publications

2026

1. CHI WS

   

   Short form Workshop First author 0 cites

   What Happened and Why? Trace-Guided Micro-Episodes with Elicited User Explanations for Product Iteration

   Sirui Tao, William P. McCarthy, and Steven P. Dow

   In Herding CATs: Making Sense of Creative Activity Traces (CHI 2026 Workshop), Apr 2026

   Workshop Position Paper

   Why cite this? Source-reviewed guide

   Cite this position paper when motivating rationale-enriched telemetry: short, trace-guided windows paired with optional in-flow clarification to diagnose ambiguous moments in creative or AI-supported work.

   Useful when

   • Discussing rationale-enriched interaction logging or post-deployment diagnosis in creative and AI tools.
   • Designing feedback interventions at likely friction points without moving users into a separate survey flow.

   Scope

   • The proposed interventions have not yet been validated for insight quality, analysis time, interruption cost, or downstream agent training.
   • Traces and clarifications do not by themselves establish causality; trigger selection may distract users or bias later behavior.
   • Friction signals and clarification schemas must be adapted to the domain and the interaction touchpoints available in a particular tool.

   Full citation context

   Bib PDF Website

   @inproceedings{tao2026whw,
     title = {What Happened and Why? Trace-Guided Micro-Episodes with Elicited User Explanations for Product Iteration},
     author = {Tao, Sirui and McCarthy, William P. and Dow, Steven P.},
     booktitle = {Herding CATs: Making Sense of Creative Activity Traces (CHI 2026 Workshop)},
     url = {https://herding-cats-ws.github.io/2026/papers/p02.pdf},
     note = {Workshop Position Paper},
     month = {apr},
     year = {2026}
   }

2025

1. CVPR

   

   Full paper Coauthor 17 cites

   HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition

   Zimo Wang, Cheng Wang, Taiki Yoshino, Sirui Tao, Ziyang Fu, and Tzu-Mao Li

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Jun 2025

   Highlight

   Why cite this? Source-reviewed guide

   Cite HotSpot for neural implicit surface reconstruction from unoriented points when the argument concerns sufficient SDF constraints, optimization stability, topology, or surface-area regularization.

   Useful when

   • Comparing losses for neural signed distance functions rather than treating the eikonal condition as sufficient.
   • Discussing stable reconstruction, distance accuracy, or topology from unoriented point observations, with sparse-boundary failure modes made explicit.

   Scope

   • The experiments target 2D and 3D reconstruction from unoriented point positions, including a 260-shape, 13-category ShapeNet subset; they do not establish superiority for every implicit-representation task.
   • Sparse boundary sampling, high absorption, or an over-strong heat term can tear boundaries or collapse a signed solution toward an unsigned distance.
   • Boundary weight and spatial scaling remain tuning considerations.

   Full citation context

   DOI arXiv Bib PDF Video Code Website

   @inproceedings{wang2025hotspot,
     title = {HotSpot: Signed Distance Function Optimization with an Asymptotically Sufficient Condition},
     author = {Wang, Zimo and Wang, Cheng and Yoshino, Taiki and Tao, Sirui and Fu, Ziyang and Li, Tzu-Mao},
     booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
     pages = {1276--1286},
     publisher = {IEEE},
     doi = {10.1109/CVPR52734.2025.00127},
     arxiv = {2411.14628},
     url = {https://openaccess.thecvf.com/content/CVPR2025/html/Wang_HotSpot_Signed_Distance_Function_Optimization_with_an_Asymptotically_Sufficient_Condition_CVPR_2025_paper.html},
     note = {Highlight},
     month = {jun},
     year = {2025}
   }

2. CHI

   

   Full paper First author 39 cites

   DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design

   Sirui Tao, Ivan Liang, Cindy Peng, Zhiqing Wang, Srishti Palani, and Steven P. Dow

   In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, Apr 2025

   Why cite this? Source-reviewed guide

   Cite DesignWeaver when discussing dimensional scaffolding, novice prompt construction, or interface support for richer and more varied exploration in text-to-image product design.

   Useful when

   • Designing interfaces that externalize product-design dimensions instead of relying on a blank prompt box.
   • Studying how prompt scaffolds change vocabulary, iteration, visual diversity, novelty, and user expectations.

   Scope

   • The controlled study involved 52 novices, ages 19–31, completing a chair-design task; experienced-designer, collaborative, and other-domain use remain open questions.
   • Preset dimensions may constrain creativity as well as scaffold it.
   • Richer prompts can raise expectations beyond what current text-to-image models deliver reliably.

   Full citation context

   DOI arXiv Bib PDF Video Code Website

   @inproceedings{tao2024designweaver,
     title = {DesignWeaver: Dimensional Scaffolding for Text-to-Image Product Design},
     author = {Tao, Sirui and Liang, Ivan and Peng, Cindy and Wang, Zhiqing and Palani, Srishti and Dow, Steven P.},
     booktitle = {Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems},
     series = {CHI '25},
     pages = {1--26},
     publisher = {ACM},
     doi = {10.1145/3706598.3714211},
     arxiv = {2502.09867},
     month = {apr},
     year = {2025}
   }

2023

1. CogSci

   

   Short form Poster + abstract Coauthor 0 cites

   Physion++: Evaluating Physical Scene Understanding with Objects Consisting of Different Physical Attributes in Humans and Machines

   Hsiao-Yu Tung, Mingyu Ding, Zhenfang Chen, Sirui Tao, Vedang Lad, Daniel Bear, Chuang Gan, Josh Tenenbaum, Daniel Yamins, Judith Fan, and Kevin Smith

   In Proceedings of the Annual Meeting of the Cognitive Science Society, Jul 2023

   Poster with abstract

   Why cite this? Source-reviewed guide

   Cite this CogSci Physion++ record when motivating benchmarks for latent physical-property inference or human–model gaps in physical scene prediction.

   Useful when

   • Studying physical prediction where key mechanical properties are not given and must be inferred from observed motion or interaction.
   • Comparing human judgments with video, object-centric, or physical-state model predictions under changing latent properties.

   Scope

   • The public CogSci record supports qualitative, not paper-table-level quantitative, claims.
   • A separate nine-author NeurIPS technical paper has a different title and author list; its numbers and DOI must not be silently attributed to this 11-author CogSci record.
   • The benchmark concerns prediction settings where properties are inferred from observed motion and interaction, not all forms of physical reasoning.

   Full citation context

   Bib PDF Website

   @inproceedings{tung2023physion++,
     title = {Physion++: Evaluating Physical Scene Understanding with Objects Consisting of Different Physical Attributes in Humans and Machines},
     author = {Tung, Hsiao-Yu and Ding, Mingyu and Chen, Zhenfang and Tao, Sirui and Lad, Vedang and Bear, Daniel and Gan, Chuang and Tenenbaum, Josh and Yamins, Daniel and Fan, Judith and Smith, Kevin},
     booktitle = {Proceedings of the Annual Meeting of the Cognitive Science Society},
     url = {https://escholarship.org/uc/item/3x9960zn},
     note = {Poster with abstract},
     month = {jul},
     year = {2023}
   }

2021

1. NeurIPS

   

   Full paper Coauthor 174 cites

   Physion: Evaluating Physical Prediction from Vision in Humans and Machines

   Daniel Bear, Elias Wang, Damian Mrowca, Felix Binder, Hsiao-Yu Tung, Pramod RT, Cameron Holdaway, Sirui Tao, Kevin Smith, Fan-Yun Sun, Fei-Fei Li, Nancy Kanwisher, Josh Tenenbaum, Dan Yamins, and Judith Fan

   In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, Dec 2021

   Why cite this? Source-reviewed guide

   Cite Physion for human-aligned intuitive-physics benchmarking, object-centric physical prediction, or generalization across diverse simulated scenario families.

   Useful when

   • Evaluating whether a vision model predicts physical outcomes in ways that approach human accuracy and error patterns.
   • Motivating object-centric representations, object-contact prediction, or transfer across physical scenario families.

   Scope

   • Physion uses synthetic ThreeDWorld scenes and a binary contact-prediction task; it does not cover all real-world materials, fluid behavior, jointed multipart objects, or property ranges.
   • Particle-based state models receive ground-truth 3D physical state that a vision system must otherwise infer.
   • Strong within-benchmark performance does not by itself establish broad real-world physical understanding or transfer from a single scenario family.

   Full citation context

   arXiv Bib PDF Video Code Website

   @inproceedings{bear2021physion,
     title = {Physion: Evaluating Physical Prediction from Vision in Humans and Machines},
     author = {Bear, Daniel and Wang, Elias and Mrowca, Damian and Binder, Felix and Tung, Hsiao-Yu and RT, Pramod and Holdaway, Cameron and Tao, Sirui and Smith, Kevin and Sun, Fan-Yun and Li, Fei-Fei and Kanwisher, Nancy and Tenenbaum, Josh and Yamins, Dan and Fan, Judith},
     booktitle = {Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks},
     editor = {Vanschoren, J. and Yeung, S.},
     volume = {1},
     arxiv = {2106.08261},
     url = {https://datasets-benchmarks-proceedings.neurips.cc/paper/2021/hash/d09bf41544a3365a46c9077ebb5e35c3-Abstract-round1.html},
     month = {dec},
     year = {2021}
   }