arXiv subjects

Shiwei Wu

Publications and source records attributed to Shiwei Wu.

At least 37 records · Page 2Linked to original sources

arXiv2024

ComViewer: An Interactive Visual Tool to Help Viewers Seek Social Support in Online Mental Health Communities

Online mental health communities (OMHCs) offer rich posts and comments for viewers, who do not directly participate in the communications, to seek social support from others' experience. However, viewers could face challenges in finding helpful posts and comments and digesting the content to get needed support, as revealed in our formative study (N=10). In this work, we present an interactive visual tool named ComViewer to help viewers seek social support in OMHCs. With ComViewer, viewers can filter posts of different topics and find supportive comments via a zoomable circle packing visual component that adapts to searched keywords. Powered by LLM, ComViewer supports an interactive sensemaking process by enabling viewers to interactively highlight, summarize, and question any community content. A within-subjects study (N=20) demonstrates ComViewer's strengths in providing viewers with a more simplified, more fruitful, and more engaging support-seeking experience compared to a baseline OMHC interface without ComViewer. We further discuss design implications for facilitating information-seeking and sense making in online mental health communities.

cs.HC↗

arXiv2024

ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Building Graphical User Interface (GUI) assistants holds significant promise for enhancing human workflow productivity. While most agents are language-based, relying on closed-source API with text-rich meta-information (e.g., HTML or accessibility tree), they show limitations in perceiving UI visuals as humans do, highlighting the need for GUI visual agents. In this work, we develop a vision-language-action model in digital world, namely ShowUI, which features the following innovations: (i) UI-Guided Visual Token Selection to reduce computational costs by formulating screenshots as an UI connected graph, adaptively identifying their redundant relationship and serve as the criteria for token selection during self-attention blocks; (ii) Interleaved Vision-Language-Action Streaming that flexibly unifies diverse needs within GUI tasks, enabling effective management of visual-action history in navigation or pairing multi-turn query-action sequences per screenshot to enhance training efficiency; (iii) Small-scale High-quality GUI Instruction-following Datasets by careful data curation and employing a resampling strategy to address significant data type imbalances. With above components, ShowUI, a lightweight 2B model using 256K data, achieves a strong 75.1% accuracy in zero-shot screenshot grounding. Its UI-guided token selection further reduces 33% of redundant visual tokens during training and speeds up the performance by 1.4x. Navigation experiments across web Mind2Web, mobile AITW, and online MiniWob environments further underscore the effectiveness and potential of our model in advancing GUI visual agents. The models are available at https://github.com/showlab/ShowUI.

cs.CV↗

arXiv2024

Resolving and routing the magnetic polymorphs in 2D layered antiferromagnet

Polymorphism, commonly denoting the variety of molecular or crystal structures, is a vital element in many natural science disciplines. In van der Waals layered antiferromagnets, a new type of magnetic polymorphism is allowed by having multiple layer-selective magnetic structures with the same total magnetization. However, resolving and manipulating such magnetic polymorphs remain a great challenge. Here we use the phase-resolved magnetic second-harmonic generation microscopy to elucidate such magnetic polymorphism in the 2D semiconducting layered antiferromagnet chromium sulfur bromide (CrSBr), and demonstrate how the magnetic polymorphs can be deterministically switched in an unprecedented layer-selective manner. With the nonlinear magneto-optical technique unveiling the magnetic symmetry information through the amplitude and phase of light, we could unambiguously resolve the polymorphic spin-flip transitions in CrSBr bilayers and tetralayers. Remarkably, the deterministic routing of polymorphic transitions originates from the breaking of energy degeneracy via a magnetic layer-sharing effect: the spin-flip transitions in a tetralayer are governed by the laterally extended bilayer, which acts as a control bit. We envision such controllable magnetic polymorphism to be ubiquitous for van der Waals layered antiferromagnets, and could lead to conceptually new design and construction of spintronic and opto-spintronic devices for probabilistic computation and neuromorphic engineering.

cond-mat.mes-hall↗

arXiv2024

Benchmarking Large Language Models for Conversational Question Answering in Multi-instructional Documents

Instructional documents are rich sources of knowledge for completing various tasks, yet their unique challenges in conversational question answering (CQA) have not been thoroughly explored. Existing benchmarks have primarily focused on basic factual question-answering from single narrative documents, making them inadequate for assessing a model`s ability to comprehend complex real-world instructional documents and provide accurate step-by-step guidance in daily life. To bridge this gap, we present InsCoQA, a novel benchmark tailored for evaluating large language models (LLMs) in the context of CQA with instructional documents. Sourced from extensive, encyclopedia-style instructional content, InsCoQA assesses models on their ability to retrieve, interpret, and accurately summarize procedural guidance from multiple documents, reflecting the intricate and multi-faceted nature of real-world instructional tasks. Additionally, to comprehensively assess state-of-the-art LLMs on the InsCoQA benchmark, we propose InsEval, an LLM-assisted evaluator that measures the integrity and accuracy of generated responses and procedural instructions.

cs.CL↗

arXiv2024

Magnetostatic effect on spin dynamics properties in antiferromagnetic Van der Waals material CrSBr

Van der Waals (vdW) antiferromagnets are exceptional platforms for exploring the spin dynamics of antiferromagnetic materials owing to their weak interlayer exchange coupling. In this study, we examined the antiferromagnetic resonance spectra of anisotropic Van der Waals antiferromagnet CrSBr. In addition to the ordinary resonance modes, we observed a dipolar spin wave mode when the microwave field was oriented perpendicular to the in-plane easy axis of CrSBr. Furthermore, our results uncovered a pronounced dependency of various resonant modes on the orientation of the microwave field, which is pivotal for the accurate determination of exchange coupling constants. Numerical simulations have elucidated this orientation dependence of spin dynamics arises from the magnetostatic effect. This discovery underscores the previously underappreciated significance of dipolar interactions in shaping the dynamical properties of two-dimensional AFM materials, thereby enhancing our understanding of the intrinsic dynamic properties of vdW magnets.

cond-mat.mtrl-sci↗

arXiv2024

VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation

A well-known dilemma in large vision-language models (e.g., GPT-4, LLaVA) is that while increasing the number of vision tokens generally enhances visual understanding, it also significantly raises memory and computational costs, especially in long-term, dense video frame streaming scenarios. Although learnable approaches like Q-Former and Perceiver Resampler have been developed to reduce the vision token burden, they overlook the context causally modeled by LLMs (i.e., key-value cache), potentially leading to missed visual cues when addressing user queries. In this paper, we introduce a novel approach to reduce vision compute by leveraging redundant vision tokens "skipping layers" rather than decreasing the number of vision tokens. Our method, VideoLLM-MoD, is inspired by mixture-of-depths LLMs and addresses the challenge of numerous vision tokens in long-term or streaming video. Specifically, for each transformer layer, we learn to skip the computation for a high proportion (e.g., 80\%) of vision tokens, passing them directly to the next layer. This approach significantly enhances model efficiency, achieving approximately \textasciitilde42\% time and \textasciitilde30\% memory savings for the entire training. Moreover, our method reduces the computation in the context and avoid decreasing the vision tokens, thus preserving or even improving performance compared to the vanilla model. We conduct extensive experiments to demonstrate the effectiveness of VideoLLM-MoD, showing its state-of-the-art results on multiple benchmarks, including narration, forecasting, and summarization tasks in COIN, Ego4D, and Ego-Exo4D datasets.

cs.CV↗

arXiv2024

Leveraging Entity Information for Cross-Modality Correlation Learning: The Entity-Guided Multimodal Summarization

The rapid increase in multimedia data has spurred advancements in Multimodal Summarization with Multimodal Output (MSMO), which aims to produce a multimodal summary that integrates both text and relevant images. The inherent heterogeneity of content within multimodal inputs and outputs presents a significant challenge to the execution of MSMO. Traditional approaches typically adopt a holistic perspective on coarse image-text data or individual visual objects, overlooking the essential connections between objects and the entities they represent. To integrate the fine-grained entity knowledge, we propose an Entity-Guided Multimodal Summarization model (EGMS). Our model, building on BART, utilizes dual multimodal encoders with shared weights to process text-image and entity-image information concurrently. A gating mechanism then combines visual data for enhanced textual summary generation, while image selection is refined through knowledge distillation from a pre-trained vision-language model. Extensive experiments on public MSMO dataset validate the superiority of the EGMS method, which also prove the necessity to incorporate entity information into MSMO problem.

cs.CV↗

arXiv2024

VideoLLM-online: Online Video Large Language Model for Streaming Video

Recent Large Language Models have been enhanced with vision capabilities, enabling them to comprehend images, videos, and interleaved vision-language content. However, the learning methods of these large multimodal models typically treat videos as predetermined clips, making them less effective and efficient at handling streaming video inputs. In this paper, we propose a novel Learning-In-Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time conversation within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training objective designed to perform language modeling for continuous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming dialogue format, and (3) an optimized inference pipeline to speed up the model responses in real-world video streams. With our LIVE framework, we built VideoLLM-online model upon Llama-2/Llama-3 and demonstrate its significant advantages in processing streaming videos. For instance, on average, our model can support streaming dialogue in a 5-minute video clip at over 10 FPS on an A100 GPU. Moreover, it also showcases state-of-the-art performance on public offline video benchmarks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at https://showlab.github.io/videollm-online.

cs.CV↗

arXiv2024

From a Social Cognitive Perspective: Context-aware Visual Social Relationship Recognition

People's social relationships are often manifested through their surroundings, with certain objects or interactions acting as symbols for specific relationships, e.g., wedding rings, roses, hugs, or holding hands. This brings unique challenges to recognizing social relationships, requiring understanding and capturing the essence of these contexts from visual appearances. However, current methods of social relationship understanding rely on the basic classification paradigm of detected persons and objects, which fails to understand the comprehensive context and often overlooks decisive social factors, especially subtle visual cues. To highlight the social-aware context and intricate details, we propose a novel approach that recognizes \textbf{Con}textual \textbf{So}cial \textbf{R}elationships (\textbf{ConSoR}) from a social cognitive perspective. Specifically, to incorporate social-aware semantics, we build a lightweight adapter upon the frozen CLIP to learn social concepts via our novel multi-modal side adapter tuning mechanism. Further, we construct social-aware descriptive language prompts (e.g., scene, activity, objects, emotions) with social relationships for each image, and then compel ConSoR to concentrate more intensively on the decisive visual social factors via visual-linguistic contrasting. Impressively, ConSoR outperforms previous methods with a 12.2\% gain on the People-in-Social-Context (PISC) dataset and a 9.8\% increase on the People-in-Photo-Album (PIPA) benchmark. Furthermore, we observe that ConSoR excels at finding critical visual evidence to reveal social relationships.

cs.CV↗

arXiv2024

NoteLLM: A Retrievable Large Language Model for Note Recommendation

People enjoy sharing "notes" including their experiences within online communities. Therefore, recommending notes aligned with user interests has become a crucial task. Existing online methods only input notes into BERT-based models to generate note embeddings for assessing similarity. However, they may underutilize some important cues, e.g., hashtags or categories, which represent the key concepts of notes. Indeed, learning to generate hashtags/categories can potentially enhance note embeddings, both of which compress key note information into limited content. Besides, Large Language Models (LLMs) have significantly outperformed BERT in understanding natural languages. It is promising to introduce LLMs into note recommendation. In this paper, we propose a novel unified framework called NoteLLM, which leverages LLMs to address the item-to-item (I2I) note recommendation. Specifically, we utilize Note Compression Prompt to compress a note into a single special token, and further learn the potentially related notes' embeddings via a contrastive learning approach. Moreover, we use NoteLLM to summarize the note and generate the hashtag/category automatically through instruction tuning. Extensive validations on real scenarios demonstrate the effectiveness of our proposed method compared with the online baseline and show major improvements in the recommendation system of Xiaohongshu.

cs.IR↗

arXiv2024

Communication-Efficient Distributed Learning with Local Immediate Error Compensation

Gradient compression with error compensation has attracted significant attention with the target of reducing the heavy communication overhead in distributed learning. However, existing compression methods either perform only unidirectional compression in one iteration with higher communication cost, or bidirectional compression with slower convergence rate. In this work, we propose the Local Immediate Error Compensated SGD (LIEC-SGD) optimization algorithm to break the above bottlenecks based on bidirectional compression and carefully designed compensation approaches. Specifically, the bidirectional compression technique is to reduce the communication cost, and the compensation technique compensates the local compression error to the model update immediately while only maintaining the global error variable on the server throughout the iterations to boost its efficacy. Theoretically, we prove that LIEC-SGD is superior to previous works in either the convergence rate or the communication cost, which indicates that LIEC-SGD could inherit the dual advantages from unidirectional compression and bidirectional compression. Finally, experiments of training deep neural networks validate the effectiveness of the proposed LIEC-SGD algorithm.

cs.LG↗

arXiv2023

Extrinsic nonlinear Kerr rotation in topological materials under a magnetic field

Topological properties in quantum materials are often governed by symmetry and tuned by crystal structure and external fields, and hence symmetry-sensitive nonlinear optical measurements in a magnetic field are a valuable probe. Here we report nonlinear magneto-optical second harmonic generation (SHG) studies of non-magnetic topological materials including bilayer WTe2, monolayer WSe2 and bulk TaAs. The polarization-resolved patterns of optical SHG under magnetic field show nonlinear Kerr rotation in these time-reversal symmetric materials. For materials with three-fold rotational symmetric lattice structure, the SHG polarization pattern rotates just slightly in a magnetic field, whereas in those with mirror or two-fold rotational symmetry the SHG polarization pattern rotates greatly and distorts. These different magneto-SHG characters can be understood by considering the superposition of the magnetic field-induced time-noninvariant nonlinear optical tensor and the crystal-structure-based time-invariant counterpart. The situation is further clarified by scrutinizing the Faraday rotation, whose subtle interplay with crystal symmetry accounts for the diverse behavior of the extrinsic nonlinear Kerr rotation in different materials. Our work illustrates the application of magneto-SHG techniques to directly probe nontrivial topological properties, and underlines the importance of minimizing extrinsic nonlinear Kerr rotation in polarization-resolved magneto-optical studies.

cond-mat.mes-hall↗

arXiv2023

Layer thickness crossover of type-II multiferroic magnetism in NiI2

The discovery of atomically thin van der Waals ferroelectric and magnetic materials encourages the exploration of 2D multiferroics, which holds the promise to understand fascinating magnetoelectric interactions and fabricate advanced spintronic devices. In addition to building a heterostructure consisting of ferroelectric and magnetic ingredients, thinning down layered multiferroics of spin origin such as NiI2 becomes a natural route to realize 2D multiferroicity. However, the layer-dependent behavior, widely known in the community of 2D materials, necessitates a rigorous scrutiny of the multiferroic order in the few-layer limit. Here, we interrogate the layer thickness crossover of helimagnetism in NiI2 that drives the ferroelectricity and thereby type-II multiferroicity. By using wavelength-dependent polarization-resolved optical second harmonic generation (SHG) to probe the ferroic symmetry, we find that the SHG arises from the inversion-symmetry-breaking magnetic order, not previously assumed ferroelectricity. This magnetism-induced SHG is only observed in bilayer or thicker layers, and vanishes in monolayer, suggesting the critical role of interlayer exchange interaction in breaking the degeneracy of geometrically frustrated spin structures in triangular lattice and stabilizing the type-II multiferroic magnetism in few-layers. While the helimagnetic transition temperature is layer dependent, the few-layer NiI2 exhibits another thickness evolution and reaches the bulk-like behavior in trilayer, indicated by the intermediate centrosymmetric antiferromagnetic state as revealed in Raman spectroscopy. Our work therefore highlights the magnetic contribution to SHG and Raman spectroscopy in reduced dimension and guides the optical study of 2D multiferroics.

cond-mat.mtrl-sci↗

arXiv2023

Multi-Grained Multimodal Interaction Network for Entity Linking

Multimodal entity linking (MEL) task, which aims at resolving ambiguous mentions to a multimodal knowledge graph, has attracted wide attention in recent years. Though large efforts have been made to explore the complementary effect among multiple modalities, however, they may fail to fully absorb the comprehensive expression of abbreviated textual context and implicit visual indication. Even worse, the inevitable noisy data may cause inconsistency of different modalities during the learning process, which severely degenerates the performance. To address the above issues, in this paper, we propose a novel Multi-GraIned Multimodal InteraCtion Network $\textbf{(MIMIC)}$ framework for solving the MEL task. Specifically, the unified inputs of mentions and entities are first encoded by textual/visual encoders separately, to extract global descriptive features and local detailed features. Then, to derive the similarity matching score for each mention-entity pair, we device three interaction units to comprehensively explore the intra-modal interaction and inter-modal fusion among features of entities and mentions. In particular, three modules, namely the Text-based Global-Local interaction Unit (TGLU), Vision-based DuaL interaction Unit (VDLU) and Cross-Modal Fusion-based interaction Unit (CMFU) are designed to capture and integrate the fine-grained representation lying in abbreviated text and implicit visual cues. Afterwards, we introduce a unit-consistency objective function via contrastive learning to avoid inconsistency and model degradation. Experimental results on three public benchmark datasets demonstrate that our solution outperforms various state-of-the-art baselines, and ablation studies verify the effectiveness of designed modules.

cs.AI↗

arXiv2023

A Solution to CVPR'2023 AQTC Challenge: Video Alignment for Multi-Step Inference

Affordance-centric Question-driven Task Completion (AQTC) for Egocentric Assistant introduces a groundbreaking scenario. In this scenario, through learning instructional videos, AI assistants provide users with step-by-step guidance on operating devices. In this paper, we present a solution for enhancing video alignment to improve multi-step inference. Specifically, we first utilize VideoCLIP to generate video-script alignment features. Afterwards, we ground the question-relevant content in instructional videos. Then, we reweight the multimodal context to emphasize prominent features. Finally, we adopt GRU to conduct multi-step inference. Through comprehensive experiments, we demonstrate the effectiveness and superiority of our method, which secured the 2nd place in CVPR'2023 AQTC challenge. Our code is available at https://github.com/zcfinal/LOVEU-CVPR23-AQTC.

cs.CV↗

arXiv2023

Twist-phase-matching in two-dimensional materials

Optical phase-matching involves establishing a proper phase relationship between the fundamental and generated waves to enable efficient optical parametric processes. It is typically achieved through either birefringence or periodically assigned polarization. Here, we report that twist angle in two-dimensional (2D) materials can generate a nonlinear Berry optical phase to compensate the phase mismatch in the process of nonlinear optical frequency conversion, and the vertical assembly of 2D layers with a proper twist sequence will generate a nontrivial "twist-phase-matching" (twist-PM) regime. The twist-PM model offers superior flexibility in the design of optical crystals, which works for twisted layers with either periodic or random thickness distribution. The designed crystals from twisted rhombohedra boron nitride films give rise to a second-harmonic generation conversion efficiency of ~8% within a thickness of only 3.2 um, and a facile polarization controllability that is absent in conventional crystals (from linear to left-/right-handed circular/elliptical polarizations). Our methodology establishes a platform for the rational designing and atomic manufacturing of nonlinear optical crystals based on abundant 2D materials for various functionalities.

physics.optics↗

arXiv2023

AU-aware graph convolutional network for Macro- and Micro-expression spotting

Automatic Micro-Expression (ME) spotting in long videos is a crucial step in ME analysis but also a challenging task due to the short duration and low intensity of MEs. When solving this problem, previous works generally lack in considering the structures of human faces and the correspondence between expressions and relevant facial muscles. To address this issue for better performance of ME spotting, this paper seeks to extract finer spatial features by modeling the relationships between facial Regions of Interest (ROIs). Specifically, we propose a graph convolutional-based network, called Action-Unit-aWare Graph Convolutional Network (AUW-GCN). Furthermore, to inject prior information and to cope with the problem of small datasets, AU-related statistics are encoded into the network. Comprehensive experiments show that our results outperform baseline methods consistently and achieve new SOTA performance in two benchmark datasets,CAS(ME)^2 and SAMM-LV. Our code is available at https://github.com/xjtupanda/AUW-GCN.

cs.CV↗

arXiv2022

Evidence for unconventional superconductivity in a spinel oxide

The charge frustration with the mixed-valence state inherent to LiTi$_2$O$_4$, which is found to be a unique spinel oxide superconductor, is the impetus for paying special attention to reveal the existence of intriguing superconducting properties. Here, we report a pronounced fourfold rotational symmetry of the superconductivity in high-quality single-crystalline LiTi$_2$O$_4$ (001) thin films. Both the magnetoresistivity and upper critical field under an applied magnetic field manifest striking fourfold oscillations deep inside the superconducting state, whereas the anisotropy vanishes in the normal state, demonstrating that it is an intrinsic property of the superconducting phase. We attribute this behavior to the unconventional $d$-wave superconducting Cooper pairs with the irreducible representation of $E_g$ protected by $O_h$ point group in LiTi$_2$O$_4$. Our findings demonstrate the unconventional character of the pairing interaction in a three-dimensional spinel oxide superconductor and shed new light on the pairing mechanism of unconventional superconductivity.

cond-mat.supr-con↗