Line drawing of a child wearing a head-mounted camera

CCN 2026 Satellite Event

Beyond Curated Datasets

Learning representations from children's everyday experiences

Date Sunday, August 2, 2026
Format Day-long workshop (1–6:30pm)

About

A central goal of cognitive computational neuroscience is to understand how structured neural and behavioral representations emerge from everyday, real-world experience. Yet most current models are trained and evaluated on curated datasets — collections of images, videos, and text disconnected from the temporal and embodied nature of how we actually experience the world.

Models trained on curated datasets achieve striking accuracy in predicting neural and behavioral responses to other curated datasets, but they often fail when asked to learn from, or generalize to, more naturalistic data. This satellite event highlights new methods for characterizing the learning environment available to young children, and new modeling approaches that can learn from these messy yet structured data.

This workshop will explore the idea that moving beyond curated datasets is essential to improve our understanding of human learning.

What to expect

Talks from researchers

Six 25+5 min keynote talks bringing together researchers from developmental psychology, AI, and machine learning. Talks introduce work using infant egocentric video to characterize early learning and computational approaches for training models on such data, alongside the practical challenges of doing both.

Flash talks & breakouts

Three student flash talks showcase emerging research, followed by a moderated breakout-and-discussion session on open questions: What makes naturalistic data fundamentally different from curated datasets? How do we collect rigorous and ethical egocentric data from a child's perspective? What challenges arise when training models on developmental data?

Learning goals

  1. Understand the limitations of curated datasets for modeling human learning.
  2. Gain familiarity with emerging naturalistic datasets and modeling approaches.
  3. Identify opportunities for cross-disciplinary collaboration on developmental data.

Confirmed speakers

Researchers working at the intersection of developmental science and machine learning.

Daniel L.K. YaminsDY

Daniel L.K. Yamins

Professor, Computer Science & Psychology

Stanford University

Bria LongBL

Bria Long

Assistant Professor, Psychology

UC San Diego

Boqing GongBG

Boqing Gong

Assistant Professor & Research Scientist

Boston University / Google

Additional speakers TBD.

Organizers

Drawn from four institutions, spanning computer science, developmental science, psychology, and cognitive neuroscience.

Clíona O'DohertyCO

Clíona O'Doherty

Postdoctoral Researcher · Moderator

Stanford University

Cameron T. EllisCE

Cameron T. Ellis

Assistant Professor, Psychology

Stanford University

Michael C. FrankMF

Michael C. Frank

Professor, Psychology

Stanford University

Jane YangJY

Jane Yang

PhD Student, Psychology

UC San Diego

Karen AdolphKA

Karen Adolph

Professor, Psychology & Neural Science

New York University

Schedule

A day-long workshop with six keynote talks across developmental science and AI, three student flash talks, and moderated breakout discussions. Final room TBD — see the CCN 2026 program.

  1. 1:00 – 1:15

    Opening remarks

  2. 1:15 – 1:45

    Title TBD

    Speaker TBD · 25+5 min

  3. 1:45 – 2:15

    BabyVLM-V2: Toward developmentally grounded pretraining and benchmarking of vision foundation models

    Boqing Gong · Boston University / Google · 25+5 min

  4. 2:15 – 2:45

    Title TBD

    Speaker TBD · 25+5 min

  5. 2:45 – 3:15

    Title TBD

    Speaker TBD · 25+5 min

  6. 3:15 – 4:00

    Emerging research — student flash talks

    Alvin Tan · Jane Yang · TBD · 3 × (12 min + 3 min Q&A)

  7. 4:00 – 4:30

    Coffee break

  8. 4:30 – 5:00

    Constraints on theories of visual learning from children's everyday experience

    Bria Long · UC San Diego · 25+5 min

  9. 5:00 – 5:30

    Title TBD

    Daniel L.K. Yamins · Stanford · 25+5 min

  10. 5:30 – 6:15

    Breakouts & moderated discussion

    Moderated by Clíona O'Doherty · all speakers + audience

  11. 6:15 – 6:30

    Closing

Talk titles and speaker line-up are tentative and may be updated closer to the event.

The data

A glimpse of what developmental egocentric data looks like: head-mounted, high-resolution cameras and the video they produce — adult faces, objects in hand, environments traversed.

The current BabyView camera mounted on a child-safety helmet
The current BabyView camera — a GoPro HERO with integrated battery, mounted on a lightweight child-safety helmet.
Labeled diagram of the BabyView camera components
The camera and its components.

The infant view

Example egocentric frame from a young child's perspective
Example frame from the child's perspective.
Example egocentric frame showing objects in hand
Example frame: objects manipulated within arm's reach.

Relevant papers from speakers and organizers

Figure from Long et al. 2025 BabyView dataset paper
Long et al., 2025 — the BabyView dataset paper.
Figure from Tan et al. 2025 paper on multimodal alignment
Tan et al., 2025 — alignment between infants' visual and linguistic experience.
Figure from Aw et al. 2026 paper on zero-shot world models
Aw et al., 2026 — zero-shot world models as developmentally efficient learners.

Attending

The event is open to all CCN 2026 attendees. We expect 50–80 participants and will keep the session accessible to a broad audience — talks emphasize conceptual insights and intuitive explanations, with familiarity with technical details helpful but not required.

The event is particularly relevant for researchers in machine learning, cognitive science, and neuroscience curious about how developmental perspectives can inform computational models. We strongly encourage questions from trainees and non-experts throughout the session.

When: Sunday, August 2, 2026 (the day before CCN 2026 begins)

Where: Hess Center for Science and Medicine, New York City

To attend the event:

  1. First, register for the main CCN 2026 conference.
  2. Then, submit this form to register for this event.