arXiv subjects

Chen Wang

Publications and source records attributed to Chen Wang.

At least 379 records · Page 21Linked to original sources

arXiv2024

ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback

Recent progress in imitation learning from human demonstrations has shown promising results in teaching robots manipulation skills. To further scale up training datasets, recent works start to use portable data collection devices without the need for physical robot hardware. However, due to the absence of on-robot feedback during data collection, the data quality depends heavily on user expertise, and many devices are limited to specific robot embodiments. We propose ARCap, a portable data collection system that provides visual feedback through augmented reality (AR) and haptic warnings to guide users in collecting high-quality demonstrations. Through extensive user studies, we show that ARCap enables novice users to collect robot-executable data that matches robot kinematics and avoids collisions with the scenes. With data collected from ARCap, robots can perform challenging tasks, such as manipulation in cluttered environments and long-horizon cross-embodiment manipulation. ARCap is fully open-source and easy to calibrate; all components are built from off-the-shelf products. More details and results can be found on our website: https://stanford-tml.github.io/ARCap

cs.RO↗

arXiv2024

The Observed O VI is Just the Tip of the Iceberg: Estimating the Hidden Material in Circumgalactic and Intergalactic Clouds

This paper proposes a new method for estimating the total quantity of material in moving circumgalactic and intergalactic clouds from O VI measurements. We simulate high-velocity clouds (HVCs) with the FLASH hydrodynamic code and track the ionization and recombination of all ionization levels of oxygen as a function of time. We calculate the O VI/oxygen ratio ($f_{\rm O VI}$) in our dynamic NEI clouds, finding that it differs significantly from that in static gas. We find that O VI exists in cool, medium, and hot gas in the clouds. As such, it traces all of the hydrogen rather than merely the ionized hydrogen. The total quantity of hydrogen along a typical observed line of sight through a cloud can be estimated from the observed O VI column density, metallicity, and our $f_{\rm O VI}$. We provide the simulations' $f_{\rm O VI}$, a prescription for finding $f_{\rm O VI}$ for observed dynamic clouds, and a methodology for calculating the total hydrogen column density from this $f_{\rm O VI}$ and an observed O VI column density. As examples, we use our $f_{\rm O VI}$ to estimate the total hydrogen column densities along various observed sight lines through two HVCs, Complex C and the Magellanic Stream, finding that these clouds contain more material than the previous lower limits. We also extend this analysis to {low-redshift} intergalactic O VI clouds, finding that they contain several times more baryonic material than previously thought and therefore may account for a significant fraction of the Universe's baryons.

astro-ph.GA↗

arXiv2024

Toward General-Purpose Robots via Foundation Models: A Survey and Meta-Analysis

Building general-purpose robots that operate seamlessly in any environment, with any object, and utilizing various skills to complete diverse tasks has been a long-standing goal in Artificial Intelligence. However, as a community, we have been constraining most robotic systems by designing them for specific tasks, training them on specific datasets, and deploying them within specific environments. These systems require extensively-labeled data and task-specific models. When deployed in real-world scenarios, such systems face several generalization issues and struggle to remain robust to distribution shifts. Motivated by the impressive open-set performance and content generation capabilities of web-scale, large-capacity pre-trained models (i.e., foundation models) in research fields such as Natural Language Processing (NLP) and Computer Vision (CV), we devote this survey to exploring (i) how these existing foundation models from NLP and CV can be applied to the field of general-purpose robotics, and also exploring (ii) what a robotics-specific foundation model would look like. We begin by providing a generalized formulation of how foundation models are used in robotics, and the fundamental barriers to making generalist robots universally applicable. Next, we establish a taxonomy to discuss current work exploring ways to leverage existing foundation models for robotics and develop ones catered to robotics. Finally, we discuss key challenges and promising future directions in using foundation models for enabling general-purpose robotic systems. We encourage readers to view our living GitHub repository 2 of resources, including papers reviewed in this survey, as well as related projects and repositories for developing foundation models for robotics.

cs.RO↗

arXiv2024

Multimodal Alignment of Histopathological Images Using Cell Segmentation and Point Set Matching for Integrative Cancer Analysis

Histopathological imaging is vital for cancer research and clinical practice, with multiplexed Immunofluorescence (MxIF) and Hematoxylin and Eosin (H&E) providing complementary insights. However, aligning different stains at the cell level remains a challenge due to modality differences. In this paper, we present a novel framework for multimodal image alignment using cell segmentation outcomes. By treating cells as point sets, we apply Coherent Point Drift (CPD) for initial alignment and refine it with Graph Matching (GM). Evaluated on ovarian cancer tissue microarrays (TMAs), our method achieves high alignment accuracy, enabling integration of cell-level features across modalities and generating virtual H&E images from MxIF data for enhanced clinical interpretation.

eess.IV↗

arXiv2024

A House United Within Itself: SLO-Awareness for On-Premises Containerized ML Inference Clusters via Faro

This paper tackles the challenge of running multiple ML inference jobs (models) under time-varying workloads, on a constrained on-premises production cluster. Our system Faro takes in latency Service Level Objectives (SLOs) for each job, auto-distills them into utility functions, "sloppifies" these utility functions to make them amenable to mathematical optimization, automatically predicts workload via probabilistic prediction, and dynamically makes implicit cross-job resource allocations, in order to satisfy cluster-wide objectives, e.g., total utility, fairness, and other hybrid variants. A major challenge Faro tackles is that using precise utilities and high-fidelity predictors, can be too slow (and in a sense too precise!) for the fast adaptation we require. Faro's solution is to "sloppify" (relax) its multiple design components to achieve fast adaptation without overly degrading solution quality. Faro is implemented in a stack consisting of Ray Serve running atop a Kubernetes cluster. Trace-driven cluster deployments show that Faro achieves 2.3$\times$-23$\times$ lower SLO violations compared to state-of-the-art systems.

cs.DC↗

arXiv2024

Empowering Agrifood System with Artificial Intelligence: A Survey of the Progress, Challenges and Opportunities

With the world population rapidly increasing, transforming our agrifood systems to be more productive, efficient, safe, and sustainable is crucial to mitigate potential food shortages. Recently, artificial intelligence (AI) techniques such as deep learning (DL) have demonstrated their strong abilities in various areas, including language, vision, remote sensing (RS), and agrifood systems applications. However, the overall impact of AI on agrifood systems remains unclear. In this paper, we thoroughly review how AI techniques can transform agrifood systems and contribute to the modern agrifood industry. Firstly, we summarize the data acquisition methods in agrifood systems, including acquisition, storage, and processing techniques. Secondly, we present a progress review of AI methods in agrifood systems, specifically in agriculture, animal husbandry, and fishery, covering topics such as agrifood classification, growth monitoring, yield prediction, and quality assessment. Furthermore, we highlight potential challenges and promising research opportunities for transforming modern agrifood systems with AI. We hope this survey could offer an overall picture to newcomers in the field and serve as a starting point for their further research. The project website is https://github.com/Frenkie14/Agrifood-Survey.

cs.AI↗

arXiv2024

Generating Is Believing: Membership Inference Attacks against Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) is a state-of-the-art technique that mitigates issues such as hallucinations and knowledge staleness in Large Language Models (LLMs) by retrieving relevant knowledge from an external database to assist in content generation. Existing research has demonstrated potential privacy risks associated with the LLMs of RAG. However, the privacy risks posed by the integration of an external database, which often contains sensitive data such as medical records or personal identities, have remained largely unexplored. In this paper, we aim to bridge this gap by focusing on membership privacy of RAG's external database, with the aim of determining whether a given sample is part of the RAG's database. Our basic idea is that if a sample is in the external database, it will exhibit a high degree of semantic similarity to the text generated by the RAG system. We present S$^2$MIA, a \underline{M}embership \underline{I}nference \underline{A}ttack that utilizes the \underline{S}emantic \underline{S}imilarity between a given sample and the content generated by the RAG system. With our proposed S$^2$MIA, we demonstrate the potential to breach the membership privacy of the RAG database. Extensive experiment results demonstrate that S$^2$MIA can achieve a strong inference performance compared with five existing MIAs, and is able to escape from the protection of three representative defenses.

cs.CR↗

arXiv2024

Observation of Transient Trion Induced by Ultrafast Charge Transfer in Graphene/MoS2 Heterostructure

Van der Waals (Vdw) heterostructures constructed from TMDCs provide an ideal platform for exploring various quasiparticle behaviors, with trion-composed of neutral exciton and charged carrier-being a notable example. There are typically three methods to generate trion: electrical doping, chemical doping, and direct optical doping. The first two methods generate static trion, while the last gives rise to transient trion. Here, we present an indirect optical doping approach to generate transient trion via ultrafast charge transfer (CT) and achieve control over the trion-to-exciton ratio by adjusting CT in Gr/MoS2 heterostructure. Furthermore, we demonstrated that dynamics of the transient trion generated with this method, which shows slightly longer lifetime than that of exciton accounted for the Coulomb interactions between trion and charged defect. This study provides fresh perspectives on the construction of new quasiparticles, dynamical characterization and the control of the many-body interaction in two-dimensional structure.

cond-mat.mes-hall↗

arXiv2024

Takin: A Cohort of Superior Quality Zero-shot Speech Generation Models

With the advent of the big data and large language model era, zero-shot personalized rapid customization has emerged as a significant trend. In this report, we introduce Takin AudioLLM, a series of techniques and models, mainly including Takin TTS, Takin VC, and Takin Morphing, specifically designed for audiobook production. These models are capable of zero-shot speech production, generating high-quality speech that is nearly indistinguishable from real human speech and facilitating individuals to customize the speech content according to their own needs. Specifically, we first introduce Takin TTS, a neural codec language model that builds upon an enhanced neural speech codec and a multi-task training framework, capable of generating high-fidelity natural speech in a zero-shot way. For Takin VC, we advocate an effective content and timbre joint modeling approach to improve the speaker similarity, while advocating for a conditional flow matching based decoder to further enhance its naturalness and expressiveness. Last, we propose the Takin Morphing system with highly decoupled and advanced timbre and prosody modeling approaches, which enables individuals to customize speech production with their preferred timbre and prosody in a precise and controllable manner. Extensive experiments validate the effectiveness and robustness of our Takin AudioLLM series models. For detailed demos, please refer to https://everest-ai.github.io/takinaudiollm/.

cs.SD↗

arXiv2024

Mitigating Exposure Bias in Score-Based Generation of Molecular Conformations

Molecular conformation generation poses a significant challenge in the field of computational chemistry. Recently, Diffusion Probabilistic Models (DPMs) and Score-Based Generative Models (SGMs) are effectively used due to their capacity for generating accurate conformations far beyond conventional physics-based approaches. However, the discrepancy between training and inference rises a critical problem known as the exposure bias. While this issue has been extensively investigated in DPMs, the existence of exposure bias in SGMs and its effective measurement remain unsolved, which hinders the use of compensation methods for SGMs, including ConfGF and Torsional Diffusion as the representatives. In this work, we first propose a method for measuring exposure bias in SGMs used for molecular conformation generation, which confirms the significant existence of exposure bias in these models and measures its value. We design a new compensation algorithm Input Perturbation (IP), which is adapted from a method originally designed for DPMs only. Experimental results show that by introducing IP, SGM-based molecular conformation models can significantly improve both the accuracy and diversity of the generated conformations. Especially by using the IP-enhanced Torsional Diffusion model, we achieve new state-of-the-art performance on the GEOM-Drugs dataset and are on par on GEOM-QM9. We provide the code publicly at https://github.com/jia-975/torsionalDiff-ip.

cs.LG↗

arXiv2024

Assessing Reusability of Deep Learning-Based Monotherapy Drug Response Prediction Models Trained with Omics Data

Cancer drug response prediction (DRP) models present a promising approach towards precision oncology, tailoring treatments to individual patient profiles. While deep learning (DL) methods have shown great potential in this area, models that can be successfully translated into clinical practice and shed light on the molecular mechanisms underlying treatment response will likely emerge from collaborative research efforts. This highlights the need for reusable and adaptable models that can be improved and tested by the wider scientific community. In this study, we present a scoring system for assessing the reusability of prediction DRP models, and apply it to 17 peer-reviewed DL-based DRP models. As part of the IMPROVE (Innovative Methodologies and New Data for Predictive Oncology Model Evaluation) project, which aims to develop methods for systematic evaluation and comparison DL models across scientific domains, we analyzed these 17 DRP models focusing on three key categories: software environment, code modularity, and data availability and preprocessing. While not the primary focus, we also attempted to reproduce key performance metrics to verify model behavior and adaptability. Our assessment of 17 DRP models reveals both strengths and shortcomings in model reusability. To promote rigorous practices and open-source sharing, we offer recommendations for developing and sharing prediction models. Following these recommendations can address many of the issues identified in this study, improving model reusability without adding significant burdens on researchers. This work offers the first comprehensive assessment of reusability and reproducibility across diverse DRP models, providing insights into current model sharing practices and promoting standards within the DRP and broader AI-enabled scientific research community.

q-bio.BM↗

arXiv2024

PointViG: A Lightweight GNN-based Model for Efficient Point Cloud Analysis

In the domain of point cloud analysis, despite the significant capabilities of Graph Neural Networks (GNNs) in managing complex 3D datasets, existing approaches encounter challenges like high computational costs and scalability issues with extensive scenarios. These limitations restrict the practical deployment of GNNs, notably in resource-constrained environments. To address these issues, this study introduce Point<\b> Vi<\b>sion G<\b>NN (PointViG), an efficient framework for point cloud analysis. PointViG incorporates a lightweight graph convolutional module to efficiently aggregate local features and mitigate over-smoothing. For large-scale point cloud scenes, we propose an adaptive dilated graph convolution technique that searches for sparse neighboring nodes within a dilated neighborhood based on semantic correlation, thereby expanding the receptive field and ensuring computational efficiency. Experiments demonstrate that PointViG achieves performance comparable to state-of-the-art models while balancing performance and complexity. On the ModelNet40 classification task, PointViG achieved 94.3% accuracy with 1.5M parameters. For the S3DIS segmentation task, it achieved an mIoU of 71.7% with 5.3M parameters. These results underscore the potential and efficiency of PointViG in point cloud analysis.

cs.CV↗

arXiv2024

Can Large Language Models Grasp Event Signals? Exploring Pure Zero-Shot Event-based Recognition

Recent advancements in event-based zero-shot object recognition have demonstrated promising results. However, these methods heavily depend on extensive training and are inherently constrained by the characteristics of CLIP. To the best of our knowledge, this research is the first study to explore the understanding capabilities of large language models (LLMs) for event-based visual content. We demonstrate that LLMs can achieve event-based object recognition without additional training or fine-tuning in conjunction with CLIP, effectively enabling pure zero-shot event-based recognition. Particularly, we evaluate the ability of GPT-4o / 4turbo and two other open-source LLMs to directly recognize event-based visual content. Extensive experiments are conducted across three benchmark datasets, systematically assessing the recognition accuracy of these models. The results show that LLMs, especially when enhanced with well-designed prompts, significantly improve event-based zero-shot recognition performance. Notably, GPT-4o outperforms the compared models and exceeds the recognition accuracy of state-of-the-art event-based zero-shot methods on N-ImageNet by five orders of magnitude. The implementation of this paper is available at \url{https://github.com/ChrisYu-Zz/Pure-event-based-recognition-based-LLM}.

cs.CV↗

arXiv2024

Multiplex Graph Contrastive Learning with Soft Negatives

Graph Contrastive Learning (GCL) seeks to learn nodal or graph representations that contain maximal consistent information from graph-structured data. While node-level contrasting modes are dominating, some efforts commence to explore consistency across different scales. Yet, they tend to lose consistent information and be contaminated by disturbing features. Here, we introduce MUX-GCL, a novel cross-scale contrastive learning paradigm that utilizes multiplex representations as effective patches. While this learning mode minimizes contaminating noises, a commensurate contrasting strategy using positional affinities further avoids information loss by correcting false negative pairs across scales. Extensive downstream experiments demonstrate that MUX-GCL yields multiple state-of-the-art results on public datasets. Our theoretical analysis further guarantees the new objective function as a stricter lower bound of mutual information of raw input features and output embeddings, which rationalizes this paradigm. Code is available at https://github.com/MUX-GCL/Code.

cs.LG↗

arXiv2024

The First-stage F Test with Many Weak Instruments

A widely adopted approach for detecting weak instruments is to use the first-stage $F$ statistic. While this method was developed with a fixed number of instruments, its performance with many instruments remains insufficiently explored. We show that the first-stage $F$ test exhibits distorted sizes for detecting many weak instruments, regardless of the choice of pretested estimators or Wald tests. These distortions occur due to the inadequate approximation using classical noncentral Chi-squared distributions. As a byproduct of our main result, we present an alternative approach to pre-test many weak instruments with the corrected first-stage $F$ statistic. An empirical illustration with Angrist and Keueger (1991)'s returns to education data confirms its usefulness.

econ.EM↗

arXiv2024

Many-sample tests for the equality and the proportionality hypotheses between large covariance matrices

This paper proposes procedures for testing the equality hypothesis and the proportionality hypothesis involving a large number of $q$ covariance matrices of dimension $p\times p$. Under a limiting scheme where $p$, $q$ and the sample sizes from the $q$ populations grow to infinity in a proper manner, the proposed test statistics are shown to be asymptotically normal. Simulation results show that finite sample properties of the test procedures are satisfactory under both the null and alternatives. As an application, we derive a test procedure for the Kronecker product covariance specification for transposable data. Empirical analysis of datasets from the Mouse Aging Project and the 1000 Genomes Project (phase 3) is also conducted.

math.ST↗

arXiv2024

JCMT 850 $\micron$ continuum observations of density structures in the G35 molecular complex

Filaments are believed to play a key role in high-mass star formation. We present a systematic study of the filaments and their hosting clumps in the G35 molecular complex using JCMT SCUBA-2 850 $\micron$ continuum data. We identified five clouds in the complex and 91 filaments within them, some of which form 10 hub-filament systems (HFSs), each with at least 3 hub-composing filaments. We also compiled a catalogue of 350 dense clumps, 183 of which are associated with the filaments. We investigated the physical properties of the filaments and clumps, such as mass, density, and size, and their relation to star formation. We find that the global mass-length trend of the filaments is consistent with a turbulent origin, while the hub-composing filaments of high line masses ($m_{\rm l}\,>$\,230\,$\mathrm{M_{\odot}~pc^{-1}}$) in HFSs deviate from this relation, possibly due to feedback from massive star formation. We also find that the most massive and densest clumps (R\,$>$\,0.2\,pc, M\,$>35\,\mathrm{M_{\odot}}$, $\mathrmΣ>\,0.05\,\mathrm{g~cm^{-2}}$) are located in the filaments and in the hubs of HFS with the latter bearing a higher probability of occurrence of high-mass star-forming signatures, highlighting the preferential sites of HFSs for high-mass star formation. We do not find significant variation in the clump mass surface density across different evolutionary environments of the clouds, which may reflect the balance between mass accretion and stellar feedback.

astro-ph.GA↗

arXiv2024

SCARF: Scalable Continual Learning Framework for Memory-efficient Multiple Neural Radiance Fields

This paper introduces a novel continual learning framework for synthesising novel views of multiple scenes, learning multiple 3D scenes incrementally, and updating the network parameters only with the training data of the upcoming new scene. We build on Neural Radiance Fields (NeRF), which uses multi-layer perceptron to model the density and radiance field of a scene as the implicit function. While NeRF and its extensions have shown a powerful capability of rendering photo-realistic novel views in a single 3D scene, managing these growing 3D NeRF assets efficiently is a new scientific problem. Very few works focus on the efficient representation or continuous learning capability of multiple scenes, which is crucial for the practical applications of NeRF. To achieve these goals, our key idea is to represent multiple scenes as the linear combination of a cross-scene weight matrix and a set of scene-specific weight matrices generated from a global parameter generator. Furthermore, we propose an uncertain surface knowledge distillation strategy to transfer the radiance field knowledge of previous scenes to the new model. Representing multiple 3D scenes with such weight matrices significantly reduces memory requirements. At the same time, the uncertain surface distillation strategy greatly overcomes the catastrophic forgetting problem and maintains the photo-realistic rendering quality of previous scenes. Experiments show that the proposed approach achieves state-of-the-art rendering quality of continual learning NeRF on NeRF-Synthetic, LLFF, and TanksAndTemples datasets while preserving extra low storage cost.

cs.CV↗