pith. machine review for the scientific record. sign in

arxiv: 2604.05120 · v4 · submitted 2026-04-06 · 💻 cs.HC · cs.MA

Recognition: 3 theorem links

· Lean Theorem

Designing Digital Humans with Ambient Intelligence

Mengyu Chen , Pranav Deshpande , Runqing Yang , Elvir Azanli , Joseph Ligman , Shaohan Hu , Chun-Fu Chen
Authors on Pith no claims yet

Pith reviewed 2026-05-10 19:00 UTC · model grok-4.3

classification 💻 cs.HC cs.MA
keywords digital humansambient intelligencecontext-aware agentsproactive assistancevirtual agentshuman-computer interactionprivacy strategiesIoT integration
0
0 comments X

The pith

Ambient intelligence gives digital humans the ability to sense surroundings and act proactively instead of responding only to spoken queries.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper sets out to show that digital humans, which are virtual conversational agents, become more capable when linked to ambient intelligence sources such as environmental sensors and IoT data. This link supplies real-world context so the agents can anticipate needs, coordinate across devices, and maintain ongoing personalized relationships with users. The authors develop this idea through a framework that assigns specific roles to ambient data, a design space covering different degrees of initiative and privacy handling, and illustrative cases drawn from retail and financial services. If the integration works as described, everyday interactions with virtual agents would shift from isolated question-and-answer exchanges to context-sensitive assistance that fits the actual situation.

Core claim

Integrating ambient intelligence with digital humans enables situational awareness of the user's environment, anticipatory and proactive assistance, seamless cross-device interactions, and personalized long-term user support. This is achieved by defining key roles that ambient data plays in shaping agent behavior, outlining a design space that includes levels of proactivity and privacy strategies, and demonstrating application patterns through case studies in financial and retail services, along with an overall architecture and responsible-design guidelines.

What carries the argument

The conceptual framework that assigns explicit roles to ambient intelligence data in determining how digital humans behave, together with the accompanying design space that varies proactivity and privacy choices.

If this is right

  • Digital humans can maintain awareness of the physical setting around the user rather than operating from dialogue alone.
  • Assistance can be offered before a user asks, based on detected conditions in the environment.
  • Interactions can move smoothly from one device to another without the user restarting the conversation.
  • Support can accumulate knowledge over repeated sessions using ongoing contextual information.
  • Design choices about how much initiative the agent takes and how much data it uses become explicit parameters that developers must set.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same role definitions could apply to other classes of AI agents that currently lack environmental context, such as voice assistants in homes or offices.
  • The privacy strategies may reduce adoption barriers in regulated industries where data handling rules are strict.
  • The architecture could support testing whether proactive behavior improves outcomes in high-stakes service encounters compared with reactive responses.

Load-bearing premise

Ambient intelligence data can be obtained and combined with digital human systems without major technical failures, privacy violations, or user resistance that would prevent the proposed roles and patterns from working in practice.

What would settle it

A deployment study in which adding ambient sensor data to a digital human produces no measurable gain in user task success or satisfaction, or triggers widespread refusal due to privacy concerns, would show that the integration does not deliver the described situational awareness and proactive benefits.

Figures

Figures reproduced from arXiv: 2604.05120 by Chun-Fu Chen, Elvir Azanli, Joseph Ligman, Mengyu Chen, Pranav Deshpande, Runqing Yang, Shaohan Hu.

Figure 1
Figure 1. Figure 1: A conceptual illustration of an ambient intelligence-enhanced digital human framework. The digital human [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Remote video-call example concept interface for a guided financial review. The digital human is shown in the [PITH_FULL_IMAGE:figures/full_fig_p016_2.png] view at source ↗
read the original abstract

Digital humans are lifelike virtual agents capable of natural conversation and are increasingly deployed in domains like retail and finance. However, most current digital humans operate in isolation from their surroundings and lack contextual awareness beyond the dialogue itself. We address this limitation by integrating ambient intelligence (AmI) - i.e., environmental sensors, IoT data, and contextual modeling - with digital human systems. This integration enables situational awareness of the user's environment, anticipatory and proactive assistance, seamless cross-device interactions, and personalized long-term user support. We present a conceptual framework defining key roles that AmI can play in shaping digital human behavior, a design space highlighting dimensions such as proactivity levels and privacy strategies, and application-driven patterns with case studies in financial and retail services. We also discuss an architecture for ambient-enabled digital humans and provide guidelines for responsible design regarding privacy and data governance. Together, our work positions ambient intelligent digital humans as a new class of interactive agents powered by AI that respond not only to users' queries but also to the context and situations in which the interaction occurs.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. The manuscript proposes integrating ambient intelligence (AmI)—environmental sensors, IoT data, and contextual modeling—with digital human systems to address their current isolation from surroundings. It defines key roles for AmI in shaping digital human behavior, a design space covering dimensions such as proactivity levels and privacy strategies, application-driven patterns illustrated by case studies in financial and retail services, an architecture for ambient-enabled digital humans, and guidelines for responsible design on privacy and data governance. The central claim is that this integration enables situational awareness of the user's environment, anticipatory and proactive assistance, seamless cross-device interactions, and personalized long-term user support.

Significance. If the conceptual framework is adopted and followed by implementation work, it could provide a useful structured approach for designing context-aware interactive agents in HCI and AI applications, particularly in domains like retail and finance. The explicit attention to responsible design guidelines and the framing of a new class of agents represent strengths in addressing ethical considerations at the proposal stage.

major comments (2)
  1. [architecture] The architecture section describes ambient-enabled digital humans at a conceptual level but does not specify data integration mechanisms, sensor fusion approaches, or handling of incomplete/uncertain AmI inputs; this is load-bearing for the claim that the integration enables seamless cross-device interactions and situational awareness.
  2. [application patterns and case studies] The case studies in financial and retail services assert that the proposed patterns enable anticipatory assistance and personalized support but provide no implementation details, pseudocode, or evaluation criteria; this gap between conceptual description and demonstrated capability undermines the translation to effective real systems.
minor comments (2)
  1. [design space] The design space discussion of proactivity levels and privacy strategies would benefit from a summary table or explicit mapping to the case studies to improve readability and allow readers to quickly compare options.
  2. [abstract and introduction] The abstract and introduction could more explicitly distinguish the proposed framework as a design proposal rather than an implemented system to set appropriate expectations for the absence of empirical validation.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback and positive recommendation for minor revision. We address each major comment below, clarifying the conceptual scope of the work while noting where we can strengthen the manuscript.

read point-by-point responses

  1. Referee: [architecture] The architecture section describes ambient-enabled digital humans at a conceptual level but does not specify data integration mechanisms, sensor fusion approaches, or handling of incomplete/uncertain AmI inputs; this is load-bearing for the claim that the integration enables seamless cross-device interactions and situational awareness.

    Authors: We agree the architecture is presented conceptually, consistent with the paper's focus on a high-level framework rather than system implementation. The claims for situational awareness and cross-device interactions are grounded in the defined AmI roles (context provider, behavior modulator) and design space dimensions, which establish the conceptual mechanisms for integration. We do not claim specific technical solutions such as particular fusion algorithms. To improve clarity, we will add a brief discussion of example data integration strategies and uncertainty handling approaches (e.g., probabilistic context modeling) in the revised architecture section, while preserving the conceptual emphasis. revision: partial

  2. Referee: [application patterns and case studies] The case studies in financial and retail services assert that the proposed patterns enable anticipatory assistance and personalized support but provide no implementation details, pseudocode, or evaluation criteria; this gap between conceptual description and demonstrated capability undermines the translation to effective real systems.

    Authors: The case studies are illustrative scenarios designed to demonstrate application of the proposed patterns within the framework, not empirical demonstrations or implemented prototypes. As a conceptual contribution, the manuscript does not include pseudocode, system evaluations, or implementation details, which would exceed its stated scope of defining roles, design space, and guidelines. This is standard for framework papers in HCI. We can strengthen the presentation by expanding the scenarios with additional contextual details and suggested evaluation criteria in the revision. revision: partial

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper is a purely conceptual design proposal that defines roles for ambient intelligence in digital human systems, a design space, application patterns, an architecture, and responsible-design guidelines. No equations, derivations, fitted parameters, predictions, or first-principles results exist that could reduce to inputs by construction. The central claim follows directly from the stated definition of AmI integration and the components presented; no self-citation load-bearing steps, ansatzes, or renamings of known results appear in any derivation chain.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper is conceptual and relies on standard domain assumptions from ambient intelligence and HCI without introducing fitted numerical parameters or new physical entities.

axioms (1)
  • domain assumption Ambient intelligence systems can supply reliable, timely contextual data from environmental sensors and IoT devices that meaningfully shapes digital human behavior.
    Invoked throughout the description of situational awareness and proactive assistance.

pith-pipeline@v0.9.0 · 5500 in / 1129 out tokens · 63964 ms · 2026-05-10T19:00:31.855078+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

197 extracted references · 5 canonical work pages · 4 internal anchors

  1. [1]

    D., DEY, A

    ABOWD, G. D., DEY, A. K., BROWN, P. J., DAVIES, N., SMITH, M.,ANDSTEGGLES, P. Towards a better understanding of context and context-awareness, 1999

    1999

  2. [2]

    GPT-4 Technical Report

    ACHIAM, J., ADLER, S., AGARWAL, S., AHMAD, L., AKKAYA, I., ALEMAN, F. L., ALMEIDA, D., AL- TENSCHMIDT, J., ALTMAN, S., ANADKAT, S.,ET AL. Gpt-4 technical report.arXiv preprint arXiv:2303.08774 (2023)

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  3. [3]

    CRC Press, 2018

    AKENINE-MÖLLER, T., HAINES, E.,ANDHOFFMAN, N.Real-Time Rendering, 4th ed. CRC Press, 2018

    2018

  4. [4]

    H., EISA, T

    ALI, A., ABDRAZAK, S., OTHMAN, S. H., EISA, T. A. E., AL-DHAQM, A., NASSER, M., ELHASSAN, T., ELSHAFIE, H.,ANDSAEED, A. Financial fraud detection based on machine learning: A systematic literature review.Applied Sciences 12, 19 (2022), 9637

    2022

  5. [5]

    Open 3D engine (O3DE)

    AMAZONWEBSERVICES,ANDOPEN3D FOUNDATION. Open 3D engine (O3DE). https://o3de.org/, 2021

    2021

  6. [6]

    N., INKPEN, K., TEEVAN, J., KIKIN-GIL, R.,ANDHORVITZ, E

    AMERSHI, S., WELD, D., VORVOREANU, M., FOURNEY, A., NUSHI, B., COLLISSON, P., SUH, J., IQBAL, S., BENNETT, P. N., INKPEN, K., TEEVAN, J., KIKIN-GIL, R.,ANDHORVITZ, E. Guidelines for human-AI interaction. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(2019), ACM

    2019

  7. [7]

    Deep evidential regression

    AMINI, A., SCHWARTING, W., SOLEIMANY, A.,ANDRUS, D. Deep evidential regression. InAdvances in Neural Information Processing Systems(2020), vol. 33

    2020

  8. [8]

    F., MCLOUGHLIN, L., LIAROKAPIS, F., PETERS, C., PETRIDIS, P.,AND DEFREITAS, S

    ANDERSON, E. F., MCLOUGHLIN, L., LIAROKAPIS, F., PETERS, C., PETRIDIS, P.,AND DEFREITAS, S. Developing serious games for cultural heritage: A state-of-the-art review.Virtual Reality 14, 4 (2020), 255–275

    2020

  9. [9]

    AI, big data, and the future of consent.AI & Society 37 (2022), 1715–1728

    ANDREOTTA, M., KIRKHAM, N.,ANDRIZZI, M. AI, big data, and the future of consent.AI & Society 37 (2022), 1715–1728

    2022

  10. [10]

    Computer use

    ANTHROPIC. Computer use. https://docs.anthropic.com/en/docs/agents-and-tools/ computer-use, 2024. Accessed: 2026-03-08

    2024

  11. [11]

    Model card: Claude 3

    ANTHROPIC. Model card: Claude 3. https://www-cdn.anthropic.com/ de8ba9b01c9ab7cbabf5c33b80b7bbc618857627/Model_Card_Claude_3.pdf, 2024. PDF

    2024

  12. [12]

    Model context protocol (MCP)

    ANTHROPIC. Model context protocol (MCP). https://modelcontextprotocol.io, 2024. Accessed: 2026-03-08

    2024

  13. [13]

    The internet of things: A survey.Computer Networks 54, 15 (2010), 2787–2805

    ATZORI, L., IERA, A.,ANDMORABITO, G. The internet of things: A survey.Computer Networks 54, 15 (2010), 2787–2805

    2010

  14. [14]

    N.,ANDBEALL, A

    BAILENSON, J. N.,ANDBEALL, A. C. Transformed social interaction: Exploring the digital plasticity of avatars.Avatars at Work and Play(2006), 1–16

    2006

  15. [15]

    A survey on context-aware systems.Int

    BALDAUF, M., DUSTDAR, S.,ANDROSENBERG, F. A survey on context-aware systems.Int. J. Ad Hoc Ubiquitous Comput. 2, 4 (2007), 263–277. 21 Designing Digital Humans

    2007

  16. [16]

    Proxemic interaction: Designing for a proximity and orientation-aware environment

    BALLENDAT, T., MARQUARDT, N.,ANDGREENBERG, S. Proxemic interaction: Designing for a proximity and orientation-aware environment. InACM International Conference on Interactive Tabletops and Surfaces (ITS)(2010), ACM, pp. 121–130

    2010

  17. [17]

    W., ANDGROSS, M

    BEELER, T., HAHN, F., BRADLEY, D., BICKEL, B., BEARDSLEY, P., GOTSMAN, C., SUMNER, R. W., ANDGROSS, M. High-quality passive facial performance capture using anchor frames.ACM Transactions on Graphics 30, 4 (2011), 75:1–75:10

    2011

  18. [18]

    A survey of context modelling and reasoning techniques, 2010

    BETTINI, C., BRDICZKA, O., HENRICKSEN, K., INDULSKA, J., NICKLAS, D., RANGANATHAN, A.,AND RIBONI, D. A survey of context modelling and reasoning techniques, 2010. Context Modelling, Reasoning and Management

    2010

  19. [19]

    Social dialogue with embodied conversational agents

    BICKMORE, T.,ANDCASSELL, J. Social dialogue with embodied conversational agents. 23–54

  20. [20]

    W., PFEIFER, L

    BICKMORE, T. W., PFEIFER, L. M.,ANDJACK, B. W. Taking the time to care: Empowering low health literacy hospital patients with virtual nurse agents. 1265–1274

  21. [21]

    W., VARDOULAKIS, L

    BICKMORE, T. W., VARDOULAKIS, L. M. P.,ANDSCHULMAN, D. Tinker: A relational agent museum guide. Autonomous Agents and Multi-Agent Systems 27, 2 (2013), 254–276

    2013

  22. [22]

    A morphable model for the synthesis of 3D faces

    BLANZ, V.,ANDVETTER, T. A morphable model for the synthesis of 3D faces. 187–194

  23. [23]

    Workarena++: Towards compositional planning and reasoning-based common knowledge work tasks, 2024

    BOISVERT, L., THAKKAR, M., GASSE, M., CACCIA, M., LESELLIERDECHEZELLES, T., CAPPART, Q., CHAPADOS, N.,ANDLACOSTE, A. Workarena++: Towards compositional planning and reasoning-based common knowledge work tasks, 2024

    2024

  24. [24]

    M., GELLY, G., KORSHUNOV, P., LAVECHIN, M., FUSEZ, D., TITEUX, H., BOUAZIZ, W.,ANDGILL, M.-P

    BREDIN, H., YIN, R., CORIA, J. M., GELLY, G., KORSHUNOV, P., LAVECHIN, M., FUSEZ, D., TITEUX, H., BOUAZIZ, W.,ANDGILL, M.-P. pyannote.audio: Neural building blocks for speaker diarization. InIEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)(2020), pp. 7124–7128

    2020

  25. [25]

    RT-2: Vision-language-action models transfer web knowledge to robotic control

    BROHAN, A., BROWN, N., CARBAJAL, J., CHEBOTAR, Y., CHEN, X., CHOROMANSKI, K.,ET AL. RT-2: Vision-language-action models transfer web knowledge to robotic control

  26. [26]

    Genie: Generative interactive environments

    BRUCE, J., DENNIS, M., EDWARDS, A., PARKER-HOLDER, J., SHI, Y., HUGHES, E., LAI, M., MBER, A., DASAGI, R.,ET AL. Genie: Generative interactive environments

  27. [27]

    N.,ANDMARQUARDT, N

    BRUDY, F., HOLZ, C., RÄDLE, R., WU, C.-J., HOUBEN, S., KLOKMOSE, C. N.,ANDMARQUARDT, N. Cross-device taxonomy: Survey, opportunities and challenges of interactions spanning across multiple devices. InProceedings of the 2019 CHI Conference on Human Factors in Computing Systems(Glasgow, Scotland, UK, 2019), Association for Computing Machinery, p. Paper 562

    2019

  28. [28]

    A tutorial on human activity recognition using body-worn inertial sensors.ACM Computing Surveys 46, 3 (2014)

    BULLING, A., BLANKE, U.,ANDSCHIELE, B. A tutorial on human activity recognition using body-worn inertial sensors.ACM Computing Surveys 46, 3 (2014)

    2014

  29. [29]

    Smartsnap: Proactive evidence seeking for self-verifying agents, 2025

    CAI, S., QIN, Y., LIN, H., XU, Z., LI, G., SHI, Y., LI, Z., MAO, Y., CAI, S., TAN, X., LIANG, Y., LI, K., ANDSUN, X. Smartsnap: Proactive evidence seeking for self-verifying agents, 2025

    2025

  30. [30]

    Context-awareness for the design of smart-product service systems: Literature review, 2022

    CARRERA-RIVERA, A., LARRINAGA, F.,ANDLASA, G. Context-awareness for the design of smart-product service systems: Literature review, 2022

    2022

  31. [31]

    K.,AND ANDERLJUNG, M

    CHAN, A., WEI, K., HUANG, S., RAJKUMAR, N., PERRIER, E., LAZAR, S., HADFIELD, G. K.,AND ANDERLJUNG, M. Infrastructure for AI agents, 2025. Accepted to TMLR

    2025

  32. [32]

    B., MITCHELL, N., PILLUTLA, K.,ANDRUSH, K

    CHARLES, Z., GANESH, A., MCKENNA, R., MCMAHAN, H. B., MITCHELL, N., PILLUTLA, K.,ANDRUSH, K. Fine-tuning large language models with user-level differential privacy, 2024

    2024

  33. [33]

    Benchmarking large language models in retrieval-augmented generation

    CHEN, J., LIN, H., HAN, X.,ANDSUN, L. Benchmarking large language models in retrieval-augmented generation. InProceedings of the AAAI Conference on Artificial Intelligence(2024), vol. 38

    2024

  34. [34]

    D., COOK, D

    CHEN, L., HOEY, J., NUGENT, C. D., COOK, D. J.,ANDYU, Z. Sensor-based activity recognition.IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 42, 6 (2012), 790–808

    2012

  35. [35]

    CHEZELLES, T. L. S. D., GASSE, M., DROUIN, A., CACCIA, M., BOISVERT, L., THAKKAR, M., MARTY, T., ASSOUEL, R., SHAYEGAN, S. O., JANG, L. K., LÙ, X. H., YORAN, O., KONG, D., XU, F. F., REDDY, S., CAPPART, Q., NEUBIG, G., SALAKHUTDINOV, R., CHAPADOS, N.,ANDLACOSTE, A. The browsergym ecosystem for web agent research, 2025

    2025

  36. [36]

    J., YANG, H.,ANDMAO, Z

    CHO, M., CAO, Y., SUN, J., ZHANG, Q., PAVONE, M., PARK, J. J., YANG, H.,ANDMAO, Z. M. Cocoon: Robust multi-modal perception with uncertainty-aware sensor fusion, 2024

    2024

  37. [37]

    H.,ANDBRENNAN, S

    CLARK, H. H.,ANDBRENNAN, S. E. Grounding in communication

  38. [38]

    Marvelous designer.https://www.marvelousdesigner.com/, 2021

    CLO VIRTUALFASHION. Marvelous designer.https://www.marvelousdesigner.com/, 2021. 22 Designing Digital Humans

    2021

  39. [39]

    J., AUGUSTO, J

    COOK, D. J., AUGUSTO, J. C.,ANDJAKKULA, V. R. Ambient intelligence: Technologies, applications, and opportunities, 2009

    2009

  40. [40]

    CryEngine documentation.https://docs.cryengine.com/, 2021

    CRYTEK. CryEngine documentation.https://docs.cryengine.com/, 2021

    2021

  41. [41]

    The power of noise: Redefining retrieval for RAG systems

    CUCONASU, F., TRAPPOLINI, G., SICILIANO, F., FILICE, S., CAMPAGNANO, C., MAAREK, Y., TONEL- LOTTO, N.,ANDSILVESTRI, F. The power of noise: Redefining retrieval for RAG systems. InProceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval(2024), ACM

    2024

  42. [42]

    CUDEIRO, D., BOLKART, T., LAIDLAW, C., RANJAN, A.,ANDBLACK, M. J. Capture, learning, and synthesis of 3D speaking styles. 10101–10111

  43. [43]

    Daz Studio and Genesis 8 platform.https://www.daz3d.com/, 2021

    DAZ3D. Daz Studio and Genesis 8 platform.https://www.daz3d.com/, 2021

    2021

  44. [44]

    J., MONFORT, S

    DEVISSER, E. J., MONFORT, S. S., MCKENDRICK, R., SMITH, M. A. B., MCKNIGHT, P. E., KRUEGER, F.,ANDPARASURAMAN, R. Almost human: Anthropomorphism increases trust resilience in cognitive agents. Journal of Experimental Psychology: Applied 22, 3 (2016), 331–349

    2016

  45. [45]

    J., PEETERS, M

    DEVISSER, E. J., PEETERS, M. M. M., JUNG, M. F., KOHN, S., SHAW, T. H., PAK, R.,ANDNEERINCX, M. A. Towards a theory of longitudinal trust calibration in human–robot teams.International Journal of Social Robotics 12(2020), 459–478

    2020

  46. [46]

    Acquiring the reflectance field of a human face

    DEBEVEC, P., HAWKINS, T., TCHOU, C., DUIKER, H.-P., SAROKIN, W.,ANDSAGAR, M. Acquiring the reflectance field of a human face. 145–156

  47. [47]

    Mind2web: Towards a generalist agent for the web

    DENG, X., GU, Y., ZHENG, B., CHEN, S., STEVENS, S., WANG, B., SUN, H.,ANDSU, Y. Mind2web: Towards a generalist agent for the web. InAdvances in Neural Information Processing Systems(2023), vol. 36

    2023

  48. [48]

    H.,ANDLAM, W

    DENG, Y., LIAO, L., LEI, W., YANG, G. H.,ANDLAM, W. Proactive conversational AI: A comprehensive survey of advancements and opportunities.ACM Transactions on Information Systems 43, 3 (2025), 1–45

    2025

  49. [49]

    Simsensei kiosk: A virtual human interviewer for healthcare decision support

    DEVAULT, D., ARTSTEIN, R., BENN, G., DEY, T., FAST, E., GAINER, A., GEORGILA, K., GRATCH, J., HARTHOLT, A., LHOMMET, M., LUCAS, G., MARSELLA, S., MORBINI, F., NAZARIAN, A., SCHERER, S., STRATOU, G., SURI, A., TRAUM, D., WOOD, R., XU, Y., RIZZO, A.,ANDMORENCY, L.-P. Simsensei kiosk: A virtual human interviewer for healthcare decision support. InProceedings...

    2014

  50. [50]

    DEY, A. K. Understanding and using context.Personal and Ubiquitous Computing 5, 1 (2001), 4–7

    2001

  51. [51]

    K., ABOWD, G

    DEY, A. K., ABOWD, G. D.,ANDSALBER, D. A conceptual framework and a toolkit for supporting the rapid prototyping of context-aware applications, 2001

    2001

  52. [52]

    Popul8: 3D avatar creation.https://www.didimo.co/, 2023

    DIDIMO. Popul8: 3D avatar creation.https://www.didimo.co/, 2023

    2023

  53. [53]

    DRIESS, D., XIA, F., SAJJADI, M. S. M., LYNCH, C., CHOWDHERY, A.,ET AL. PaLM-E: An embodied multimodal language model

  54. [54]

    Times Books, 2003

    EKMAN, P.Emotions Revealed: Recognizing Faces and Feelings to Improve Communication and Emotional Life. Times Books, 2003

    2003

  55. [55]

    Frostbite engine.https://www.ea.com/frostbite, 2020

    ELECTRONICARTS. Frostbite engine.https://www.ea.com/frostbite, 2020

    2020

  56. [56]

    MetaHuman creator documentation

    EPICGAMES. MetaHuman creator documentation. https://docs.metahuman.unrealengine.com/, 2021

    2021

  57. [57]

    Pixel streaming documentation

    EPICGAMES. Pixel streaming documentation. https://docs.unrealengine.com/en-US/ SharingAndReleasing/PixelStreaming/, 2021

    2021

  58. [58]

    Unreal Engine 5 documentation.https://docs.unrealengine.com/5.0/, 2021

    EPICGAMES. Unreal Engine 5 documentation.https://docs.unrealengine.com/5.0/, 2021

    2021

  59. [59]

    ERICKSON, T.,ANDKELLOGG, W. A. Social translucence: an approach to designing systems that support social processes.ACM Trans. Comput.-Hum. Interact. 7, 1 (Mar. 2000), 59–83

    2000

  60. [60]

    GPAI code of practice

    EU AI OFFICE. GPAI code of practice. https://digital-strategy.ec.europa.eu/en/policies/ gpai-code-practice, 2025. Accessed: 2026-03-08

    2025

  61. [61]

    Regulation (EU) 2024/1689 of the european parliament and of the council laying down harmonised rules on artificial intelligence (AI act)

    EUROPEANPARLIAMENT ANDCOUNCIL OF THEEUROPEANUNION. Regulation (EU) 2024/1689 of the european parliament and of the council laying down harmonised rules on artificial intelligence (AI act). Official Journal of the European Union, L series, 2024

    2024

  62. [62]

    User modeling in human–computer interaction.User Modeling and User-Adapted Interaction 11, 1 (2001), 65–86

    FISCHER, G. User modeling in human–computer interaction.User Modeling and User-Adapted Interaction 11, 1 (2001), 65–86

    2001

  63. [63]

    P., VANHECKE, K., DECOSTER, L.,ANDNANNI, M

    FRIEDMAN, A., KNIJNENBURG, B. P., VANHECKE, K., DECOSTER, L.,ANDNANNI, M. Privacy aspects of recommender systems. InRecommender Systems Handbook. Springer, 2015, pp. 649–688. 23 Designing Digital Humans

    2015

  64. [64]

    Dynamic neural radiance fields for monocular 4D facial avatar reconstruction

    GAFNI, G., THIES, J., ZOLLHÖFER, M.,ANDNIESSNER, M. Dynamic neural radiance fields for monocular 4D facial avatar reconstruction

  65. [65]

    Retrieval-augmented generation for large language models: A survey, 2024

    GAO, Y., XIONG, Y., GAO, X., JIA, K., PAN, J., BI, Y., DAI, Y., SUN, J., WANG, M.,ANDWANG, H. Retrieval-augmented generation for large language models: A survey, 2024

    2024

  66. [66]

    GARAU, M., SLATER, M., VINAYAGAMOORTHY, V., BROGNI, A., STEED, A.,ANDSASSE, M. A. The impact of avatar realism and eye gaze control on perceived quality of communication in a shared immersive virtual environment. 529–536

  67. [67]

    Multi-view conformal learning for heterogeneous sensor fusion, 2024

    GARCIA-CEJA, E. Multi-view conformal learning for heterogeneous sensor fusion, 2024

    2024

  68. [68]

    Acting with Technology

    GAY, G.,ANDHEMBROOKE, H.Activity-Centered Design: An Ecological Approach to Designing Smart Tools and Usable Systems. Acting with Technology. The MIT Press, 2004

    2004

  69. [69]

    Gemini: A family of highly capable multimodal models, 2023

    GEMINITEAM, GOOGLE. Gemini: A family of highly capable multimodal models, 2023

    2023

  70. [70]

    S., XU, M., PATROS, P., WU, H., KAUR, R., KAUR, K., FULLER, S.,ANDSINGH, M

    GILL, S. S., XU, M., PATROS, P., WU, H., KAUR, R., KAUR, K., FULLER, S.,ANDSINGH, M. Transformative effects of ChatGPT on modern education: Emerging era of AI chatbots.Internet of Things and Cyber-Physical Systems 4(2024), 19–23

    2024

  71. [71]

    Godot engine documentation.https://docs.godotengine.org/, 2021

    GODOTENGINE. Godot engine documentation.https://docs.godotengine.org/, 2021

    2021

  72. [72]

    Agent-to-agent protocol (A2A)

    GOOGLE. Agent-to-agent protocol (A2A). https://a2a-protocol.org/latest/, 2025. Accessed: 2026- 03-08

    2025

  73. [73]

    Genie 2: A large-scale foundation world model

    GOOGLEDEEPMIND. Genie 2: A large-scale foundation world model. https://deepmind.google/ discover/blog/genie-2-a-large-scale-foundation-world-model/, 2024

    2024

  74. [74]

    Genie 3: Photorealistic interactive world generation

    GOOGLEDEEPMIND. Genie 3: Photorealistic interactive world generation. https://deepmind.google/ discover/blog/genie-3/, 2025

    2025

  75. [75]

    The Llama 3 Herd of Models

    GRATTAFIORI, A., DUBEY, A., JAUHRI, A., PANDEY, A., KADIAN, A., AL-DAHLE, A., LETMAN, A., MATHUR, A., SCHELTEN, A., VAUGHAN, A.,ET AL. The llama 3 herd of models.arXiv preprint arXiv:2407.21783(2024)

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  76. [76]

    Internet of things (iot): A vision, architectural elements, and future directions, 2013

    GUBBI, J., BUYYA, R., MARUSIC, S.,ANDPALANISWAMI, M. Internet of things (iot): A vision, architectural elements, and future directions, 2013

    2013

  77. [77]

    V., WIEST, O.,ANDZHANG, X

    GUO, T., CHEN, X., WANG, Y., CHANG, R., PEI, S., CHAWLA, N. V., WIEST, O.,ANDZHANG, X. Large language model based multi-agents: A survey of progress and challenges, 2024

    2024

  78. [78]

    World Models

    HA, D.,ANDSCHMIDHUBER, J. World models.arXiv preprint arXiv:1803.10122(2018)

    work page internal anchor Pith review arXiv 2018

  79. [79]

    Dream to control: Learning behaviors by latent imagination

    HAFNER, D., LILLICRAP, T., BA, J.,ANDNOROUZI, M. Dream to control: Learning behaviors by latent imagination

  80. [80]

    Sophia the robot.https://www.hansonrobotics.com/sophia/, 2021

    HANSONROBOTICS. Sophia the robot.https://www.hansonrobotics.com/sophia/, 2021

    2021

Showing first 80 references.