arXiv subjects

Zijian Ding

Publications and source records attributed to Zijian Ding.

At least 37 records · Page 2Linked to original sources

arXiv2025

"The Diagram is like Guardrails": Structuring GenAI-assisted Hypotheses Exploration with an Interactive Shared Representation

Data analysis encompasses a spectrum of tasks, from high-level conceptual reasoning to lower-level execution. While AI-powered tools increasingly support execution tasks, there remains a need for intelligent assistance in conceptual tasks. This paper investigates the design of an ordered node-link tree interface augmented with AI-generated information hints and visualizations, as a potential shared representation for hypothesis exploration. Through a design probe (n=22), participants generated diagrams averaging 21.82 hypotheses. Our findings showed that the node-link diagram acts as "guardrails" for hypothesis exploration, facilitating structured workflows, providing comprehensive overviews, and enabling efficient backtracking. The AI-generated information hints, particularly visualizations, aided users in transforming abstract ideas into data-backed concepts while reducing cognitive load. We further discuss how node-link diagrams can support both parallel exploration and iterative refinement in hypothesis formulation, potentially enhancing the breadth and depth of human-AI collaborative data analysis.

cs.HC↗

arXiv2025

Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis

High-level synthesis (HLS) is a widely used tool in designing Field Programmable Gate Array (FPGA). HLS enables FPGA design with software programming languages by compiling the source code into an FPGA circuit. The source code includes a program (called "kernel") and several pragmas that instruct hardware synthesis, such as parallelization, pipeline, etc. While it is relatively easy for software developers to design the program, it heavily relies on hardware knowledge to design the pragmas, posing a big challenge for software developers. Recently, different machine learning algorithms, such as GNNs, have been proposed to automate the pragma design via performance prediction. However, when applying the trained model on new kernels, the significant domain shift often leads to unsatisfactory performance. We propose a more domain-generalizable model structure: a two-level hierarchical Mixture of Experts (MoE), that can be flexibly adapted to any GNN model. Different expert networks can learn to deal with different regions in the representation space, and they can utilize similar patterns between the old kernels and new kernels. In the low-level MoE, we apply MoE on three natural granularities of a program: node, basic block, and graph. The high-level MoE learns to aggregate the three granularities for the final decision. To train the hierarchical MoE stably, we further propose a two-stage training method to avoid expert polarization. Extensive experiments verify the effectiveness of the proposed hierarchical MoE. We publicized our codes at https://github.com/weikai-li/HierarchicalMoE.

cs.LG↗

arXiv2025

Can AI Prompt Humans? Multimodal Agents Prompt Players' Game Actions and Show Consequences to Raise Sustainability Awareness

Unsustainable behaviors are challenging to prevent due to their long-term, often unclear consequences. Games offer a promising solution by creating artificial environments where players can immediately experience the outcomes of their actions. To explore this potential, we developed EcoEcho, a GenAI-powered game leveraging multimodal agents to raise sustainability awareness. These agents engage players in natural conversations, prompting them to take in-game actions that lead to visible environmental impacts. We evaluated EcoEcho using a mixed-methods approach with 23 participants. Results show a significant increase in intended sustainable behaviors post-game, although attitudes towards sustainability only slightly improved. This finding highlights the potential of multimodal agents and action-consequence mechanics to effectively motivate real-world behavioral changes such as raising environmental sustainability awareness.

cs.HC↗

arXiv2024

Efficient Task Transfer for HLS DSE

There have been several recent works proposed to utilize model-based optimization methods to improve the productivity of using high-level synthesis (HLS) to design domain-specific architectures. They would replace the time-consuming performance estimation or simulation of design with a proxy model, and automatically insert pragmas to guide hardware optimizations. In this work, we address the challenges associated with high-level synthesis (HLS) design space exploration (DSE) through the evolving landscape of HLS tools. As these tools develop, the quality of results (QoR) from synthesis can vary significantly, complicating the maintenance of optimal design strategies across different toolchains. We introduce Active-CEM, a task transfer learning scheme that leverages a model-based explorer designed to adapt efficiently to changes in toolchains. This approach optimizes sample efficiency by identifying high-quality design configurations under a new toolchain without requiring extensive re-evaluation. We further refine our methodology by incorporating toolchain-invariant modeling. This allows us to predict QoR changes more accurately despite shifts in the black-box implementation of the toolchains. Experiment results on the HLSyn benchmark transitioning to new toolchain show an average performance improvement of 1.58$\times$ compared to AutoDSE and a 1.2$\times$ improvement over HARP, while also increasing the sample efficiency by 5.26$\times$, and reducing the runtime by 2.7$\times$.

cs.AR↗

arXiv2024

Cross-Modality Program Representation Learning for Electronic Design Automation with High-Level Synthesis

In recent years, domain-specific accelerators (DSAs) have gained popularity for applications such as deep learning and autonomous driving. To facilitate DSA designs, programmers use high-level synthesis (HLS) to compile a high-level description written in C/C++ into a design with low-level hardware description languages that eventually synthesize DSAs on circuits. However, creating a high-quality HLS design still demands significant domain knowledge, particularly in microarchitecture decisions expressed as \textit{pragmas}. Thus, it is desirable to automate such decisions with the help of machine learning for predicting the quality of HLS designs, requiring a deeper understanding of the program that consists of original code and pragmas. Naturally, these programs can be considered as sequence data. In addition, these programs can be compiled and converted into a control data flow graph (CDFG). But existing works either fail to leverage both modalities or combine the two in shallow or coarse ways. We propose ProgSG, a model that allows interaction between the source code sequence modality and the graph modality in a deep and fine-grained way. To alleviate the scarcity of labeled designs, a pre-training method is proposed based on a suite of compiler's data flow analysis tasks. Experimental results show that ProgSG reduces the RMSE of design performance predictions by up to $22\%$, and identifies designs with an average of $1.10\times$ and $1.26\times$ (up to $8.17\times$ and $13.31\times$) performance improvement in design space exploration (DSE) task compared to HARP and AutoDSE, respectively.

cs.LG↗

arXiv2024

Frontend Diffusion: Exploring Intent-Based User Interfaces through Abstract-to-Detailed Task Transitions

The emergence of Generative AI is catalyzing a paradigm shift in user interfaces from command-based to intent-based outcome specification. In this paper, we explore abstract-to-detailed task transitions in the context of frontend code generation as a step towards intent-based user interfaces, aiming to bridge the gap between abstract user intentions and concrete implementations. We introduce Frontend Diffusion, an end-to-end LLM-powered tool that generates high-quality websites from user sketches. The system employs a three-stage task transition process: sketching, writing, and coding. We demonstrate the potential of task transitions to reduce human intervention and communication costs in complex tasks. Our work also opens avenues for exploring similar approaches in other domains, potentially extending to more complex, interdependent tasks such as video production.

cs.HC↗

arXiv2024

Towards Intent-based User Interfaces: Charting the Design Space of Intent-AI Interactions Across Task Types

Technological advances continue to redefine the dynamics of human-machine interactions, particularly in task execution. This proposal responds to the advancements in Generative AI by outlining a research plan that probes intent-AI interaction across a diverse set of tasks: fixed-scope content curation task, atomic creative tasks, and complex and interdependent tasks. This exploration aims to inform and contribute to the development of Intent-based User Interface (IUI). The study is structured in three phases: examining fixed-scope tasks through news headline generation, exploring atomic creative tasks via analogy generation, and delving into complex tasks through exploratory visual data analysis. Future work will focus on improving IUIs to better provide suggestions to encourage experienced users to express broad and exploratory intents, and detailed and structured guidance for novice users to iterate on analysis intents for high quality outputs.

cs.HC↗

arXiv2024

Monad: Towards Cost-effective Specialization for Chiplet-based Spatial Accelerators

Advanced packaging offers a new design paradigm in the post-Moore era, where many small chiplets can be assembled into a large system. Based on heterogeneous integration, a chiplet-based accelerator can be highly specialized for a specific workload, demonstrating extreme efficiency and cost reduction. To fully leverage this potential, it is critical to explore both the architectural design space for individual chiplets and different integration options to assemble these chiplets, which have yet to be fully exploited by existing proposals. This paper proposes Monad, a cost-aware specialization approach for chiplet-based spatial accelerators that explores the tradeoffs between PPA and fabrication costs. To evaluate a specialized system, we introduce a modeling framework considering the non-uniformity in dataflow, pipelining, and communications when executing multiple tensor workloads on different chiplets. We propose to combine the architecture and integration design space by uniformly encoding the design aspects for both spaces and exploring them with a systematic ML-based approach. The experiments demonstrate that Monad can achieve an average of 16% and 30% EDP reduction compared with the state-of-the-art chiplet-based accelerators, Simba and NN-Baton, respectively.

cs.AR↗

arXiv2024

Intelligent Canvas: Enabling Design-Like Exploratory Visual Data Analysis with Generative AI through Rapid Prototyping, Iteration and Curation

Complex data analysis inherently seeks unexpected insights through exploratory visual analysis methods, transcending logical, step-by-step processing. However, existing interfaces such as notebooks and dashboards have limitations in exploration and comparison for visual data analysis. Addressing these limitations, we introduce a "design-like" intelligent canvas environment integrating generative AI into data analysis, offering rapid prototyping, iteration, and comparative visualization management. Our dual contributions include the integration of generative AI components into a canvas interface, and empirical findings from a user study (N=10) evaluating the effectiveness of the canvas interface.

cs.HC↗

arXiv2024

UniSparse: An Intermediate Language for General Sparse Format Customization

The ongoing trend of hardware specialization has led to a growing use of custom data formats when processing sparse workloads, which are typically memory-bound. These formats facilitate optimized software/hardware implementations by utilizing sparsity pattern- or target-aware data structures and layouts to enhance memory access latency and bandwidth utilization. However, existing sparse tensor programming models and compilers offer little or no support for productively customizing the sparse formats. Additionally, because these frameworks represent formats using a limited set of per-dimension attributes, they lack the flexibility to accommodate numerous new variations of custom sparse data structures and layouts. To overcome this deficiency, we propose UniSparse, an intermediate language that provides a unified abstraction for representing and customizing sparse formats. Unlike the existing attribute-based frameworks, UniSparse decouples the logical representation of the sparse tensor (i.e., the data structure) from its low-level memory layout, enabling the customization of both. As a result, a rich set of format customizations can be succinctly expressed in a small set of well-defined query, mutation, and layout primitives. We also develop a compiler leveraging the MLIR infrastructure, which supports adaptive customization of formats, and automatic code generation of format conversion and compute operations for heterogeneous architectures. We demonstrate the efficacy of our approach through experiments running commonly-used sparse linear algebra operations with specialized formats on multiple different hardware targets, including an Intel CPU, an NVIDIA GPU, an AMD Xilinx FPGA, and a simulated processing-in-memory (PIM) device.

cs.CL↗

arXiv2024

Advancing GUI for Generative AI: Charting the Design Space of Human-AI Interactions through Task Creativity and Complexity

Technological progress has persistently shaped the dynamics of human-machine interactions in task execution. In response to the advancements in Generative AI, this paper outlines a detailed study plan that investigates various human-AI interaction modalities across a range of tasks, characterized by differing levels of creativity and complexity. This exploration aims to inform and contribute to the development of Graphical User Interfaces (GUIs) that effectively integrate with and enhance the capabilities of Generative AI systems. The study comprises three parts: exploring fixed-scope tasks through news headline generation, delving into atomic creative tasks with analogy generation, and investigating complex tasks via data visualization. Future work aims to extend this exploration to linearize complex data analysis results into narratives understandable to a broader audience, thereby enhancing the interpretability of AI-generated content.

cs.HC↗

arXiv2024

Formulating or Fixating: Effects of Examples on Problem Solving Vary as a Function of Example Presentation Interface Design

Interactive systems that facilitate exposure to examples can augment problem solving performance. However designers of such systems are often faced with many practical design decisions about how users will interact with examples, with little clear theoretical guidance. To understand how example interaction design choices affect whether/how people benefit from examples, we conducted an experiment where 182 participants worked on a controlled analog to an exploratory creativity task, with access to examples of varying diversity and presentation interfaces. Task performance was worse when examples were presented in a list, compared to contextualized in the exploration space or shown in a dropdown list. Example lists were associated with more fixation, whereas contextualized examples were associated with using examples to formulate a model of the problem space to guide exploration. We discuss implications of these results for a theoretical framework that maps design choices to fundamental psychological mechanisms of creative inspiration from examples.

cs.HC↗

arXiv2023

Harnessing the Power of LLMs: Evaluating Human-AI Text Co-Creation through the Lens of News Headline Generation

To explore how humans can best leverage LLMs for writing and how interacting with these models affects feelings of ownership and trust in the writing process, we compared common human-AI interaction types (e.g., guiding system, selecting from system outputs, post-editing outputs) in the context of LLM-assisted news headline generation. While LLMs alone can generate satisfactory news headlines, on average, human control is needed to fix undesirable model outputs. Of the interaction methods, guiding and selecting model output added the most benefit with the lowest cost (in time and effort). Further, AI assistance did not harm participants' perception of control compared to freeform editing.

cs.CL↗

arXiv2023

Elucidating STEM Concepts through Generative AI: A Multi-modal Exploration of Analogical Reasoning

This study explores the integration of generative artificial intelligence (AI), specifically large language models, with multi-modal analogical reasoning as an innovative approach to enhance science, technology, engineering, and mathematics (STEM) education. We have developed a novel system that utilizes the capacities of generative AI to transform intricate principles in mathematics, physics, and programming into comprehensible metaphors. To further augment the educational experience, these metaphors are subsequently converted into visual form. Our study aims to enhance the learners' understanding of STEM concepts and their learning engagement by using the visual metaphors. We examine the efficacy of our system via a randomized A/B/C test, assessing learning gains and motivation shifts among the learners. Our study demonstrates the potential of applying large language models to educational practice on STEM subjects. The results will shed light on the design of educational system in terms of harnessing AI's potential to empower educational stakeholders.

cs.AI↗

arXiv2023

AI Chatbots as Multi-Role Pedagogical Agents: Transforming Engagement in CS Education

This study investigates the use of Artificial Intelligence (AI)-powered, multi-role chatbots as a means to enhance learning experiences and foster engagement in computer science education. Leveraging a design-based research approach, we develop, implement, and evaluate a novel learning environment enriched with four distinct chatbot roles: Instructor Bot, Peer Bot, Career Advising Bot, and Emotional Supporter Bot. These roles, designed around the tenets of Self-Determination Theory, cater to the three innate psychological needs of learners - competence, autonomy, and relatedness. Additionally, the system embraces an inquiry-based learning paradigm, encouraging students to ask questions, seek solutions, and explore their curiosities. We test this system in a higher education context over a period of one month with 200 participating students, comparing outcomes with conditions involving a human tutor and a single chatbot. Our research utilizes a mixed-methods approach, encompassing quantitative measures such as chat log sequence analysis, and qualitative methods including surveys and focus group interviews. By integrating cutting-edge Natural Language Processing techniques such as topic modelling and sentiment analysis, we offer an in-depth understanding of the system's impact on learner engagement, motivation, and inquiry-based learning. This study, through its rigorous design and innovative approach, provides significant insights into the potential of AI-empowered, multi-role chatbots in reshaping the landscape of computer science education and fostering an engaging, supportive, and motivating learning environment.

cs.AI↗

arXiv2023

Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of concept of Large language Models' (LLMs) ability to generate cross-domain analogies. However, the reliability and potential usefulness of this capacity for augmenting human creative work has received little systematic exploration. In this paper, we systematically explore LLMs capacity to augment cross-domain analogical reasoning. Across three studies, we found: 1) LLM-generated cross-domain analogies were frequently judged as helpful in the context of a problem reformulation task (median 4 out of 5 helpfulness rating), and frequently (~80% of cases) led to observable changes in problem formulations, and 2) there was an upper bound of 25% of outputs bring rated as potentially harmful, with a majority due to potentially upsetting content, rather than biased or toxic content. These results demonstrate the potential utility -- and risks -- of LLMs for augmenting cross-domain analogical creativity.

cs.CL↗

arXiv2023

Freeform Templates: Combining Freeform Curation with Structured Templates

Online whiteboards are becoming a popular way to facilitate collaborative design work, providing a free-form environment to curate ideas. However, as templates are increasingly being used to scaffold contributions from non-experts designers, it is crucial to understand their impact on the creative process. In this paper, we present the results from a study with 114 students in a large introductory design course. Our results confirm prior findings that templates benefit students by providing a starting point, a shared process, and the ability to access their own work from previous steps. While prior research has criticized templates for being too rigid, we discovered that using templates within a free-form environment resulted in visual patterns of free-form curation where concepts were spatially organized, clustered, color-coded, and connected using arrows and lines. We introduce the concept of "Free-form Templates" to illustrate how templates and free-form curation can be synergistic.

cs.HC↗

arXiv2023

Mapping the Design Space of Interactions in Human-AI Text Co-creation Tasks

Large Language Models (LLMs) have demonstrated impressive text generation capabilities, prompting us to reconsider the future of human-AI co-creation and how humans interact with LLMs. In this paper, we present a spectrum of content generation tasks and their corresponding human-AI interaction patterns. These tasks include: 1) fixed-scope content curation tasks with minimal human-AI interactions, 2) independent creative tasks with precise human-AI interactions, and 3) complex and interdependent creative tasks with iterative human-AI interactions. We encourage the generative AI and HCI research communities to focus on the more complex and interdependent tasks, which require greater levels of human involvement.

cs.AI↗