive learning to align queries (questions) with MHyS. Moreover, we propose a coarse-to-fine strategy for calculating both sentence-level and word-level similarity scores, to further enhance retrieval and filter out irrelevant details. Our approach achieves a 3.7% absolute improvement over state-of-the-art methods on RETVQA and a 14.5% improvement over CLIP. Comprehensive experiments and detailed ablation studies demonstrate the superiority of our method.

cs.CV↗

arXiv2024

How phonon coherence develops and contributes to heat conduction in periodic and aperiodic superlattices

This work investigates the impact of device length on thermal conductivity in periodic and aperiodic superlattices (SLs). While it is well known that thermal conductivity in aperiodic SLs exhibits a weaker dependence on device length compared to periodic SLs, existing literature attributes this behavior to the scattering of coherent phonons by aperiodically arranged interfaces. Through atomistic wave-packet simulations, we show that coherent phonons in aperiodic SLs have spatial extensions limited to a certain number of SL layers, which prevents transmission if the extension is shorter than the device length. Specifically, the disordered interface spacing in aperiodic SLs causes coherent phonons to behave as non-propagative vibrational modes, resulting in diffuse energy transmission. In periodic SLs, however, coherent phonons can propagate across the entire structure, enabling high transmission. The difference between ballistic transport in periodic SLs and diffuse transport in aperiodic SLs is captured in the length-dependence of phonon transmission. These findings provide new insights into phonon coherence and its implications for heat conduction in superlattices, with potential applications in the thermal design of nanostructures.

cond-mat.mtrl-sci↗

arXiv2024

Rapid Bayesian Seismic Tomography using Graph Mixture Density Networks

Seismic tomography is a methodology to image subsurface properties of the Earth. In order to better interpret the resulting images, it is important to assess uncertainty in the results. Mixture density networks (MDNs) provide an efficient way to estimate Bayesian posterior probability density functions (pdfs) that describe the uncertainty of tomographic images. However, the method can only be applied in cases where the number of data is fixed, and consequently a large number of practical applications that have variable data sizes cannot be solved. To resolve this issue, we introduce graph neural networks (GNNs) to solve seismic tomographic problems. Graphs are data structure which provides flexible representation of complex, variable systems. GNNs are neural networks that manipulates graph data, and can be combined with MDNs (called graph MDNs) to provide efficient estimates of posterior pdfs for graph data. In this study we apply graph MDNs to seismic tomography by representing travel time data with a graph. We demonstrate the method using both synthetic and real data, and compare the results with those obtained using Markov chain Monte Carlo (McMC). The results show that graph MDNs can provide comparable posterior pdfs to those obtained using McMC at significantly lower cost. We thus conclude that graph MDNs can be used in a range of practical applications that require many similar seismic tomographic problems with different number of data to be solved.

physics.geo-ph↗

arXiv2024

DiffuBox: Refining 3D Object Detection with Point Diffusion

Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving. Recent models, however, face difficulties in maintaining high performance when applied to domains with differing sensor setups or geographic locations, often resulting in poor localization accuracy due to domain shift. To overcome this challenge, we introduce a novel diffusion-based box refinement approach. This method employs a domain-agnostic diffusion model, conditioned on the LiDAR points surrounding a coarse bounding box, to simultaneously refine the box's location, size, and orientation. We evaluate this approach under various domain adaptation settings, and our results reveal significant improvements across different datasets, object classes and detectors. Our PyTorch implementation is available at \href{https://github.com/cxy1997/DiffuBox}{https://github.com/cxy1997/DiffuBox}.

cs.CV↗

arXiv2024

Detecting eclipsing double white dwarfs with electromagnetic and gravitational waves

Galactic double white dwarfs are predominant sources of gravitational waves in the millihertz frequencies accessible to space-borne gravitational wave detectors. With advances in multi-messenger astronomy, an increasing number of double white dwarf systems will be discovered through both electromagnetic and gravitational wave observations. In this paper, we simulated two populations of double white dwarfs originating from different star formation histories (hereafter referred to as Model 1 and Model 2) using the binary population synthesis method. We predicted the number of double white dwarfs in our Galaxy detectable by TianQin and Laser Interferometer Space Antenna (LISA) individually, as well as through their joint observation. In addition, we performed an analysis to evaluate the accuracy of the parameter estimation using the Fisher information matrix. Furthermore, we predicted the number of detached eclipsing double white dwarfs detectable by Gaia and the Vera C. Rubin Observatory (VRO). Our study found that over the nominal mission durations, TianQin, LISA, and their joint observation can detect at least five thousand and potentially several tens of thousands of double white dwarfs with signal-to-noise ratios greater than 7. Gaia and VRO are expected to detect at least several dozen and up to several hundred eclipsing double white dwarfs with orbital periods less than 30 hours. We also found that several dozen eclipsing double white dwarfs can be detected jointly through electromagnetic and gravitational wave observations.

astro-ph.SR↗

arXiv2024

Progressive Vision-Language Prompt for Multi-Organ Multi-Class Cell Semantic Segmentation with Single Branch

Pathological cell semantic segmentation is a fundamental technology in computational pathology, essential for applications like cancer diagnosis and effective treatment. Given that multiple cell types exist across various organs, with subtle differences in cell size and shape, multi-organ, multi-class cell segmentation is particularly challenging. Most existing methods employ multi-branch frameworks to enhance feature extraction, but often result in complex architectures. Moreover, reliance on visual information limits performance in multi-class analysis due to intricate textural details. To address these challenges, we propose a Multi-OrgaN multi-Class cell semantic segmentation method with a single brancH (MONCH) that leverages vision-language input. Specifically, we design a hierarchical feature extraction mechanism to provide coarse-to-fine-grained features for segmenting cells of various shapes, including high-frequency, convolutional, and topological features. Inspired by the synergy of textual and multi-grained visual features, we introduce a progressive prompt decoder to harmonize multimodal information, integrating features from fine to coarse granularity for better context capture. Extensive experiments on the PanNuke dataset, which has significant class imbalance and subtle cell size and shape variations, demonstrate that MONCH outperforms state-of-the-art cell segmentation methods and vision-language models. Codes and implementations will be made publicly available.

cs.CV↗

arXiv2024

A Semi-Supervised Approach with Error Reflection for Echocardiography Segmentation

Segmenting internal structure from echocardiography is essential for the diagnosis and treatment of various heart diseases. Semi-supervised learning shows its ability in alleviating annotations scarcity. While existing semi-supervised methods have been successful in image segmentation across various medical imaging modalities, few have attempted to design methods specifically addressing the challenges posed by the poor contrast, blurred edge details and noise of echocardiography. These characteristics pose challenges to the generation of high-quality pseudo-labels in semi-supervised segmentation based on Mean Teacher. Inspired by human reflection on erroneous practices, we devise an error reflection strategy for echocardiography semi-supervised segmentation architecture. The process triggers the model to reflect on inaccuracies in unlabeled image segmentation, thereby enhancing the robustness of pseudo-label generation. Specifically, the strategy is divided into two steps. The first step is called reconstruction reflection. The network is tasked with reconstructing authentic proxy images from the semantic masks of unlabeled images and their auxiliary sketches, while maximizing the structural similarity between the original inputs and the proxies. The second step is called guidance correction. Reconstruction error maps decouple unreliable segmentation regions. Then, reliable data that are more likely to occur near high-density areas are leveraged to guide the optimization of unreliable data potentially located around decision boundaries. Additionally, we introduce an effective data augmentation strategy, termed as multi-scale mixing up strategy, to minimize the empirical distribution gap between labeled and unlabeled images and perceive diverse scales of cardiac anatomical structures. Extensive experiments demonstrate the competitiveness of the proposed method.

eess.IV↗

arXiv2024

DIVD: Deblurring with Improved Video Diffusion Model

Video deblurring presents a considerable challenge owing to the complexity of blur, which frequently results from a combination of camera shakes, and object motions. In the field of video deblurring, many previous works have primarily concentrated on distortion-based metrics, such as PSNR. However, this approach often results in a weak correlation with human perception and yields reconstructions that lack realism. Diffusion models and video diffusion models have respectively excelled in the fields of image and video generation, particularly achieving remarkable results in terms of image authenticity and realistic perception. However, due to the computational complexity and challenges inherent in adapting diffusion models, there is still uncertainty regarding the potential of video diffusion models in video deblurring tasks. To explore the viability of video diffusion models in the task of video deblurring, we introduce a diffusion model specifically for this purpose. In this field, leveraging highly correlated information between adjacent frames and addressing the challenge of temporal misalignment are crucial research directions. To tackle these challenges, many improvements based on the video diffusion model are introduced in this work. As a result, our model outperforms existing models and achieves state-of-the-art results on a range of perceptual metrics. Our model preserves a significant amount of detail in the images while maintaining competitive distortion metrics. Furthermore, to the best of our knowledge, this is the first time the diffusion model has been applied in video deblurring to overcome the limitations mentioned above.

cs.CV↗

arXiv2024

CDEMapper: Enhancing NIH Common Data Element Normalization using Large Language Models

Common Data Elements (CDEs) standardize data collection and sharing across studies, enhancing data interoperability and improving research reproducibility. However, implementing CDEs presents challenges due to the broad range and variety of data elements. This study aims to develop an effective and efficient mapping tool to bridge the gap between local data elements and National Institutes of Health (NIH) CDEs. We propose CDEMapper, a large language model (LLM) powered mapping tool designed to assist in mapping local data elements to NIH CDEs. CDEMapper has three core modules: (1) CDE indexing and embeddings. NIH CDEs were indexed and embedded to support semantic search; (2) CDE recommendations. The tool combines Elasticsearch (BM25 similarity methods) with state of the art GPT services to recommend candidate CDEs and their permissible values; and (3) Human review. Users review and select the NIH CDEs and values that best match their data elements and value sets. We evaluate the tool recommendation accuracy against manually annotated mapping results. CDEMapper offers a publicly available, LLM-powered, and intuitive user interface that consolidates essential and advanced mapping services into a streamlined pipeline. It provides a step by step, quality assured mapping workflow designed with a user-centered approach. The evaluation results demonstrated that augmenting BM25 with GPT embeddings and a ranker consistently enhances CDEMapper mapping accuracy in three different mapping settings across four evaluation datasets. This work opens up the potential of using LLMs to assist with CDE recommendation and human curation when aligning local data elements with NIH CDEs. Additionally, this effort enhances clinical research data interoperability and helps researchers better understand the gaps between local data elements and NIH CDEs.

cs.IR↗

arXiv2024

Semantic Data Augmentation for Long-tailed Facial Expression Recognition

Facial Expression Recognition has a wide application prospect in social robotics, health care, driver fatigue monitoring, and many other practical scenarios. Automatic recognition of facial expressions has been extensively studied by the Computer Vision research society. But Facial Expression Recognition in real-world is still a challenging task, partially due to the long-tailed distribution of the dataset. Many recent studies use data augmentation for Long-Tailed Recognition tasks. In this paper, we propose a novel semantic augmentation method. By introducing randomness into the encoding of the source data in the latent space of VAE-GAN, new samples are generated. Then, for facial expression recognition in RAF-DB dataset, we use our augmentation method to balance the long-tailed distribution. Our method can be used in not only FER tasks, but also more diverse data-hungry scenarios.

cs.CV↗

arXiv2024

RevSAM2: Prompt SAM2 for Medical Image Segmentation via Reverse-Propagation without Fine-tuning

The Segment Anything Model 2 (SAM2) has recently demonstrated exceptional performance in zero-shot prompt segmentation for natural images and videos. However, when the propagation mechanism of SAM2 is applied to medical images, it often results in spatial inconsistencies, leading to significantly different segmentation outcomes for very similar images. In this paper, we introduce RevSAM2, a simple yet effective self-correction framework that enables SAM2 to achieve superior performance in unseen 3D medical image segmentation tasks without the need for fine-tuning. Specifically, to segment a 3D query volume using a limited number of support image-label pairs that define a new segmentation task, we propose reverse propagation strategy as a query information selection mechanism. Instead of simply maintaining a first-in-first-out (FIFO) queue of memories to predict query slices sequentially, reverse propagation selects high-quality query information by leveraging support images to evaluate the quality of each predicted query slice mask. The selected high-quality masks are then used as prompts to propagate across the entire query volume, thereby enhancing generalization to unseen tasks. Notably, we are the first to explore the potential of SAM2 in label-efficient medical image segmentation without fine-tuning. Compared to fine-tuning on large labeled datasets, the label-efficient scenario provides a cost-effective alternative for medical segmentation tasks, particularly for rare diseases or when dealing with unseen classes. Experiments on four public datasets demonstrate the superiority of RevSAM2 in scenarios with limited labels, surpassing state-of-the-arts by 12.18% in Dice. The code will be released.

cs.CV↗

arXiv2024

Training an Open-Vocabulary Monocular 3D Object Detection Model without 3D Data

Open-vocabulary 3D object detection has recently attracted considerable attention due to its broad applications in autonomous driving and robotics, which aims to effectively recognize novel classes in previously unseen domains. However, existing point cloud-based open-vocabulary 3D detection models are limited by their high deployment costs. In this work, we propose a novel open-vocabulary monocular 3D object detection framework, dubbed OVM3D-Det, which trains detectors using only RGB images, making it both cost-effective and scalable to publicly available data. Unlike traditional methods, OVM3D-Det does not require high-precision LiDAR or 3D sensor data for either input or generating 3D bounding boxes. Instead, it employs open-vocabulary 2D models and pseudo-LiDAR to automatically label 3D objects in RGB images, fostering the learning of open-vocabulary monocular 3D detectors. However, training 3D models with labels directly derived from pseudo-LiDAR is inadequate due to imprecise boxes estimated from noisy point clouds and severely occluded objects. To address these issues, we introduce two innovative designs: adaptive pseudo-LiDAR erosion and bounding box refinement with prior knowledge from large language models. These techniques effectively calibrate the 3D labels and enable RGB-only training for 3D detectors. Extensive experiments demonstrate the superiority of OVM3D-Det over baselines in both indoor and outdoor scenarios. The code will be released.

cs.CV↗

arXiv2024

Global Challenge for Safe and Secure LLMs Track 1

This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks. With the increasing integration of LLMs in critical sectors such as healthcare, finance, and public administration, ensuring these models are resilient to adversarial attacks is vital for preventing misuse and upholding ethical standards. This competition focused on two distinct tracks designed to evaluate and enhance the robustness of LLM security frameworks. Track 1 tasked participants with developing automated methods to probe LLM vulnerabilities by eliciting undesirable responses, effectively testing the limits of existing safety protocols within LLMs. Participants were challenged to devise techniques that could bypass content safeguards across a diverse array of scenarios, from offensive language to misinformation and illegal activities. Through this process, Track 1 aimed to deepen the understanding of LLM vulnerabilities and provide insights for creating more resilient models.

cs.CR↗

arXiv2024

Boosting Open-Domain Continual Learning via Leveraging Intra-domain Category-aware Prototype

Despite recent progress in enhancing the efficacy of Open-Domain Continual Learning (ODCL) in Vision-Language Models (VLM), failing to (1) correctly identify the Task-ID of a test image and (2) use only the category set corresponding to the Task-ID, while preserving the knowledge related to each domain, cannot address the two primary challenges of ODCL: forgetting old knowledge and maintaining zero-shot capabilities, as well as the confusions caused by category-relatedness between domains. In this paper, we propose a simple yet effective solution: leveraging intra-domain category-aware prototypes for ODCL in CLIP (DPeCLIP), where the prototype is the key to bridging the above two processes. Concretely, we propose a training-free Task-ID discriminator method, by utilizing prototypes as classifiers for identifying Task-IDs. Furthermore, to maintain the knowledge corresponding to each domain, we incorporate intra-domain category-aware prototypes as domain prior prompts into the training process. Extensive experiments conducted on 11 different datasets demonstrate the effectiveness of our approach, achieving 2.37% and 1.14% average improvement in class-incremental and task-incremental settings, respectively.

cs.CV↗