WebML WG Teleconference – 29 January 2026 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md


WebML WG Teleconference – 29 January 2026 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#webml-wg-teleconference--29-january-2026---1500-1600-utc>

Important

⏰ Early morning warning for the West Coast.

See the timezone table ...
🤝 Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#-logistics>

  *   Chair: Anssi
  *   Scribe: Anssi
  *   IRC: irc://irc.w3.org:6667/#webmachinelearning
  *   IRC web client: https://irc.w3.org/?channels=#webmachinelearning

  *   Zoom joining instructions: internal-webmachinelearning<https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html>
  *   Minutes: https://www.w3.org/2026/01/29-webmachinelearning-minutes.html


🧪 Incubations
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#-incubations>

A debrief from WebML CG Teleconference – 22 January 2026<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-22-cg-agenda.md> (minutes<https://www.w3.org/2026/01/22-webmachinelearning-minutes.html>).

💡 HTTP Archive’s annual state of the web report for Generative AI
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#-http-archives-annual-state-of-the-web-report-for-generative-ai>

Share key takeaways for WebNN, Built-in AI APIs and related capabilities.

  *   ☰ https://almanac.httparchive.org/en/2025/generative-ai


🧠 Web Neural Network API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#-web-neural-network-api>

Tip

Specification<https://www.w3.org/TR/webnn/> | Explainer<https://github.com/webmachinelearning/webnn/blob/main/explainer.md> | Implementation Report<https://wpt.fyi/results/webnn> | Implementation Status<https://webmachinelearning.github.io/webnn-status/>

🎉 Candidate Recommendation Snapshot published
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#-candidate-recommendation-snapshot-published>

Celebrate the latest WebNN API publication milestone.

  *   ◉ W3C Candidate Recommendation Snapshot, 22 January 2026<https://www.w3.org/TR/2026/CR-webnn-20260122/>
  *   ☰ News announcement<https://www.w3.org/news/2026/updated-candidate-recommendation-web-neural-network-webnn-api/>

ℹ️ Accelerated context option implementation feedback
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-accelerated-context-option-implementation-feedback>

Discuss new implementation feedback and seek consensus on the proposed spec change to add "no-acceleration" to powerPreference enum.

  *   ⨀ webmachinelearning/webnn#911<https://github.com/webmachinelearning/webnn/issues/911>

ℹ️ Model Cache API
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-model-cache-api>

Reinvigorate discussion on the Model Cache API. Discuss constraints imposed by implementations. Revise the explainer as appropriate.

  *   ⨀ webmachinelearning/webnn#807<https://github.com/webmachinelearning/webnn/issues/807>
  *   ☰ cache-explainer.md<https://github.com/webmachinelearning/webnn/blob/main/cache-explainer.md>

ℹ️ Floating point accuracy for sin and cos with range constraint
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-floating-point-accuracy-for-sin-and-cos-with-range-constraint>

Discuss the proposal to define accuracy for sin and cos, any WPT enhancements.

  *   ⨀ webmachinelearning/webnn#914<https://github.com/webmachinelearning/webnn/issues/914>

ℹ️ The minimum data type set
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-the-minimum-data-type-set>

Discuss the group's preference wrt "report backend inconsistencies exactly" v "normalize to provide a predictable WebNN API".

  *   ⨀ webmachinelearning/webnn#853<https://github.com/webmachinelearning/webnn/issues/853>

ℹ️ Support flexible input sizes
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-support-flexible-input-sizes>

Discuss Mozilla's implementation feedback.

  *   ⨀ webmachinelearning/webnn#883<https://github.com/webmachinelearning/webnn/issues/883>

ℹ️ Operator chaining
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2026-01-29-wg-agenda.md#%E2%84%B9%EF%B8%8F-operator-chaining>

Revisit operator chaining proposal with new information.

  *   ⨀ webmachinelearning/webnn#106<https://github.com/webmachinelearning/webnn/issues/106>