Showing 1–19 of 19 results for author: Tai, Z

FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering

Authors: Jijun Chi, Zhenghan Tai, Hanwei Wu, Tung Sum Thomas Kwok, Hailin He, Zixing Liao, Bohuai Xiao, Chaolong Jiang, Jianliang Lei, Jerry Huang, Peng Lu, Muzhi Li, Liheng Ma, Yihong Wu, Sicheng Lyu, Jingrui Tian, Yihan Li, Yanzhang Ma, Sizhe Guan, Dingtao Hu, Yufei Cui, Ling Zhou, Lei Ding, Xinyu Wang

Abstract: Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these… ▽ More Financial question answering over U.S. Securities and Exchange Commission (SEC) filings requires retrieving and synthesizing heterogeneous evidence dispersed across long, standardized, and highly redundant disclosures. Existing retrieval-augmented and multi-agent systems typically derive retrieval queries directly from the user's question and rank candidates by semantic similarity. Together, these choices create prior-corpus misalignment: a mismatch between model priors and the target filings' structure, terminology, and evidence standards. As a result, query generation misses corpus-specific evidence, while semantic reranking favors topically similar but evidentially invalid false-positive chunks. We propose FinSAgent, an evidence-grounded multi-agent framework that reframes SEC filing QA as corpus-aligned retrieval planning and corrects both ends with a single principle: inject corpus-side conditioning wherever model priors would otherwise dominate. FinSAgent combines (1) role-specialized agents anchored to the mandated 10-K item structure, (2) database-aware query decomposition that conditions each agent's sub-queries on a lightweight, summary-level view of the local corpus, and (3) multi-path retrieval with a learned feature-gated reranker that separates evidential validity from semantic similarity. Across five offline financial QA benchmarks, FinSAgent improves retrieval coverage and answer correctness over strong single-agent and multi-agent baselines; in a three-arm randomized online experiment with 1,000 anonymous user ratings, it also receives higher scores than baselines. △ Less

Submitted 21 July, 2026; v1 submitted 20 July, 2026; originally announced July 2026.

Comments: 20 pages, 14 figures, 9 tables

MSC Class: H.3.3; I.2.7; I.2.11

SafeRx-Agent: A Knowledge-Grounded Multi-Agent Framework for Safe and Explainable Medication Recommendation

Authors: Xinyu Wang, Hanwei Wu, Zhenghan Tai, Sicheng Lyu, Qincheng Lu, Ziyu Zhao, Jijun Chi, Jingrui Tian, Xiao-Wen Chang, Ziyang Song

Abstract: Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broa… ▽ More Medication recommendation predicts medications for patient visits, but existing methods still face two key challenges. At the model level, traditional drug recommendation methods only predict structured drug codes with limited evidence grounding, while LLM agents can use richer clinical context but may lack safety verification and traceability. At the task level, existing benchmarks often use broad medication categories, which ignore subgroup-level safety differences and can lead to risk overestimation. We introduce the first fine-grained medication recommendation setting based on fourth-level ATC code generation. We propose Safe Prescription Agent (SafeRx-Agent), a knowledge-grounded multi-agent framework that uses patient context, external clinical knowledge, and safety verification to recommend traceable medication sets. Experimental results on MIMIC-III and MIMIC-IV datasets show that SafeRx-Agent improves fine-grained medication prediction accuracy while controlling drug interactions, contraindications, and medication set size. △ Less

Submitted 28 May, 2026; v1 submitted 27 May, 2026; originally announced May 2026.

ACALSim: A Scalable Parallel Simulation Framework for High-Performance System Design Space Exploration

Authors: Wei-Fen Lin, Jen-Chien Chang, Yen-Po Chen, Zi-Yi Tai, Yu-Cheng Chang, Chia-Pao Chiang, Yu-Yang Lee, Yu-Jie Wan

Abstract: Architectural simulation has become the critical bottleneck limiting design space exploration for high-performance computing systems. Modern GPUs and AI accelerators -- with hundreds to thousands of tightly-coupled components -- demand simulation frameworks that deliver efficient parallelism and scalable single-node execution. Existing frameworks fall short: SST focuses on multi-node MPI scalabili… ▽ More Architectural simulation has become the critical bottleneck limiting design space exploration for high-performance computing systems. Modern GPUs and AI accelerators -- with hundreds to thousands of tightly-coupled components -- demand simulation frameworks that deliver efficient parallelism and scalable single-node execution. Existing frameworks fall short: SST focuses on multi-node MPI scalability but struggles with intra-node scaling, while GPGPU-Sim remains largely single-threaded. Critically, none expose a mechanism for users to optimize threading for their specific workloads. We introduce ACALSim, a scalable parallel simulation framework providing infrastructure and APIs for building high-performance simulators -- timing-model accuracy remains the responsibility of simulator developers. Its key innovation is a pluggable thread-management architecture that lets developers implement custom scheduling strategies tailored to specific simulation patterns, absent in existing frameworks. Complementing it are (1) event-driven execution with fast-forward to eliminate idle-cycle overhead, (2) a shared-memory data model enabling zero-copy communication, and (3) a two-phase parallel execution model for deterministic thread scaling. We demonstrate ACALSim through HPCSim, a GPU simulator targeting A100-class architectures. Against an SST implementation using identical shared timing cores to isolate framework overhead, ACALSim achieves over 14x speedup with 41% lower memory footprint; hardware validation confirms 0.72--1.22x cycle-count correlation with A100 measurements. While SST fails to complete 256+ thread-block workloads within practical time limits, ACALSim simulates full LLaMA transformer layers (single block) in 17.7 minutes for LLaMA-7B and 30.4 minutes for LLaMA-13B -- enabling design space exploration that SST cannot achieve. △ Less

Submitted 21 May, 2026; originally announced May 2026.

LLM Pretraining Shapes a Generalizable Manifold: Insights into Cross-Modal Transfer to Time Series

Authors: Alexis Roger, Prateek Humane, Zhenghan Tai, Gwen Legate, Andrei Mircea, Vasilii Feofanov, Irina Rish

Abstract: Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusable manifold. A linear probe on frozen LLM states decodes realistic time-series trajectories without paired supervision, and retrieval in this projected space yields competitive fo… ▽ More Can language-pretrained transformers become effective time-series forecasters, and why? In this paper, we show that cross-modal transfer arises because language pretraining preconditions time series training with a reusable manifold. A linear probe on frozen LLM states decodes realistic time-series trajectories without paired supervision, and retrieval in this projected space yields competitive forecasts, showing that structure and dynamics exist before finetuning. Pretrained initialization also improves optimization, producing coherent gradients and a highly anisotropic loss landscape unlike random initialization. Finetuning then acts as low-dimensional alignment, reusing existing directions rather than learning temporal primitives from scratch, as evidenced by low-rank updates, subspace alignment, and shared features for periodicity, trend, and repetition. Together, these results support a geometric account of LLM-to-time-series transfer: language pretraining builds the manifold, and finetuning projects numerical dynamics onto task-relevant directions. △ Less

Submitted 19 May, 2026; originally announced May 2026.

$\text{R}^2\text{R}$: A Route-to-Rerank Post-Training Framework for Multi-Domain Decoder-Only Rerankers

Authors: Xinyu Wang, Hanwei Wu, Qingchen Hu, Zhenghan Tai, Jingrui Tian, Lei Ding, Jijun Chi, Hailin He, Tung Sum Thomas Kwok, Yufei Cui, Sicheng Lyu, Muzhi Li, Mingze Li, Xinyue Yu, Ling Zhou, Peng Lu

Abstract: Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and naive fine-tuning causes surface-form overfitting and catastrophic forgetting. To address this challenge, we introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy… ▽ More Decoder-only rerankers are central to Retrieval-Augmented Generation (RAG). However, generalist models miss domain-specific nuances in high-stakes fields like finance and law, and naive fine-tuning causes surface-form overfitting and catastrophic forgetting. To address this challenge, we introduce R2R, a domain-aware framework that combines dynamic expert routing with a two-stage training strategy, Entity Abstraction for Generalization (EAG). EAG introduces a counter-shortcut mechanism by masking the most predictive surface cues, forcing the reranker to learn domain-invariant relevance patterns rather than memorizing dataset-specific entities. To efficiently activate domain experts, R2R employs a lightweight Latent Semantic Router that probes internal representations from the frozen backbone decoder to select the optimal LoRA expert per query. Extensive experiments across different reranker backbones and diverse domains (legal, medical, and financial) demonstrate that R2R consistently surpasses generalist and single-domain fine-tuned baselines. Our results confirm that R2R is a model-agnostic and modular approach to domain specialization with strong cross-domain robustness. △ Less

Submitted 25 November, 2025; originally announced November 2025.

Comments: 13 pages, including 3 figures and 3 tables

VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering

Authors: Zhenghan Tai, Hanwei Wu, Qingchen Hu, Jijun Chi, Hailin He, Lei Ding, Tung Sum Thomas Kwok, Bohuai Xiao, Yuchen Hua, Suyuchen Wang, Peng Lu, Muzhi Li, Yihong Wu, Liheng Ma, Jerry Huang, Jiayi Zhang, Gonghao Zhang, Chaolong Jiang, Jingrui Tian, Sicheng Lyu, Zeyu Li, Boyu Han, Fengran Mo, Xinyue Yu, Yufei Cui , et al. (2 additional authors not shown)

Abstract: Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they en… ▽ More Retrieval-Augmented Generation (RAG) is becoming increasingly essential for Question Answering (QA) in the financial sector, where accurate and contextually grounded insights from complex public disclosures are crucial. However, existing financial RAG systems face two significant challenges: (1) they struggle to process heterogeneous data formats, such as text, tables, and figures; and (2) they encounter difficulties in balancing general-domain applicability with company-specific adaptation. To overcome these challenges, we present VeritasFi, an innovative hybrid RAG framework that incorporates a multi-modal preprocessing pipeline alongside a cutting-edge two-stage training strategy for its re-ranking component. VeritasFi enhances financial QA through three key innovations: (1) A multi-modal preprocessing pipeline that seamlessly transforms heterogeneous data into a coherent, machine-readable format. (2) A tripartite hybrid retrieval engine that operates in parallel, combining deep multi-path retrieval over a semantically indexed document corpus, real-time data acquisition through tool utilization, and an expert-curated memory bank for high-frequency questions, ensuring comprehensive scope, accuracy, and efficiency. (3) A two-stage training strategy for the document re-ranker, which initially constructs a general, domain-specific model using anonymized data, followed by rapid fine-tuning on company-specific data for targeted applications. By integrating our proposed designs, VeritasFi presents a groundbreaking framework that greatly enhances the adaptability and robustness of financial RAG systems, providing a scalable solution for both general-domain and company-specific QA tasks. Code accompanying this work is available at https://github.com/simplew4y/VeritasFi.git. △ Less

Submitted 12 October, 2025; originally announced October 2025.

From Evidence to Trajectory: Abductive Reasoning Path Synthesis for Retrieval-Augmented Generation Agents Development

Authors: Muzhi Li, Jinhu Qi, Yihong Wu, Minghao Zhao, Liheng Ma, Yifan Li, Xinyu Wang, Zhenghan Tai, Zixing Song, Yingxue Zhang, Ho-fung Leung, Irwin King

Abstract: Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but often suffers from sparse… ▽ More Retrieval-augmented generation (RAG) agent development is hindered by the lack of executable ground-truth agent-environment interaction trajectories. Existing datasets provide questions, answers, and evidence, but lack fine-grained supervision for retriever invocation, dynamic planning, and stepwise decision-making. Reinforcement learning offers a potential solution, but often suffers from sparse rewards and cold-start failures when base large language models (LLMs) lack sufficient reasoning capability. Meanwhile, existing data synthesis methods mainly generate post-hoc rationales rather than executable environment-interaction trajectories. In this paper, we propose EviPath, an evidence-anchored reasoning path synthesis paradigm for RAG agent development. EviPath reverse-engineers executable trajectories from question-answer pairs and supporting evidence through three stages: (i) Abductive Subtask Planning, which decomposes questions and plans dependency-aware solution paths; (ii) Faithful Sub-question Answering, which uses supporting evidence as a proxy environment to generate grounded intermediate thoughts and answers; and (iii) Conversational Fine-Tuning, which converts complete trajectories into a dialogue format for supervised fine-tuning. Experiments on widely used question-answering benchmarks show that an 8B model trained on our synthetic corpus significantly and consistently outperforms state-of-the-art baselines, achieving a 14.7% absolute Exact Match gain in open-domain question answering. △ Less

Submitted 20 July, 2026; v1 submitted 26 September, 2025; originally announced September 2025.

Comments: KDD 2026 Research Track

Slanted light-sheet array microscopy for large volume imaging at rates exceeding 100 Hz

Authors: Kai Long, Wenkai Chen, Junming Zhou, Junyi Li, Shuhao Shen, Zhipeng Tai, Shifeng Xue, Anqi Qiu, Nanguang Chen

Abstract: High-speed image acquisition in light microscopy is essential for a wide range of applications, including observing dynamic biological processes and enabling high-throughput sample analysis. However, traditional imaging speeds are often limited by the scanning mechanisms and the signal-to-noise ratio, and these constraints are further exacerbated by the need for volumetric imaging, optical section… ▽ More High-speed image acquisition in light microscopy is essential for a wide range of applications, including observing dynamic biological processes and enabling high-throughput sample analysis. However, traditional imaging speeds are often limited by the scanning mechanisms and the signal-to-noise ratio, and these constraints are further exacerbated by the need for volumetric imaging, optical sectioning, high spatial resolution, and large fields of view. To address these challenges, we have developed a slanted light-sheet array microscope (SLAM), which enables ultrafast volumetric imaging without compromising key technical specifications. SLAM is built on a standard wide-field compound microscope with minimal and straightforward modifications to the illumination path, allowing for easy integration. It can acquire multi-dimensional, high-resolution images at rates exceeding 100 volumes per second across large imaging regions (e.g., exceeding 500 pixels in transverse dimensions and 200 layers in depth). In addition, a deep learning approach based on conditional denoising diffusion probabilistic models is proposed to achieve isotropic resolution. Like traditional light-sheet microscopy, SLAM offers intrinsic optical sectioning and localized photochemistry, while its innovative optomechanical design is compatible with most biological samples prepared using conventional protocols. This makes SLAM a versatile and powerful imaging platform that is accessible to the broader biomedical research community. △ Less

Submitted 16 June, 2025; originally announced June 2025.

Comments: 26 pages, 4 figures

STRICT: Stress Test of Rendering Images Containing Text

Authors: Tianyu Zhang, Xinyu Wang, Lu Li, Zhenghan Tai, Jijun Chi, Jingrui Tian, Hailin He, Suyuchen Wang

Abstract: While diffusion models have revolutionized text-to-image generation with their ability to synthesize realistic and diverse scenes, they continue to struggle to generate consistent and legible text within images. This shortcoming is commonly attributed to the locality bias inherent in diffusion-based generation, which limits their ability to model long-range spatial dependencies. In this paper, we… ▽ More While diffusion models have revolutionized text-to-image generation with their ability to synthesize realistic and diverse scenes, they continue to struggle to generate consistent and legible text within images. This shortcoming is commonly attributed to the locality bias inherent in diffusion-based generation, which limits their ability to model long-range spatial dependencies. In this paper, we introduce $\textbf{STRICT}$, a benchmark designed to systematically stress-test the ability of diffusion models to render coherent and instruction-aligned text in images. Our benchmark evaluates models across multiple dimensions: (1) the maximum length of readable text that can be generated; (2) the correctness and legibility of the generated text, and (3) the ratio of not following instructions for generating text. We evaluate several state-of-the-art models, including proprietary and open-source variants, and reveal persistent limitations in long-range consistency and instruction-following capabilities. Our findings provide insights into architectural bottlenecks and motivate future research directions in multimodal generative modeling. We release our entire evaluation pipeline at https://github.com/tianyu-z/STRICT-Bench. △ Less

Submitted 14 September, 2025; v1 submitted 25 May, 2025; originally announced May 2025.

Comments: Accepted as a main conference paper at EMNLP 2025

MSC Class: 68T50 ACM Class: I.2.7; I.4.0

FinSage: A Multi-aspect RAG System for Financial Filings Question Answering

Authors: Xinyu Wang, Jijun Chi, Zhenghan Tai, Tung Sum Thomas Kwok, Muzhi Li, Zhuhong Li, Hailin He, Yuchen Hua, Peng Lu, Suyuchen Wang, Yihong Wu, Jerry Huang, Jingrui Tian, Fengran Mo, Yufei Cui, Ling Zhou

Abstract: Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. Howeve… ▽ More Leveraging large language models in real-world settings often entails a need to utilize domain-specific data and tools in order to follow the complex regulations that need to be followed for acceptable use. Within financial sectors, modern enterprises increasingly rely on Retrieval-Augmented Generation (RAG) systems to address complex compliance requirements in financial document workflows. However, existing solutions struggle to account for the inherent heterogeneity of data (e.g., text, tables, diagrams) and evolving nature of regulatory standards used in financial filings, leading to compromised accuracy in critical information extraction. We propose the FinSage framework as a solution, utilizing a multi-aspect RAG framework tailored for regulatory compliance analysis in multi-modal financial documents. FinSage introduces three innovative components: (1) a multi-modal pre-processing pipeline that unifies diverse data formats and generates chunk-level metadata summaries, (2) a multi-path sparse-dense retrieval system augmented with query expansion (HyDE) and metadata-aware semantic search, and (3) a domain-specialized re-ranking module fine-tuned via Direct Preference Optimization (DPO) to prioritize compliance-critical content. Extensive experiments demonstrate that FinSage achieves an impressive recall of 92.51% on 75 expert-curated questions derived from surpasses the best baseline method on the FinanceBench question answering datasets by 24.06% in accuracy. Moreover, FinSage has been successfully deployed as financial question-answering agent in online meetings, where it has already served more than 1,200 people. △ Less

Submitted 13 August, 2025; v1 submitted 20 April, 2025; originally announced April 2025.

Comments: Accepted at the 34th ACM International Conference on Information and Knowledge Management (CIKM2025)

Tight Lower Bounds for Directed Cut Sparsification and Distributed Min-Cut

Authors: Yu Cheng, Max Li, Honghao Lin, Zi-Yi Tai, David P. Woodruff, Jason Zhang

Abstract: In this paper, we consider two fundamental cut approximation problems on large graphs. We prove new lower bounds for both problems that are optimal up to logarithmic factors. The first problem is to approximate cuts in balanced directed graphs. In this problem, the goal is to build a data structure that $(1 \pm ε)$-approximates cut values in graphs with $n$ vertices. For arbitrary directed graph… ▽ More In this paper, we consider two fundamental cut approximation problems on large graphs. We prove new lower bounds for both problems that are optimal up to logarithmic factors. The first problem is to approximate cuts in balanced directed graphs. In this problem, the goal is to build a data structure that $(1 \pm ε)$-approximates cut values in graphs with $n$ vertices. For arbitrary directed graphs, such a data structure requires $Ω(n^2)$ bits even for constant $ε$. To circumvent this, recent works study $β$-balanced graphs, meaning that for every directed cut, the total weight of edges in one direction is at most $β$ times that in the other direction. We consider two models: the {\em for-each} model, where the goal is to approximate each cut with constant probability, and the {\em for-all} model, where all cuts must be preserved simultaneously. We improve the previous $Ω(n \sqrt{β/ε})$ lower bound to $\tildeΩ(n \sqrtβ/ε)$ in the for-each model, and we improve the previous $Ω(n β/ε)$ lower bound to $Ω(n β/ε^2)$ in the for-all model. This resolves the main open questions of (Cen et al., ICALP, 2021). The second problem is to approximate the global minimum cut in a local query model, where we can only access the graph via degree, edge, and adjacency queries. We improve the previous $Ω\bigl(\frac{m}{k}\bigr)$ query complexity lower bound to $Ω\bigl(\min\{m, \frac{m}{ε^2 k}\}\bigr)$ for this problem, where $m$ is the number of edges, $k$ is the size of the minimum cut, and we seek a $(1+ε)$-approximation. In addition, we show that existing upper bounds with slight modifications match our lower bound up to logarithmic factors. △ Less

Submitted 19 June, 2024; originally announced June 2024.

New Interaction Paradigm for Complex EDA Software Leveraging GPT

Authors: Xinyu Wang, Boyu Han, Zhenghan Tai, Jingrui Tian, Yifan Wang, Junyu Yan, Yidong Tian

Abstract: Electronic Design Automation (EDA) tools such as KiCad offer powerful functionalities but remain difficult to use, particularly for beginners, due to their steep learning curves and fragmented documentation. To address this challenge, we present SmartonAI, an AI-assisted interaction system that integrates large language models into the EDA workflow, enabling natural language communication, intelli… ▽ More Electronic Design Automation (EDA) tools such as KiCad offer powerful functionalities but remain difficult to use, particularly for beginners, due to their steep learning curves and fragmented documentation. To address this challenge, we present SmartonAI, an AI-assisted interaction system that integrates large language models into the EDA workflow, enabling natural language communication, intelligent task decomposition, and contextual plugin execution. SmartonAI consists of two main components: a Chat Plugin that breaks down user instructions into subtasks and retrieves tailored documentation, and a OneCommandLine Plugin that recommends and executes relevant plugins based on user intent. The system supports multilingual interaction and adapts to user feedback through incremental learning. Preliminary results suggest that SmartonAI significantly reduces onboarding time and enhances productivity, representing a promising step toward generalizable AI-assisted interaction paradigms for complex software systems. △ Less

Submitted 18 August, 2025; v1 submitted 27 July, 2023; originally announced July 2023.

Comments: Accepted to ICML 2025 Workshop on New In Machine Learning (NewInML), 9 pages, 8 figures

Empowering NLG: Offline Reinforcement Learning for Informal Summarization in Online Domains

Authors: Zhi-Xuan Tai, Po-Chuan Chen

Abstract: Our research introduces an innovative Natural Language Generation (NLG) approach that aims to optimize user experience and alleviate the workload of human customer support agents. Our primary objective is to generate informal summaries for online articles and posts using an offline reinforcement learning technique. In our study, we compare our proposed method with existing approaches to text gener… ▽ More Our research introduces an innovative Natural Language Generation (NLG) approach that aims to optimize user experience and alleviate the workload of human customer support agents. Our primary objective is to generate informal summaries for online articles and posts using an offline reinforcement learning technique. In our study, we compare our proposed method with existing approaches to text generation and provide a comprehensive overview of our architectural design, which incorporates crawling, reinforcement learning, and text generation modules. By presenting this original approach, our paper makes a valuable contribution to the field of NLG by offering a fresh perspective on generating natural language summaries for online content. Through the implementation of Empowering NLG, we are able to generate higher-quality replies in the online domain. The experimental results demonstrate a significant improvement in the average "like" score, increasing from 0.09954378 to 0.5000152. This advancement has the potential to enhance the efficiency and effectiveness of customer support services and elevate the overall user experience when consuming online content. △ Less

Submitted 17 June, 2023; originally announced June 2023.

Comments: 14 pages, 3 figures

Graph Exploration with Embedding-Guided Layouts

Authors: Leixian Shen, Zhiwei Tai, Enya Shen, Jianmin Wang

Abstract: Node-link diagrams are widely used to visualize graphs. Most graph layout algorithms only use graph topology for aesthetic goals (e.g., minimize node occlusions and edge crossings) or use node attributes for exploration goals (e.g., preserve visible communities). Existing hybrid methods that bind the two perspectives still suffer from various generation restrictions (e.g., limited input types and… ▽ More Node-link diagrams are widely used to visualize graphs. Most graph layout algorithms only use graph topology for aesthetic goals (e.g., minimize node occlusions and edge crossings) or use node attributes for exploration goals (e.g., preserve visible communities). Existing hybrid methods that bind the two perspectives still suffer from various generation restrictions (e.g., limited input types and required manual adjustments and prior knowledge of graphs) and the imbalance between aesthetic and exploration goals. In this paper, we propose a flexible embedding-based graph exploration pipeline to enjoy the best of both graph topology and node attributes. First, we leverage embedding algorithms for attributed graphs to encode the two perspectives into latent space. Then, we present an embedding-driven graph layout algorithm, GEGraph, which can achieve aesthetic layouts with better community preservation to support an easy interpretation of the graph structure. Next, graph explorations are extended based on the generated graph layout and insights extracted from the embedding vectors. Illustrated with examples, we build a layout-preserving aggregation method with Focus+Context interaction and a related nodes searching approach with multiple proximity strategies. Finally, we conduct quantitative and qualitative evaluations, a user study, and two case studies to validate our approach. △ Less

Submitted 19 January, 2023; v1 submitted 29 August, 2022; originally announced August 2022.

Comments: accepted by TVCG

Visual Data Analysis with Task-based Recommendations

Authors: Leixian Shen, Enya Shen, Zhiwei Tai, Yihao Xu, Jianmin Wang

Abstract: General visualization recommendation systems typically make design decisions for the dataset automatically. However, most of them can only prune meaningless visualizations but fail to recommend targeted results. This paper contributes TaskVis, a task-oriented visualization recommendation system that allows users to select their tasks precisely on the interface. We first summarize a task base with… ▽ More General visualization recommendation systems typically make design decisions for the dataset automatically. However, most of them can only prune meaningless visualizations but fail to recommend targeted results. This paper contributes TaskVis, a task-oriented visualization recommendation system that allows users to select their tasks precisely on the interface. We first summarize a task base with 18 classical analytic tasks by a survey both in academia and industry. On this basis, we maintain a rule base, which extends empirical wisdom with our targeted modeling of the analytic tasks. Then, our rule-based approach enumerates all the candidate visualizations through answer set programming. After that, the generated charts can be ranked by four ranking schemes. Furthermore, we introduce a task-based combination recommendation strategy, leveraging a set of visualizations to give a brief view of the dataset collaboratively. Finally, we evaluate TaskVis through a series of use cases and a user study. △ Less

Submitted 14 September, 2022; v1 submitted 6 May, 2022; originally announced May 2022.

Comments: 16 pages 10 figures. Data Sci. Eng. (2022)

Towards Natural Language Interfaces for Data Visualization: A Survey

Authors: Leixian Shen, Enya Shen, Yuyu Luo, Xiaocong Yang, Xuming Hu, Xiongshuai Zhang, Zhiwei Tai, Jianmin Wang

Abstract: Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience. It enables users to focus on their tasks rather than having to worry about how to operate visualization tools on the interface. In the past two decades, leveraging advanced natural language processing technologie… ▽ More Utilizing Visualization-oriented Natural Language Interfaces (V-NLI) as a complementary input modality to direct manipulation for visual analytics can provide an engaging user experience. It enables users to focus on their tasks rather than having to worry about how to operate visualization tools on the interface. In the past two decades, leveraging advanced natural language processing technologies, numerous V-NLI systems have been developed in academic research and commercial software, especially in recent years. In this article, we conduct a comprehensive review of the existing V-NLIs. In order to classify each paper, we develop categorical dimensions based on a classic information visualization pipeline with the extension of a V-NLI layer. The following seven stages are used: query interpretation, data transformation, visual mapping, view transformation, human interaction, dialogue management, and presentation. Finally, we also shed light on several promising directions for future work in the V-NLI community. △ Less

Submitted 4 February, 2022; v1 submitted 8 September, 2021; originally announced September 2021.

Comments: 20 pages, 15 figures, accepted by IEEE TVCG

SqueezeNext: Hardware-Aware Neural Network Design

Authors: Amir Gholami, Kiseok Kwon, Bichen Wu, Zizheng Tai, Xiangyu Yue, Peter Jin, Sicheng Zhao, Kurt Keutzer

Abstract: One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks. In this work, we introduce SqueezeNext, a new family of neural network architectures whose design was guided by considering previous architectures such as SqueezeNet, as well as by simulation results on a neural network accelerator. This new network is… ▽ More One of the main barriers for deploying neural networks on embedded systems has been large memory and power consumption of existing neural networks. In this work, we introduce SqueezeNext, a new family of neural network architectures whose design was guided by considering previous architectures such as SqueezeNet, as well as by simulation results on a neural network accelerator. This new network is able to match AlexNet's accuracy on the ImageNet benchmark with $112\times$ fewer parameters, and one of its deeper variants is able to achieve VGG-19 accuracy with only 4.4 Million parameters, ($31\times$ smaller than VGG-19). SqueezeNext also achieves better top-5 classification accuracy with $1.3\times$ fewer parameters as compared to MobileNet, but avoids using depthwise-separable convolutions that are inefficient on some mobile processor platforms. This wide range of accuracy gives the user the ability to make speed-accuracy tradeoffs, depending on the available resources on the target hardware. Using hardware simulation results for power and inference speed on an embedded system has guided us to design variations of the baseline model that are $2.59\times$/$8.26\times$ faster and $2.25\times$/$7.5\times$ more energy efficient as compared to SqueezeNet/AlexNet without any accuracy degradation. △ Less

Submitted 27 August, 2018; v1 submitted 23 March, 2018; originally announced March 2018.

Comments: 12 Pages

Journal ref: Design Automation Conference 2018 (and CVPR 2018 workshop)

Multi-cavity ultra-stable laser towards 10-18

Authors: Zhaoyang Tai, Lulu Yan, Yanyan Zhang, Pan Zhang, Xiaofei Zhang, Wenge Guo, Shougang Zhang, Haifeng Jiang

Abstract: In this letter, we demonstrate a technique of making an ultrastable laser referenced to a multi-cavity, corresponding to a lower thermal noise limit due to the larger equivalent beam size. The multi-cavity consists of several pairs of mirrors and a common spacer. We can stabilize the laser frequencies on these cavities, and average the laser frequencies with synthesizing technique. In comparison w… ▽ More In this letter, we demonstrate a technique of making an ultrastable laser referenced to a multi-cavity, corresponding to a lower thermal noise limit due to the larger equivalent beam size. The multi-cavity consists of several pairs of mirrors and a common spacer. We can stabilize the laser frequencies on these cavities, and average the laser frequencies with synthesizing technique. In comparison with a single cavity system, relative frequency instability of the synthesized laser can be improved by a factor of the squire root of the cavity number (n). In addition, we perform an experiment to simulate a two-cavity system. Experimental results show that frequency instability of the synthesized laser is improved by a factor of 1.4, and discrimination of the laser frequency instability, introduced by the process of lasers synthesizing, is negligible, and can reach a floor at low level 10-18 limited by noise of currently used signal generators. This technique is comparable with other techniques; thus, it can gain a factor of the squre root of n on the frequency instability of an ultrastable laser to an unprecedented level. △ Less

Submitted 5 February, 2018; originally announced February 2018.

Comments: 5 pages 4 figures

Hemingway: Modeling Distributed Optimization Algorithms

Authors: Xinghao Pan, Shivaram Venkataraman, Zizheng Tai, Joseph Gonzalez

Abstract: Distributed optimization algorithms are widely used in many industrial machine learning applications. However choosing the appropriate algorithm and cluster size is often difficult for users as the performance and convergence rate of optimization algorithms vary with the size of the cluster. In this paper we make the case for an ML-optimizer that can select the appropriate algorithm and cluster si… ▽ More Distributed optimization algorithms are widely used in many industrial machine learning applications. However choosing the appropriate algorithm and cluster size is often difficult for users as the performance and convergence rate of optimization algorithms vary with the size of the cluster. In this paper we make the case for an ML-optimizer that can select the appropriate algorithm and cluster size to use for a given problem. To do this we propose building two models: one that captures the system level characteristics of how computation, communication change as we increase cluster sizes and another that captures how convergence rates change with cluster sizes. We present preliminary results from our prototype implementation called Hemingway and discuss some of the challenges involved in developing such a system. △ Less

Submitted 20 February, 2017; originally announced February 2017.

Comments: Presented at ML Systems Workshop at NIPS, Dec 2016