WebML WG Teleconference – 14 August 2025 - 15:00-16:00 UTC

Latest version: https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md


WebML WG Teleconference – 14 August 2025 - 15:00-16:00 UTC
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#webml-wg-teleconference--14-august-2025---1500-1600-utc>
See the timezone table ...
Logistics
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-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: https://lists.w3.org/Archives/Member/internal-webmachinelearning/2023Jun/0000.html

  *   Minutes: https://www.w3.org/2025/08/14-webmachinelearning-minutes.html


Agenda
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#agenda>
📣 TPAC 2025 F2F announced (Kobe, Japan, 10–14 Nov 2025)
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#-tpac-2025-f2f-announced-kobe-japan-1014-nov-2025>

Discuss the overall TPAC 2025 plan and gather feedback on how to avoid scheduling conflicts for participants. Confirmed time available for the WebML community:

  *   10 November 2025, 09:00–16:45 Japan Standard Time
  *   11 November 2025, 09:45-18:00 Japan Standard Time

Resources:

  *   TPAC 2025 overview https://www.w3.org/2025/11/TPAC/

  *   Registration https://www.w3.org/2025/11/TPAC/#registration


🤖 Agentic web workstream
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#-agentic-web-workstream>

Discuss the newly launched agentic web workstream, initial scope of work, next steps. Review the WIP WebMCP explainer.

  *   WebMCP explainer https://github.com/webmachinelearning/webmcp


🏷️ Operator specific issues
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#%EF%B8%8F-operator-specific-issues>

Review and discuss operator specific issues that reduce code complexity and improve maintainability, e.g.:

  *   Simplify the operand layout support of conv2d and pooling 2d operations

     *   ⨀ webmachinelearning/webnn#324<https://github.com/webmachinelearning/webnn/issues/324>
     *   ⛙ webmachinelearning/webnn#770<https://github.com/webmachinelearning/webnn/pull/770>
  *   Support uint8/int8 input for resample2d

     *   ⨀ webmachinelearning/webnn#872<https://github.com/webmachinelearning/webnn/issues/872>
  *   Clarify 0D tensor supports axis-dependent operations

     *   ⨀ webmachinelearning/webnn#873<https://github.com/webmachinelearning/webnn/issues/873>
  *   Normalize the behavior when NaN is used for minValue or maxValue of clamp operator

     *   ⨀ webmachinelearning/webnn#874<https://github.com/webmachinelearning/webnn/issues/874>
  *   Minimum data type set

     *   ⨀ webmachinelearning/webnn#853<https://github.com/webmachinelearning/webnn/issues/853>
     *   Proposed WPT changes: quantizeLinear #879<https://github.com/webmachinelearning/webnn/issues/879>

🏷️ Wide review updates
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#%EF%B8%8F-wide-review-updates>

  *   ⛙ New accessibility considerations webmachinelearning/webnn#869<https://github.com/webmachinelearning/webnn/pull/869>
  *   ⨀ Future-proofing privacy considerations webmachinelearning/webnn#875<https://github.com/webmachinelearning/webnn/issues/875>
  *   ⨀ Evaluate sustainability impact webmachinelearning/webnn#861<https://github.com/webmachinelearning/webnn/issues/861>

ℹ️ Open PRs
<https://github.com/webmachinelearning/meetings/blob/main/telcons/2025-08-14-wg-agenda.md#%E2%84%B9%EF%B8%8F-open-prs>

Review any open PRs that benefit from high-bandwidth discussion.

  *   ⛙ https://github.com/webmachinelearning/webnn/pulls