Florida International University, doctoral research

Inferential Discovery and Design Adaptation in Visual Generative Workflows

Research question

How does a designer’s relationship to their visual work in progress shift when inferential discovery can recur across a generative workflow?

In a generative workflow, model inference produces or transforms visual material, and that material can become grounds for the designer’s inference: the designer can take something visible in it to support a conclusion about the work in progress.

Where a workflow invokes model inference recurrently rather than episodically, the work can change through model inference at more points in the process, and the occasions on which the designer finds something consequential can recur. The possibility of recurrent inferential discovery makes this research an inquiry into deciding under an abundance of options.

The research examines how designers exercise agency in responding to inferential discovery across workflows that combine automated production with direct editing, compositing and physical making. It asks how the conditions of their work can enable or constrain what they can do.

Human inference is drawing a conclusion from available information and prior understanding. The word also names the conclusion drawn.

When information is limited, prior knowledge can shape which explanations a person considers and how plausible they find them (Tenenbaum and colleagues).

In his account of human reasoning with beliefs, Boghossian explains that a person draws a conclusion because they take other beliefs to support it. In design work, a designer can take something visible in the work as grounds for a conclusion about it.

In machine learning, inference applies a trained or fitted model to supplied input to produce a prediction or generated result.

In neural networks, training adjusts numerical weights and other parameters using data; inference processes the supplied input through the network using those learned values (Google machine learning glossary).

A text-to-image system, for example, uses a trained model to generate an image guided by a prompt (Rombach and colleagues). That image becomes visual material from which the designer can draw an inference.

In natural language processing, a trained model can perform a task called natural language inference by predicting whether a premise entails, contradicts, or is neutral toward a hypothesis (Bowman et al., 2015). Using inference for both people and models can encourage anthropomorphism when the shared term is taken to imply human reasoning or understanding. Following McDermott (1976) and Shanahan (2024), this account describes model inference through the mechanisms that produce its results.

In this research, an inference a designer finds becomes an inferential discovery as the designer determines what it means for adaptation and continuation of their work.

Design adaptation names the changes a discovery can prompt in the material being developed and the aims guiding it. It develops through situated judgments, and a judgment can shape the work the designer encounters in subsequent decisions, as when the designer prepares what the next generation receives (Suchman, 1987; Hutchins, 1995; Kirsh, 1995).

Here, abundance includes the information available in generated material, the possibility of further discovery, and the range of responses available across blended practice. A blended practice combines generative computation with other ways of making and editing, within one application or across several.

Simon (1971) observed that “a wealth of information creates a poverty of attention.” Abundance in this inquiry carries that cost: each generated result, each route through blended practice and each possible further discovery asks for judgment.

A designer can pursue something found in a generated result through another kind of operation. The response may develop the existing material, change the conditions of further production, or change the intention guiding the work. Further discovery can remain possible whichever response the designer chooses. That possibility can affect present decisions about continuation, as the designer considers what further work might reveal.

Further discovery need not depend on generating another output. Relationships can also become apparent through working with material already available. In his account of designing as reflective conversation with materials, Schön describes how designers’ moves can reveal unintended consequences and how their intentions can develop through the work. A discovery can change the designer’s understanding without being incorporated into a finished artifact.

More available material does not establish what matters to the designer. An undesirable result can occasion a consequential discovery.

Further discovery can occur after work has come to depend on an earlier decision. Reconsidering that decision can then affect the work that depends on it. What pursuing an interpretation requires depends partly on the possibilities for further work that remain after an operation. Those requirements can affect whether and how the designer continues.

Green and Blackwell call this resistance to change viscosity: changing one part of a working structure can require further changes to connected parts.

Continuation concerns what becomes of the work as the designer responds to it, including the possibility of deciding not to proceed. The work can be sufficient for its purpose while further discovery remains possible. A decision to stop can therefore rest on what the work accomplishes. Looking only at a finished output would leave much of the designer’s response and its consequences unexplained.

How the designer continues the work depends partly on their reasons and agency—the exercise of their capacity to act. The amount of automated production alone does not establish that capacity or explain how it is exercised.

The research has a technical component and a qualitative component: the Inference Resolution Map assesses software operations, and a visual workbook examines the designer’s response through evolving workflow examples.

4How does the map compare software operations?

The Inference Resolution Map assigns provisional X coordinates on a proposed scale of how trained or fitted prediction affects an operation’s returned result. Because what prediction determines depends on the task and its implementation, the map assesses named software tasks, provisionally defined here as operations. For each operation, the assessment identifies the software version, model where applicable, and settings relevant to its predictive task and computation.

For each operation, the assessment asks what the designer specifies, what specified computation determines, and what depends on prediction from a trained or fitted model in the returned result. The predictive task receives graded ratings describing what prediction determines in producing the returned result (scope), how much the supplied material and task leave the model to resolve (latitude), and which relationships it resolves together (coordination). X combines these ratings with implementation counts of the model’s parameters and computation. X is 1 when trained or fitted prediction makes no contribution to the returned result; where prediction contributes, X moves toward 0 as the ratings and transformed counts increase:

X = 1 − R[½(S + U + J3 × 5) + ½(p + c2)]

Ratings describe the task the prediction performs. Each is scored 0–5 against written anchors, and the support for a rating depends on the documentation, code, model files or papers available for the assessed implementation.

A workflow example connects the two components when it links the designer’s response and a working version to relevant operation assessments, including provisional X coordinates where supported. X summarizes the assessed operation’s predictive task and implementation; the accompanying account describes how the result is produced, as documented in the sources for that operation. The workbook describes what the designer finds significant and what responding requires, including what needs to be rebuilt when an earlier decision changes. For example, a generated clip may remain adjustable in timing and placement within an editable composition while its depicted movement stays fixed in the generated frames. If that composition is nested in another sequence, changing the clip’s timing changes when its movement occurs in that sequence. The designer may then find a different relationship between the movement and the next shot, prompting them to reconsider the earlier edit or what they want the sequence to achieve.

Shneiderman’s counterpoint also shapes the research’s direction. Greater automation need not be treated in advance as either a loss or a gain in the designer’s capacity to continue. A particular arrangement of model determination and retained controls may make one response possible while making another difficult. What that means is examined in relation to the work, the designer’s developing intentions and the response under consideration.

Three revision capabilities describe which responses an operation keeps possible. Shneiderman explicitly discusses interfaces that support revised intent and reversible actions. That supports a connection: these capabilities may describe part of the human control that Shneiderman keeps separate from automation. They make particular questions about further work available for examination:

Capability	What it helps investigate
Recovery and reuse	What earlier material remains accessible and usable when the designer considers another response.
Scope of available revision	Which aspects of the work the retained controls can change.
Preservation of dependent later work	What remains applied, and what needs to be rebuilt, when an earlier decision changes.

These descriptions can help explain control over revision across continuation without a second coordinate. They also give the research a particular concern: how earlier decisions and subsequent work remain connected when something is reconsidered. Considering these capabilities does not make preserving earlier decisions a goal in itself; their significance depends on what the designer is trying to pursue at that point.

Which part of the result the prediction sets: settings, a selection, a component, a reconstruction of supplied material, new content within a restricted region, or content throughout.

S · rating scale

S concerns what is predicted and effectively restricted, rather than the percentage of pixels changed. A larger crop does not change a fixed component’s scope. Source protection requires evidence that processing preserves or reinstates the source information.

Rating	Definition
0	No in-scope learned determination remains in the returned result.
1	A learned category, scalar or bounded set of global settings; no dense field, structured relations or content construction is learned.
2	A learned selection, constraint/dimension set, coordinate or transformation field governing supplied content or geometry, without learned reconstruction of its appearance or new scene content.
3	A missing attribute channel or a fixed identified component/property is learned, while the surrounding observed instance defines the task: e.g. chroma, a face-recovery component or a driven mouth region. This functional restriction needs supporting evidence.
4	Reconstruct an observed instance or its fitted representation, or synthesize a completion under an effective restriction retaining source information outside the generative prediction. Reconstruction includes registered images and scene representations fitted to supplied observations. It does not assert exact pixel copying or unique recovery.
5	The operation can generate the entities/parts and arrangement throughout the output domain, with no documented protection/reinstatement restricting retained generative predictions to a component or region. A prompt or reference alone does not establish protection.

How much the supplied material and the task’s objective leave the model to resolve, from locating content already in the image, through faithful restoration, to constructing new content, including its arrangement, from a subject, style or action request or from surrounding context.

U · rating scale

U0 can still determine returned values: CopyCat can predict matte boundaries beyond the user-marked training examples. U follows the task definitions below; it does not count possible outputs or measure a probability distribution.

Rating	Definition
0	Recognize or locate observed content, or emulate a specified fixed transformation; no restoration, preference assignment or new-content task is included.
1	Retired from current coding. Fidelity-directed recovery is coded U2 regardless of sampling change; earlier U1 assessments are retained as history.
2	Recover an observed instance under a documented fidelity target, whether restoring corrupted samples on existing sampling support or estimating missing samples at increased sampling. A sampling change alone does not change U. Do not infer a fidelity target merely because training examples exist.
3	Infer an unobserved attribute, coordinate value, preference or design-intent relation among feasible choices not uniquely specified by the supplied instance and rules; no new semantic scene construction is the task. Latitude 3 applies when the model chooses which of several observed candidates the result is about, with no location from the person and no class named by the operation; selection of a named class and selection the person marks stay at latitude 0.
4	Reconstruct plausible detail or appearance under a documented generative/perceptual/distributional role beyond recovery aimed at fidelity, or synthesize new content following an explicit supplied structural guide. Such a guide prescribes locations, shapes, poses, trajectories or event ordering for identifiable output parts, in words, coordinates or media; it is more than a high-level subject, style or action request. Evidence that the assessed mechanism uses it is needed. Guidance need not be hard protection. Predicting unobserved samples alone does not establish this anchor.
5	Construct a new content/configuration instance without an observed recovery target or an explicit supplied structural guide. Semantic instructions and surrounding context can constrain the task without specifying its internal arrangement.

ESRGAN §§3.1–3.3 supports distinguishing fidelity-oriented recovery from plausible-detail reconstruction. Latent diffusion §3.3 describes supplied conditioning of synthesis. These distinctions inform U’s task categories.

Which relationships the model resolves together: neighboring values, relationships across a supplied subject or scene, semantic and spatial relationships in synthesized content, or evolving relationships across video frames or camera views.

J · rating scale

Network connections show possible dependencies; subject or scene integration needs evidence that those dependencies operate across that subject or scene. A static fitted scene is rated by the relationships resolved in fitting it.

Rating	Definition
0	Separable learned responses; no learned coordination between locations, components or states is established as part of the task. Where the available evidence does not distinguish J0 from higher coordination levels, J remains unresolved.
1	Learned local neighboring values/features are resolved together.
2	Learned relationships across extended regions or scales of registered supplied content are resolved together. Coordination 2 applies to fitted predictors whose features are the output's own spatial coordinates, linear fits included, when the fitting happens inside the operation whose returned result is assessed.
3	Integrate context across the supplied task instance or structure in learned predictions, including a face, a whole subject, a sketch or an observed scene. Establish this functional integration with product-linked task, mechanism or experimental evidence; an undisclosed architecture is not automatically zero. Record the reference domain.
4	The learned task jointly constructs semantic and spatial/structural relationships in synthesized content. Mere consistent appearance in a screenshot does not establish the mechanism.
5	A learned joint mechanism synthesizes evolving content relationships across time or views. Autoregressive internal tokens, conventional playback or repeated independent calls alone do not establish this.

Lumiere §3.1 describes a model that resolves relationships jointly across time, supporting the coordination distinction used by J.

The sources support developing X as a provisional comparative index. The numerical ratings remain methodological judgments.

Automation research has proposed scales like this before. Sheridan and Verplank set out ten levels from human control to computer automation, and Parasuraman, Sheridan and Wickens applied levels of automation to four stages of a task: acquiring information, analyzing it, choosing an action and carrying it out. They allow different automation levels for different functions within the same system, which helps establish why the particular operation and function being compared matter. These levels concern functions allocated to computers and their authority to suggest or execute actions, and they include rule-based automation. An operation is at X’s upper end when implementation evidence establishes that no trained or fitted prediction contributes to its returned result. Shneiderman objects that one line from human control to computer automation carries the message that “more automation meant less user control,” and separates the two into dimensions that can both be high.

Evidence	Relevance to the assessment
The measurement and composite-index literature	The OECD handbook recognizes both statistical and judgment-based choices in weighting and aggregation. It relates those choices to the intended comparison and examines their consequences through uncertainty and sensitivity analysis. Stevens distinguishes ordered categories from scales with equal intervals. Stevens, pp. 678–679, OECD handbook, pp. 31–35.
Parasuraman, Sheridan and Wickens; Shneiderman	These support examining distinct functions and levels within an operation, while keeping human control and agency separate from automation. They strengthen the rationale for retaining the operation’s profile alongside its coordinate. Parasuraman and colleagues, Shneiderman.

5 Inference Resolution Map

↓

Current coordinates use 0–1 units; displayed values are rounded to three decimal places.

Download the map’s records (CSV) Download the map’s records (JSON)

6Proposed contribution

The contribution I am developing is a shared vocabulary for designers and a method for comparing operations, and for comparing designers’ responses to what those operations produce, so that claims about agency and automation can be examined against both technical evidence and documented visual practice.

The qualitative component is a visual workbook in Miro of evolving workflow examples. The examples connect supplied material and relevant settings with working versions and, where a discovery is documented, the designer’s account of it and what follows from the response. Through the examples, the research examines how the designer’s understanding, aims and judgments develop within the work, including what makes a result “coherent enough”: sufficient for its purpose, even when further discovery remains possible. Comparing the examples can test and refine the vocabulary for describing discoveries, what the available evidence supports about them, and the forms continuation takes. Where the records support a distinction the existing terms do not describe, the vocabulary is revised or extended.

The workbook accounts can record how intentions develop and state the criteria behind judgments that designers may otherwise make tacitly (Schön and Wiggins, 1992). The aim is for someone working on different material to take up, question and develop the distinctions and questions developed through the examples (Green and Blackwell, 1998; Gaver and Bowers, 2012; Yuan et al., 2026).

In practice, I have photographed my hands and edited reference images to convey relationships I had difficulty expressing through a text prompt alone. The workbook distinguishes what a prompt requests, what the operation’s mechanism supports, and what the designer then understands or values. That understanding can change what they prepare for the next operation.

Copper-figure example

The copper-figure example shows how the technical assessment could be connected to a designer’s response within a blended workflow, one that combines generative computation with other ways of making and editing. While developing the figure, I found that the head needed a bridge to the crown and considered a do-rag as a way to connect them. The process included generation, Photoshop Generative Fill, the Pen tool, layer masks and color grading. When generation failed to produce the required relationship, I constructed and composited the do-rag in Photoshop, then used the composite as the reference image for further generation. I accepted some loss of patina texture to retain the cultural fidelity I wanted in the do-rag.

The statue at night — References: the statue at night (left), the player in a black satin do-rag (center) and the championship trophy (right).

The player in a black satin do-rag — References: the statue at night (left), the player in a black satin do-rag (center) and the championship trophy (right).

Working version with braids over the statue’s carved hair — Working versions: braids over the statue’s carved hair (left) and cloth bands under the crown (center and right).

Working version with a cloth band under the crown — Working versions: braids over the statue’s carved hair (left) and cloth bands under the crown (center and right).

The black satin do-rag composited onto the figure — The figure with a black satin do-rag (left) and the do-rag in patina green (center). Right: a copper-toned night version with a cloth band under the crown, braids and the trophy.

The same image with the do-rag in patina green — The figure with a black satin do-rag (left) and the do-rag in patina green (center). Right: a copper-toned night version with a cloth band under the crown, braids and the trophy.

Constructing the composite made the head–do-rag–crown relationship I had worked out part of the material supplied for further generation. This gives the technical assessment a specific question: how did the generative operation use that supplied relationship, and what did it determine in the returned material? Assessing that operation would require its software and model versions, relevant settings and technical evidence about how it uses reference material.

Earlier research proposal · 11 September 2026

7Next steps

Test how independent assessors apply the written categories, using disagreements to refine the guidelines. Agreement would address consistency; category validity and X’s numerical calibration would require further evidence.

2024 — 2025

8Earlier research

Method history

The equation moved from aspect ratings to the combined method

August 2026 · Prototype catalogue of 417 rows, with coordinates proposed by research agents under broad numerical guidance.
20 September · Five-aspect specification score: X = ∑S_i, with subject, composition, form, appearance and detail each scored 0–3 by how they are supplied.
21–27 September · Five opportunity-for-inference ratings: X = 15 − 3∑O_i.
29 September – 1 October · X/Y maps: X from the September assessments, with Y added for revision capacity.
Early October · Reference comparisons: X = X_L + t(X_H − X_L), placing an operation between two reference operations.
4 October · Decision categories for 145 operations previously at X = 2: X = 2 + 3 × kept categories ÷ (applicable categories − 1).
14 October · S/U/J calibration proposal across 399 operations: X = 15 − 13(S + U + J)/15.
15 October · Combined method selected, adding model size and computation to the ratings: X = 15[1 − R((S + U + J)/30 + (p + c)/4)].
19 October · Output settings stop moving X; computation is counted at the implementation’s published default.
26 October · U1 retired; fidelity-directed recovery is coded U2 whatever the sampling change.
28 October – 3 November · The 15-point scale is dropped and X runs from 0 to 1: X = 1 − R[½(S + U + J)/(3 × 5) + ½(p + c)/2].

2025

Modalities & spatial structures

Multimodal Spatial Intelligence

PRESENTATION / DECEMBER 2025Full size ↗

1 / 21

Earlier work examined how different input modalities supply partial spatial information, how generative systems resolve that information, and how people interpret the resulting structures.

Read 2025 paper ↗

2024–25

Teaching, tools, and individual learning

While teaching architecture in Miami, I explored how people could learn to use tools through experiences tailored to them. My early research considered visualization and gamification as ways of making learning interactive, with climate education as an initial context. The emphasis subsequently moved toward personalized education and how learning could respond to individual needs.

As generative practice became a stronger focus, my attention shifted toward what designers encounter while working with these tools. The current dissertation focuses on the designer’s response to inferential discovery.

Research timeline

OCTOBER–NOVEMBER 2024

Visualization and interactive learning

Literature review and research-paper drafts examined 3D visualization, gamification, and AI-supported personalization in climate education.

DECEMBER 2024

Architectural education and AI

A Digital Futures paper considered prospective changes to architectural education, curricula, and relationships between educators and students.

MARCH 2025

Personalized learning

Personalized Learning in Higher Education: AI-Driven Analytics and Competency-Based Models as Catalysts for Reform placed adaptive learning and individual needs at the center of the inquiry.

9Personal reading & sources

Listening is an important part of how I learn and develop my work. My reading and listening span technology, creativity, perception, culture, and lived experience.

Linked titles and covers open their audiobook editions on Audible.

Browse titles

Find a title or author

78 titles

Feeling BeautyG. Gabrielle Starr
RangeDavid Epstein
The Nvidia WayTae Kim
PeakAnders Ericsson and Robert Pool
A Paradise Built in HellRebecca Solnit
Algorithms to Live ByBrian Christian and Tom Griffiths
The Anxious GenerationJonathan Haidt
Building a StoryBrandDonald Miller
The Thinking MachineStephen Witt
The Infinity MachineSebastian Mallaby
Worldwide Evil and Misery – The Legacy of the 13 Satanic BloodlinesRobin de Ruiter and Fritz Springmeier
Life on EarthDavid Attenborough
Breaking the Habit of Being YourselfJoe Dispenza
Blue MindWallace J. Nichols
OceanDavid Attenborough and Colin Butfield
Africa Is Not a CountryDipo Faloyin
Exactly What to SayPhil M. Jones
GoogooshGoogoosh and Tara Dehlavi
QuantumManjit Kumar
Visual ThinkingTemple Grandin
The Let Them TheoryMel Robbins
Only God Can Judge MeJeff Pearlman
It Was All a DreamJustin Tinsley
Tupac ShakurStaci Robinson
Unmasking AIJoy Buolamwini
Energy Healing for AnimalsJoan Ranquet
How the Word Is PassedClint Smith
CasteIsabel Wilkerson
Re-RegulatedAnna Runkle
Miracle and Wonder (Special Edition)Malcolm Gladwell and Bruce Headlam
David and GoliathMalcolm Gladwell
Claim Your PowerMastin Kipp
Your Debt PlanRachel Rodgers
AbundanceEzra Klein and Derek Thompson
WordslutAmanda Montell
Reclaim Your Nervous SystemMastin Kipp
The Mountain Is YouBrianna Wiest
The Creative ActRick Rubin
BlinkMalcolm Gladwell
I Hate the Ivy LeagueMalcolm Gladwell
Data FeminismCatherine D’Ignazio and Lauren F. Klein
OutliersMalcolm Gladwell
SapiensYuval Noah Harari
ShowboatRoland Lazenby
Revenge of the Tipping PointMalcolm Gladwell
NexusYuval Noah Harari
The Tipping PointMalcolm Gladwell
What the Dog SawMalcolm Gladwell
Finding MeViola Davis
SupercommunicatorsCharles Duhigg
DuneFrank Herbert
The Deep Learning RevolutionTerrence J. Sejnowski
Weapons of Math DestructionCathy O’Neil
Invisible WomenCaroline Criado Perez
Stop Living on AutopilotAntonio Neves
It’s All in Your HeadRuss
The Broken LadderKeith Payne
Evolve Your BrainJoe Dispenza
The Four Horsemen
We Should All Be MillionairesRachel Rodgers
Steve JobsWalter Isaacson
Elon MuskAshlee Vance
Healing Your Attachment WoundsDiane Poole Heller
The AlchemistPaulo Coelho
The Body Keeps the ScoreBessel van der Kolk
The Autobiography of Malcolm XMalcolm X and Alex Haley
Shoe DogPhil Knight
WillWill Smith and Mark Manson
Born a CrimeTrevor Noah
JAY-ZMichael Eric Dyson
Dark PsychologyValerie Glossner
MetahumanDeepak Chopra
Atomic HabitsJames Clear
AttachedAmir Levine and Rachel Heller
Trillion Dollar Coach
The Spark and the GrindErik Wahl
Summary: 12 Rules for LifeEpicread
Pitch AnythingOren Klaff

Research sources

Sources cited or held for the current research. Updated 3 November 2026.

Find an author, title, or topic

137 sources

Adobe. (n.d.). Precomposing, nesting, and pre-rendering [After Effects help page]. Retrieved November 3, 2026, from https://helpx.adobe.com/after-effects/desktop/work-with-compositions/precomposing-and-nesting/precomposing-nesting-pre-rendering.html
Adobe. (2026, April 15). Adobe ushers in a new era of creativity with new creative agent and generative AI innovations in Adobe Firefly [Press release]. https://news.adobe.com/news/2026/04/adobe-new-creative-agent
Ameisen, E., Lindsey, J., Pearce, A., Gurnee, W., Turner, N. L., Chen, B., Citro, C., Abrahams, D., Carter, S., Hosmer, B., Marcus, J., Sklar, M., Templeton, A., Bricken, T., McDougall, C., Cunningham, H., Henighan, T., Jermyn, A., Jones, A., … Batson, J. (2025). Circuit tracing: Revealing computational graphs in language models. Transformer Circuits Thread. https://transformer-circuits.pub/2025/attribution-graphs/methods.html
Anonymous authors. (n.d.). PSBench: Editing image via GUI agents in Photoshop [Manuscript submitted for publication; ICLR 2026 review version]. OpenReview. https://openreview.net/pdf?id=DWATchaS4U
Anthropic. (2024, December 19). Building effective agents. https://www.anthropic.com/research/building-effective-agents
Baltrušaitis, T., Ahuja, C., & Morency, L.-P. (2019). Multimodal machine learning: A survey and taxonomy. IEEE Transactions on Pattern Analysis and Machine Intelligence, 41(2), 423–443. https://doi.org/10.1109/TPAMI.2018.2798607
Bar-Tal, O., et al. (2024). Lumiere: A space-time diffusion model for video generation. ArXiv.org.https://arxiv.org/abs/2401.12945
Behrens, T. E. J., Muller, T. H., Whittington, J. C. R., Mark, S., Baram, A. B., Stachenfeld, K. L., & Kurth-Nelson, Z. (2018). What is a cognitive map? Organizing knowledge for flexible behavior. Neuron, 100(2), 490–509. https://doi.org/10.1016/j.neuron.2018.10.002
Benharrak, K., & Pavel, A. (2025). HistoryPalette: Supporting Exploration and Reuse of Past Alternatives in Image Generation and Editing [Version 1; Preprint]. arXiv. https://arxiv.org/abs/2501.04163v1
Berni, A., Borgianni, Y., Rotini, F., Gonçalves, M., & Thoring, K. (2024). Stimulating design ideation with artificial intelligence: Present and (short-term) future. Proceedings of the Design Society, 4, 1939–1948. https://doi.org/10.1017/pds.2024.196
Boghossian, P. (2014). What is inference? Philosophical Studies, 169(1), 1–18. https://doi.org/10.1007/s11098-012-9903-x
Bowman, S. R., Angeli, G., Potts, C., & Manning, C. D. (2015). A large annotated corpus for learning natural language inference. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (pp. 632–642). Association for Computational Linguistics. https://doi.org/10.18653/v1/D15-1075
Bowker, G. C., & Star, S. L. (1999). Sorting things out: Classification and its consequences. MIT Press. MIT Press
Burke, A. (2025). Multimodal spatial intelligence [Unpublished doctoral project paper, ARC 7980]. Department of Architecture, Florida International University.
Caetano, I., Santos, L., & Leitão, A. (2020). Computational design in architecture: Defining parametric, generative, and algorithmic design. Frontiers of Architectural Research, 9(2), 287–300. https://doi.org/10.1016/j.foar.2019.12.008
Calefato, F., Castellano, G., & Rossano, V. (2019). RECODE: Revision control for digital images. Multimedia Tools and Applications, 78(23), 33169–33188. https://doi.org/10.1007/s11042-019-7735-9
Castro Pena, M. L., Carballal, A., Rodríguez-Fernández, N., Santos, I., & Romero, J. (2021). Artificial intelligence applied to conceptual design. A review of its use in architecture. Automation in Construction, 124, Article 103550. https://doi.org/10.1016/j.autcon.2021.103550
Chatzikyriakidis, S., & Lappin, S. (2026). Neuro-symbolic NLP: Taxonomy, assessment, and directions. Frontiers in Artificial Intelligence, 9, Article 1797587. https://doi.org/10.3389/frai.2026.1797587
Chen, T., Goodfellow, I., & Shlens, J. (2016). Net2Net: Accelerating learning via knowledge transfer. In Proceedings of the International Conference on Learning Representations. https://arxiv.org/abs/1511.05641
Chiriatti, M., Ganapini, M., Panai, E., Ubiali, M., & Riva, G. (2024). The case for human–AI interaction as system 0 thinking. Nature Human Behaviour, 8(10), 1829–1830. https://doi.org/10.1038/s41562-024-01995-5
Choi, J., Vasconcelos, H., Lee, H., Zou, C., Lee, T. Y., & Bernstein, M. (2026). FocusGen: Expanding visual design exploration with a simulated focus group of persona agents [Preprint]. arXiv. https://arxiv.org/abs/2608.28001
Christian, B., & Griffiths, T. (2016). Algorithms to live by: The computer science of human decisions. Henry Holt and Company. Macmillan / Henry Holt
Clark, A. (1997). Being there: Putting brain, body, and world together again. MIT Press. MIT Press
Conijn, R., Dux Speltz, E., van Zaanen, M., Van Waes, L., & Chukharev-Hudilainen, E. (2022). A product- and process-oriented tagset for revisions in writing. Written Communication, 39(1), 97–128. https://doi.org/10.1177/07410883211052104
Daston, L., & Galison, P. (2007). Objectivity. Zone Books. Zone Books
Deng, A., Cao, T., Chen, Z., & Hooi, B. (2025). Words or vision: Do vision-language models have blind faith in text? In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://arxiv.org/abs/2503.02199
Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021). RepVGG: Making VGG-style ConvNets great again. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 13733–13742). https://openaccess.thecvf.com/content/CVPR2021/html/Ding_RepVGG_Making_VGG-Style_ConvNets_Great_Again_CVPR_2021_paper.html
Dorst, K. (2011). The core of ‘design thinking’ and its application. Design Studies, 32(6), 521–532. https://doi.org/10.1016/j.destud.2011.07.006
Dorst, K., & Cross, N. (2001). Creativity in the design process: Co-evolution of problem–solution. Design Studies, 22(5), 425–437. https://doi.org/10.1016/S0142-694X(01)00009-6
Doshi, A. R., & Hauser, O. P. (2024). Generative AI enhances individual creativity but reduces the collective diversity of novel content. Science Advances, 10(28), Article eadn5290. https://doi.org/10.1126/sciadv.adn5290
Doshi-Velez, F., & Kim, B. (2017). Towards a rigorous science of interpretable machine learning [Preprint]. arXiv. https://arxiv.org/abs/1702.08608
Dourish, P. (2001). Where the action is: The foundations of embodied interaction. MIT Press. MIT Press
Dow, S. P., Glassco, A., Kass, J., Schwarz, M., Schwartz, D. L., & Klemmer, S. R. (2010). Parallel prototyping leads to better design results, more divergence, and increased self-efficacy. ACM Transactions on Computer-Human Interaction, 17(4), Article 18. https://doi.org/10.1145/1879831.1879836
Driscoll, J. R., Sarnak, N., Sleator, D. D., & Tarjan, R. E. (1989). Making data structures persistent. Journal of Computer and System Sciences, 38(1), 86–124. https://doi.org/10.1016/0022-0000(89)90034-2
Faigley, L., & Witte, S. (1981). Analyzing revision. College Composition and Communication, 32(4), 400–414. https://doi.org/10.58680/ccc198115887
Fiebrink, R., Cook, P. R., & Trueman, D. (2011). Human model evaluation in interactive supervised learning. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 147–156). ACM. https://doi.org/10.1145/1978942.1978965
Foundry. (n.d.). Apply and improve the results from your network. Nuke Documentation. Retrieved October 26, 2026, from https://learn.foundry.com/nuke/content/comp_environment/air_tools/cc-apply.html
Foundry. (n.d.). Train and monitor the network. Nuke Documentation. Retrieved November 3, 2026, from https://learn.foundry.com/nuke/content/comp_environment/air_tools/cc-train.html
Ganz, F., & Müller, M. (2026). The weight is over: Interactive diffusion on consumer GPUs [Preprint]. arXiv. https://arxiv.org/abs/2609.21849
Garcin, S., Walker, T., McDonagh, S., Pearce, T., Bilen, H., He, T., Wang, K., & Bian, J. (2026). Beyond pixel histories: World models with persistent 3D state [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2603.03482
Gaver, B., & Bowers, J. (2012). Annotated portfolios. Interactions, 19(4), 40–49. https://doi.org/10.1145/2212877.2212889
Gharbi, M., Chen, J., Barron, J. T., Hasinoff, S. W., & Durand, F. (2017). Deep bilateral learning for real-time image enhancement. ACM Transactions on Graphics, 36(4), Article 118. https://doi.org/10.1145/3072959.3073592
Gilbert, D. T., & Ebert, J. E. J. (2002). Decisions and revisions: The affective forecasting of changeable outcomes. Journal of Personality and Social Psychology, 82(4), 503–514. https://doi.org/10.1037/0022-3514.82.4.503
Goodwin, C. (1994). Professional vision. American Anthropologist, 96(3), 606–633. DOI / American Anthropologist
Google. (2025, August 25). Embeddings. Google for Developers. Retrieved November 2, 2026, from https://developers.google.com/machine-learning/crash-course/embeddings
Google. (2025, December 3). Neural networks: Nodes and hidden layers. Google for Developers. Retrieved November 2, 2026, from https://developers.google.com/machine-learning/crash-course/neural-networks/nodes-hidden-layers
Google. (2026, April 13). Machine learning glossary: ML fundamentals. Google for Developers. Retrieved October 26, 2026, from https://developers.google.com/machine-learning/glossary/fundamentals
Google. (2026, January 27). What is machine learning? Google for Developers. Retrieved November 2, 2026, from https://developers.google.com/machine-learning/intro-to-ml/what-is-ml
Google. (2026, January 9). Introduction to large language models. Google for Developers. Retrieved November 2, 2026, from https://developers.google.com/machine-learning/crash-course/llm
Green, T. R. G., & Blackwell, A. F. (1998). Cognitive dimensions of information artefacts: A tutorial (Version 1.2). https://www.cl.cam.ac.uk/~afb21/CognitiveDimensions/CDtutorial.pdf
Green, T. R. G., & Petre, M. (1996). Usability analysis of visual programming environments: A ‘cognitive dimensions’ framework. Journal of Visual Languages & Computing, 7(2), 131–174. https://doi.org/10.1006/jvlc.1996.0009
Grossman, T., Matejka, J., & Fitzmaurice, G. (2010). Chronicle: Capture, exploration, and playback of document workflow histories. In Proceedings of the 23rd Annual ACM Symposium on User Interface Software and Technology (pp. 143–152). ACM. https://www.research.autodesk.com/app/uploads/2023/03/chronicle-capture-exploration-and.pdf_recNcJfrpKrBAdAgH.pdf
Hugging Face. (n.d.). Reproducibility. Diffusers documentation. Retrieved November 2, 2026, from https://huggingface.co/docs/diffusers/using-diffusers/reusing_seeds
Hutchins, E. (1995). Cognition in the wild. MIT Press. MIT Press
Jaiswal, S., Prabhudesai, M., Bhardwaj, N., Qin, Z., Zadeh, A., Li, C., Fragkiadaki, K., & Pathak, D. (2026). Iterative refinement improves compositional image generation [Preprint]. arXiv. https://arxiv.org/abs/2601.15286
Jewitt, C. (Ed.). (2009). The Routledge handbook of multimodal analysis. Routledge. Routledge, first edition
Kautz, H. (2022). The third AI summer: AAAI Robert S. Engelmore Memorial Lecture. AI Magazine, 43(1), 105–125. https://doi.org/10.1002/aaai.12036
Kim, J., Pratt, M. J., Iyer, R. G., & Sriram, R. D. (2008). Standardized data exchange of CAD models with design intent. Computer-Aided Design, 40(7), 760–777. https://doi.org/10.1016/j.cad.2007.06.014
Kirillov, A., Mintun, E., Ravi, N., Mao, H., Rolland, C., Gustafson, L., Xiao, T., Whitehead, S., Berg, A. C., Lo, W.-Y., Dollár, P., & Girshick, R. (2023). Segment anything [Preprint]. arXiv. https://arxiv.org/abs/2304.02643
Kirsh, D. (1995). The intelligent use of space. Artificial Intelligence, 73(1–2), 31–68. DOI / Artificial Intelligence
Kirsh, D., & Maglio, P. (1994). On distinguishing epistemic from pragmatic action. Cognitive Science, 18(4), 513–549. https://doi.org/10.1207/s15516709cog1804_1
Kress, G., & van Leeuwen, T. (2001). Multimodal discourse: The modes and media of contemporary communication. Arnold. Bloomsbury, original 2001 work
Lee, H.-P., Sarkar, A., Tankelevitch, L., Drosos, I., Rintel, S., Banks, R., & Wilson, N. (2025). The impact of generative AI on critical thinking: Self-reported reductions in cognitive effort and confidence effects from a survey of knowledge workers. In Proceedings of the CHI Conference on Human Factors in Computing Systems. ACM. https://doi.org/10.1145/3706598.3713778
Li, B., Lin, Z., Shechtman, E., Li, D., Fu, H., & Zhou, Y. (2026). StreamStudio: Exploring video authoring with streaming autoregressive generation [Preprint]. arXiv. https://arxiv.org/abs/2610.38467
Liapis, A., Yannakakis, G. N., Alexopoulos, C., & Lopes, P. (2016). Can computers foster human users' creativity? Theory and praxis of mixed-initiative co-creativity. Digital Culture & Education, 8(2), 136–153. Digital Culture & Education
Lin, Z., Ehsan, U., Agarwal, R., Dani, S., Vashishth, V., & Riedl, M. (2023). Beyond prompts: Exploring the design space of mixed-initiative co-creativity systems [Preprint]. arXiv. https://arxiv.org/abs/2305.07465
Lipton, Z. C. (2018). The mythos of model interpretability. Queue, 16(3), 31–57. https://doi.org/10.1145/3236386.3241340
Ma, N., Tong, S., Jia, H., Hu, H., Su, Y.-C., Zhang, M., Yang, X., Li, Y., Jaakkola, T., Jia, X., & Xie, S. (2025). Inference-time scaling for diffusion models beyond scaling denoising steps [Preprint]. arXiv. https://arxiv.org/abs/2501.09732
Maher, M. L., & Poon, J. (1996). Modeling design exploration as co-evolution. Microcomputers in Civil Engineering, 11(3), 195–209. DOI / published 1996 article
McDermott, D. (1976). Artificial intelligence meets natural stupidity. ACM SIGART Bulletin, (57), 4–9. https://doi.org/10.1145/1045339.1045340
Meng, C., He, Y., Song, Y., Song, J., Wu, J., Zhu, J.-Y., & Ermon, S. (2022). SDEdit: Guided image synthesis and editing with stochastic differential equations. In International Conference on Learning Representations. https://arxiv.org/abs/2108.01073
Mildenhall, B., et al. (2020). NeRF: Representing scenes as neural radiance fields for view synthesis. ArXiv.org. https://arxiv.org/abs/2003.08934
Mitchell, W. J. (1992). The reconfigured eye: Visual truth in the post-photographic era. MIT Press. MIT Press
Model Context Protocol. (2025, June 18). Tools [Specification]. https://modelcontextprotocol.io/specification/2025-06-18/server/tools
Moors, A., & De Houwer, J. (2006). Automaticity: A theoretical and conceptual analysis. Psychological Bulletin, 132(2), 297–326. https://doi.org/10.1037/0033-2909.132.2.297
Myers, B. A., Lai, A., Le, T. M., Yoon, Y., Faulring, A., & Brandt, J. (2015). Selective undo support for painting applications. In Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. ACM. https://doi.org/10.1145/2702123.2702543
Naik, S., Shukla, P., Obi, I., Backus, J., Rasche, N., & Parsons, P. (2025). Tracing the invisible: Understanding students' judgment in AI-supported design work. In Creativity and Cognition (C&C '25). ACM. https://doi.org/10.1145/3698061.3734399
Nguyen, T., Michaels, J., Fiterau, M., & Jensen, D. (2025). Challenges in understanding modality conflict in vision-language models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2509.02805
Nielsen, J. (1993, January 1). Response time limits. Nielsen Norman Group. https://www.nngroup.com/articles/response-times-3-important-limits/
Nooralahzadeh, F., Rohanian, O., Zhang, Y., Fürst, J., & Stockinger, K. (2026). Arbitration failure, not perceptual blindness: How vision-language models resolve visual-linguistic conflicts [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2604.09364
OECD, European Union, & European Commission, Joint Research Centre. (2008). Handbook on constructing composite indicators: Methodology and user guide. OECD Publishing. https://doi.org/10.1787/9789264043466-en
Oxman, R. (2006). Theory and design in the first digital age. Design Studies, 27(3), 229–265. https://doi.org/10.1016/j.destud.2005.11.002
Parasuraman, R., Sheridan, T. B., & Wickens, C. D. (2000). A model for types and levels of human interaction with automation. IEEE Transactions on Systems, Man, and Cybernetics—Part A: Systems and Humans, 30(3), 286–297. https://doi.org/10.1109/3468.844354
Park, J., Jang, K. J., Alasaly, B., Mopidevi, S., Zolensky, A., Eaton, E., Lee, I., & Johnson, K. (2025). Assessing modality bias in video question answering benchmarks with multimodal large language models. Proceedings of the AAAI Conference on Artificial Intelligence, 39(19), 19821–19829. https://doi.org/10.1609/aaai.v39i19.34183
Peirce, C. S. (1934). Collected papers of Charles Sanders Peirce: Vol. 5. Pragmatism and pragmaticism (C. Hartshorne & P. Weiss, Eds.). Harvard University Press.
Peng, X., Haldar, D., Mackay, W. E., & Koch, J. (2026). DesignTrace: Exploring, iterating and tracking design alternatives with GenAI. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (pp. 1–22). ACM. https://doi.org/10.1145/3772318.3791036
Piccinini, G. (2025). Computation in physical systems. In E. N. Zalta & U. Nodelman (Eds.), The Stanford encyclopedia of philosophy (Fall 2025 ed.). Metaphysics Research Lab, Stanford University. https://plato.stanford.edu/archives/fall2025/entries/computation-physicalsystems/
Poole, D. L., & Mackworth, A. K. (2023). Artificial intelligence: Foundations of computational agents (3rd ed.). Cambridge University Press. https://artint.info/3e/html/ArtInt3e.html
Rezwana, J., & Maher, M. L. (2023). Designing creative AI partners with COFI: A framework for modeling interaction in human-AI co-creative systems. ACM Transactions on Computer-Human Interaction, 30(5), 1–28. https://doi.org/10.1145/3519026
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022). High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10684–10695). https://doi.org/10.1109/CVPR52688.2022.01042
Roozenburg, N. F. M. (1993). On the pattern of reasoning in innovative design. Design Studies, 14(1), 4–18. DOI / Design Studies
Sajid, H. (2024, November 13). Building a generative AI evaluation framework. Encord Blog. https://encord.com/blog/building-a-generative-ai-evaluation-framework
Sajjadi, M. S. M., et al. (2022). Scene representation transformer: Geometry-free novel view synthesis through set-latent scene representations. CVPR. https://srt-paper.github.io
Schlosser, M. (2019). Agency. In E. N. Zalta (Ed.), The Stanford encyclopedia of philosophy (Winter 2019 ed.). Metaphysics Research Lab, Stanford University. https://plato.stanford.edu/archives/win2019/entries/agency/
Schön, D. A. (1992). Designing as reflective conversation with the materials of a design situation. Research in Engineering Design, 3, 131–147. https://doi.org/10.1007/BF01580516
Schön, D. A., & Wiggins, G. (1992). Kinds of seeing in designing. Creativity and Innovation Management, 1(2), 68–74. DOI / Creativity and Innovation Management
Schulz, L. E., & Gopnik, A. (2004). Causal learning across domains. Developmental Psychology, 40(2), 162–176. https://doi.org/10.1037/0012-1649.40.2.162
Shanahan, M. (2024). Still “Talking about large language models”: Some clarifications [Preprint]. arXiv. https://arxiv.org/abs/2412.10291
Shanahan, M. (2024). Talking about large language models. Communications of the ACM, 67(2), 68–79. https://doi.org/10.1145/3624724
Shen, H., Shen, L., Wu, W., & Zhang, K. (2025). IdeationWeb: Tracking the evolution of design ideas in human-AI co-creation. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (pp. 1–19). ACM. https://doi.org/10.1145/3706598.3713375
Sheng, Z., Han, X., Zhang, Z., Xiong, Z., Ding, Y., Ping, A., Li, X., Guo, T., & Mao, Y. (2026). InEdit-Bench: Benchmarking intermediate logical pathways for intelligent image editing models [Preprint]. arXiv. https://doi.org/10.48550/arXiv.2603.03657
Sheridan, T. B., & Verplank, W. L. (1978). Human and computer control of undersea teleoperators. Man-Machine Systems Laboratory, Massachusetts Institute of Technology. NTIS government report record
Shin, J., Li, Z., Zhang, R., Zhu, J.-Y., Park, J., Shechtman, E., & Huang, X. (2026). MotionStream: Real-time video generation with interactive motion controls. In International Conference on Learning Representations. https://arxiv.org/abs/2511.01266
Shneiderman, B. (2020). Human-centered artificial intelligence: Reliable, safe & trustworthy [Preprint]. arXiv. https://arxiv.org/abs/2002.04087
Sim, M. Y., Zhang, W. E., Dai, X., & Fang, B. (2025). Can VLMs actually see and read? A survey on modality collapse in vision-language models. In Findings of the Association for Computational Linguistics: ACL 2025 (pp. 24452–24470). Association for Computational Linguistics. https://aclanthology.org/2025.findings-acl.1256/
Simon, H. A. (1955). A behavioral model of rational choice. The Quarterly Journal of Economics, 69(1), 99–118. https://doi.org/10.2307/1884852
Simon, H. A. (1971). Designing organizations for an information-rich world. In M. Greenberger (Ed.), Computers, communications, and the public interest (pp. 37–72). Johns Hopkins Press. Published chapter, Purdue-hosted scan
Sommers, N. (1980). Revision strategies of student writers and experienced adult writers. College Composition and Communication, 31(4), 378–388. https://www.jstor.org/stable/356588
Stevens, S. S. (1946). On the theory of scales of measurement. Science, 103(2684), 677–680. https://doi.org/10.1126/science.103.2684.677
Suchman, L. A. (1987). Plans and situated actions: The problem of human-machine communication. Cambridge University Press. Google Books, original 1987 work
Sun, Y., Jang, E., Ma, F., & Wang, T. (2024). Generative AI in the wild: Prospects, challenges, and strategies. In Proceedings of the CHI Conference on Human Factors in Computing Systems (pp. 1–16). ACM. https://arxiv.org/abs/2404.04101
Suwa, M., Gero, J. S., & Purcell, T. (2000). Unexpected discoveries and S-invention of design requirements: Important vehicles for a design process. Design Studies, 21(6), 539–567. https://doi.org/10.1016/S0142-694X(99)00034-4
Suwa, M., Gero, J. S., & Purcell, T. A. (1998). The roles of sketches in early conceptual design processes. In Proceedings of the Twentieth Annual Conference of the Cognitive Science Society (pp. 1043–1048). Lawrence Erlbaum Associates. https://escholarship.org/uc/item/1g4564qk
Tanimoto, S. L. (2013). A perspective on the evolution of live programming. In 2013 1st International Workshop on Live Programming (LIVE) (pp. 31–34). IEEE. https://doi.org/10.1109/LIVE.2013.6617346
Tankelevitch, L., Glassman, E. L., He, J., Kittur, A., Lee, M., Palani, S., Sarkar, A., Ramos, G., Rogers, Y., & Subramonyam, H. (2025). Understanding, protecting, and augmenting human cognition with generative AI: A synthesis of the CHI 2025 Tools for Thought workshop [Preprint]. arXiv. https://arxiv.org/abs/2508.21036
Tankelevitch, L., Kewenig, V., Simkute, A., Scott, A. E., Sarkar, A., Sellen, A., & Rintel, S. (2024). The metacognitive demands and opportunities of generative AI. In Proceedings of the 2024 CHI Conference on Human Factors in Computing Systems (Article 680, pp. 1–24). ACM. https://doi.org/10.1145/3613904.3642902
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011). How to grow a mind: Statistics, structure, and abstraction. Science, 331(6022), 1279–1285. https://doi.org/10.1126/science.1192788
Terry, M., & Mynatt, E. D. (2002). Recognizing creative needs in user interface design. In Proceedings of the 4th Conference on Creativity & Cognition (pp. 38–44). ACM. https://doi.org/10.1145/581710.581718
Terry, M., Mynatt, E. D., Nakakoji, K., & Yamamoto, Y. (2004). Variation in element and action: Supporting simultaneous development of alternative solutions. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (pp. 711–718). ACM. https://doi.org/10.1145/985692.985782
Tran Luciani, D., Löwgren, J., & Lundberg, J. (2020). Designing fine-grained interactions for automation in air traffic control. Cognition, Technology & Work, 22(4), 685–701. https://doi.org/10.1007/s10111-019-00598-9
Tversky, B. (2011). Visualizing thought. Topics in Cognitive Science, 3(3), 499–535. https://doi.org/10.1111/j.1756-8765.2010.01113.x
Wadinambiarachchi, S., Kelly, R. M., Pareek, S., Zhou, Q., & Velloso, E. (2024). The effects of generative AI on design fixation and divergent thinking. In Proceedings of the CHI Conference on Human Factors in Computing Systems (pp. 1–18). ACM. https://doi.org/10.1145/3613904.3642919
Wadinambiarachchi, S., Waycott, J., Rogers, Y., & Wadley, G. (2025). Imagining design workflows in agentic AI futures [Preprint; 37th Australian Conference on Human-Computer Interaction]. arXiv. https://arxiv.org/abs/2509.20731
Wang, X., Yu, K., Wu, S., Gu, J., Liu, Y., Dong, C., Loy, C. C., Qiao, Y., & Tang, X. (2018). ESRGAN: Enhanced super-resolution generative adversarial networks [Preprint]. arXiv. https://arxiv.org/abs/1809.00219
Wen, Y., Jain, N., Kirchenbauer, J., Goldblum, M., Geiping, J., & Goldstein, T. (2023). Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery. In Advances in Neural Information Processing Systems (Vol. 36). https://arxiv.org/abs/2302.03668
Willis, K., Katz, M., Jayaraman, P. K., & Casey, E. (2025, January 29). Using AI to power AutoConstrain in Fusion automated sketching. Autodesk Research. https://www.research.autodesk.com/blog/using-ai-to-power-autoconstrain-in-fusion-automated-sketching/
Yannakakis, G. N., Liapis, A., & Alexopoulos, C. (2014). Mixed-initiative co-creativity. In Proceedings of the 9th International Conference on the Foundations of Digital Games. University of Malta repository
Yin, S., Zhang, Z., Tang, Z., Gao, K., Xu, X., Yan, K., Li, J., Chen, Y., Chen, Y., Shum, H.-Y., Ni, L. M., Zhou, J., Lin, J., & Wu, C. (2025). Qwen-Image-Layered: Towards inherent editability via layer decomposition [Preprint]. arXiv. https://arxiv.org/abs/2512.15603
Yuan, D., Graham, C., Yakura, H., & Lim, A. (2026). Using the blackbox in embodied AI art practice: Uncertainty at the interface. In Designing Interactive Systems Conference (DIS ’26) (pp. 4181–4201). ACM. https://doi.org/10.1145/3800645.3813020
Yuille, A., & Kersten, D. (2006). Vision as Bayesian inference: Analysis by synthesis? Trends in Cognitive Sciences, 10(7), 301–308. https://doi.org/10.1016/j.tics.2006.05.002
Yun, J., Park, J., Lim, H., Hyung, J., Chung, H., & Choo, J. (2026). ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition [Preprint]. arXiv. https://arxiv.org/abs/2607.25565v1
Zhang, C., Ge, Q., & Han, T. (2026). Overwhelmed by AI? How task difficulty and creative potential moderate cognitive load in human-AI co-creation. In Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems (pp. 1–6). ACM. https://doi.org/10.1145/3772363.3798752
Zhang, K., Mo, L., Chen, W., Sun, H., & Su, Y. (2023). MagicBrush: A manually annotated dataset for instruction-guided image editing. Advances in Neural Information Processing Systems, 36. https://proceedings.neurips.cc/paper_files/paper/2023/hash/64008fa30cba9b4d1ab1bd3bd3d57d61-Abstract-Datasets_and_Benchmarks.html
Zhang, K., Zuo, W., Chen, Y., Meng, D., & Zhang, L. (2016). Beyond a Gaussian denoiser: Residual learning of deep CNN for image denoising [Preprint]. arXiv. https://arxiv.org/abs/1608.03981
Zhang, L., Rao, A., & Agrawala, M. (2023). Adding conditional control to text-to-image diffusion models. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 3836–3847). https://openaccess.thecvf.com/content/ICCV2023/html/Zhang_Adding_Conditional_Control_to_Text-to-Image_Diffusion_Models_ICCV_2023_paper.html
Zhang, Z., Zhou, W., Zhao, J., & Li, H. (2025). Robust multimodal large language models against modality conflict. In Proceedings of the 42nd International Conference on Machine Learning. https://arxiv.org/abs/2507.07151
Zhao, Z., Rees, C., Bailey, G., Jones, M., Robinson, S., & Pearson, J. (2026). Less redraw, more explore: Suggestion and completion for sketch-to-image. In Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems (pp. 1–11). ACM. https://doi.org/10.1145/3772318.3791026

Sources for map operations

Technical documentation and research supporting the operation records on this page.

Find an author, title, or topic

32 sources

Adobe Research. (2025, September 15). Photoshop turns 35: How Adobe Research helps keep creatives on the cutting edge. https://research.adobe.com/news/photoshop-turns-35/
Adobe. (2023, August 17). How Lightroom Classic catalogs work. https://helpx.adobe.com/lightroom-classic/desktop/manage-catalogs-and-files/lightroom-catalog-basics.html
Adobe. (2023, May 24). Nondestructive editing. https://helpx.adobe.com/photoshop/using/nondestructive-editing.html
Adobe. (2024, July 18). Edit layer masks in Photoshop. https://helpx.adobe.com/photoshop/using/editing-layer-masks.html
Adobe. (2024, July 29). Develop module options in Photoshop Lightroom Classic. https://helpx.adobe.com/lightroom-classic/desktop/process-and-develop-photos/develop-module-options.html
Adobe. (2024, October 14). Manage layers and groups in Photoshop. https://helpx.adobe.com/ca/photoshop/using/layers.html
Adobe. (2025, July 15). New features summary for the June 2025 release of Lightroom Classic. https://helpx.adobe.com/lightroom-classic/desktop/help/whats-new/2025-4.html
Adobe. (2025, June 17). Replace distractions with Remove tool. https://helpx.adobe.com/photoshop/using/tool-techniques/remove-tool.html
Adobe. (2025, October 27). Remove distractions with Lightroom Classic’s Remove tool. https://helpx.adobe.com/lightroom-classic/desktop/process-and-develop-photos/remove-tool.html
Adobe. (2026, August 7). How to manage photos within folders in Lightroom Classic. https://helpx.adobe.com/in/lightroom-classic/desktop/manage-catalogs-and-files/photos.html
Adobe. (2026, February 23). Detect and select subjects in Photoshop. https://helpx.adobe.com/photoshop/desktop/make-selections/automatic-color-based-selections/detect-subject-using-select-subject.html
Adobe. (2026, February 23). Generative AI features in Photoshop FAQ. https://helpx.adobe.com/photoshop/desktop/generative-ai/frequently-asked-questions-about-generative-ai-features.html
Adobe. (2026, February 23). History panel settings overview in Photoshop. https://helpx.adobe.com/photoshop/desktop/get-started/set-up-toolbars-panels/history-panel-overview.html
Adobe. (2026, February 23). Improve Select Subject and Remove Background in Photoshop. https://helpx.adobe.com/photoshop/desktop/make-selections/automatic-color-based-selections/improved-select-subject-and-remove-background-results.html
Adobe. (2026, February 23). Use snapshots in History panel in Photoshop. https://helpx.adobe.com/photoshop/desktop/get-started/set-up-toolbars-panels/create-work-snapshots.html
Adobe. (2026, May 1). Enhance fine details in raw images. https://helpx.adobe.com/lightroom-classic/desktop/process-and-develop-photos/enhance-details.html
Adobe. (2026, September 15). Use Generative Fill in Photoshop on desktop. https://helpx.adobe.com/photoshop/desktop/create-open-import-images/create-images/edit-images-with-generative-fill.html
Alliance for OpenUSD. (n.d.). Introduction to USD. https://openusd.org/release/intro.html
Apple. (n.d.). Creating 3D objects from photographs. Apple Developer Documentation. Retrieved October 26, 2026, from https://developer.apple.com/documentation/realitykit/creating-3d-objects-from-photographs/
Artificial Analysis. (n.d.). AI hardware benchmarks. https://artificialanalysis.ai/hardware-inference-stack
Artificial Analysis. (n.d.). Methodology. https://artificialanalysis.ai/methodology
Chan, E. (2021, March 10). Pack more megapixels into your photos with Adobe Super Resolution. Adobe Blog. https://blog.adobe.com/en/publish/2021/03/10/from-the-acr-team-super-resolution
Clark, P. (2026, January 27). New Photoshop innovations provide creative pros more control, realism, and precision. Adobe Blog. https://blog.adobe.com/en/publish/2026/01/27/new-photoshop-innovations-provide-creative-pros-more-control-realism-precision
Epic Games. (n.d.). ML Deformer Framework. Unreal Engine Documentation. Retrieved October 26, 2026, from https://dev.epicgames.com/documentation/en-us/unreal-engine/ml-deformer-framework-in-unreal-engine
Esparza, A. (2023, July 30). How to use Generative Fill in Photoshop. Envato Tuts+. https://design.tutsplus.com/tutorials/how-to-use-generative-fill-in-photoshop--cms-107604
Fitzgerald, T. (2025, June 17). Lightroom 14.4 released. Big changes to Raw Details, Denoise and Super Resolution. Thomas Fitzgerald Photography. https://blog.thomasfitzgeraldphotography.com/blog/2025/6/lightroom-144-released-big-changes-to-raw-details-denoise-and-super-resolution
Kerbl, B., Kopanas, G., Leimkühler, T., & Drettakis, G. (2023). 3D Gaussian splatting for real-time radiance field rendering [Preprint]. arXiv. https://arxiv.org/abs/2308.04079
Krita Foundation. (n.d.). Paint layers. https://docs.krita.org/en/reference_manual/layers_and_masks/paint_layers.html
Mangalick, S. (2019, February 12). Enhance Details. Adobe Blog. https://blog.adobe.com/en/publish/2019/02/12/enhance-details
SideFX. (n.d.). Neural Point Surface 1.0 geometry node. Houdini Documentation. Retrieved October 26, 2026, from https://www.sidefx.com/docs/houdini/nodes/sop/neuralpointsurface.html
SideFX. (n.d.). Nodes. https://www.sidefx.com/docs/houdini/nodes/index.html
SideFX. (n.d.). Stash. https://www.sidefx.com/docs/houdini/nodes/sop/stash.html

Inferential Discovery and Design Adaptation in Visual Generative Workflows