Markdown source

Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge

Conference Context

Session Description

With the boom of vision language models barrier of entry to build vision apps are much lower so developers tend to use them right away. However, these models are very large and inefficient in production. In this talk, I will go through combining vision language models with Skills to build end-to-end vision apps from training to deployment using HF Skills, on top of showing the state-of-the-art in small computer vision/multimodal models.

Media Evidence

Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning — Merve Noyan, Hugging Face (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Evidence Graph

This evidence graph is generated from currently linked source material: official schedule text, related video pages, cached transcripts, visible slide text, dense/reconstructed slide pages, and AI slide-classification audits.

Media Signals

Agent Reading Notes

Use these signals to refine the synopsis, topic links, people/company context, and method notes. If a source is a related external video rather than an exact official recording, keep it framed as supporting evidence.

Transcript Status

Related video transcript availability: English auto-captions. Treat this as supporting context, not a recording of this exact scheduled session unless later confirmed. Not fetched yet.

People

Supporting Slides

Slide Evidence

Synthesis

Synthesized Breakdown

Skill issue: stop deploying vision language models, use them with Skills to build e2e vision apps on edge ## Conference Context - Date/time: 2026-06-29 · 11:40am-12:00pm - Track/room: Vision & OCR · Track 2 - Speaker(s): Merve Noyan - Session type/status: sponsor · confirmed - Track: Vision & OCR - Room: Track 2 - Session type: sponsor - Status: confirmed ## Session Description With the boom of vision language models barrier of entry to build vision apps are much lower so developers tend to use them right away. However, these models are very large and inefficient in production. In this talk, I will go through combining vision language models with Skills to build end-to-end vision apps from training to deployment using HF Skills, on top of showing the state-of-the-art in small computer vision/multimodal models. ## Media Evidence Self-Training Agents: Hermes Agent, HF Traces, Skills, MCP & Finetuning — Merve Noyan, Hugging Face (speaker-match related prior/adjacent AI Engineer video; captions: English auto-captions).

Speaker And Company Context

Topics Covered

Derived Links And Source Material

Novel Concepts / Clever Methods

Evidence Boundary

This synthesis is based on the official schedule and linked source pages. It should be revisited when exact session recordings or transcript-backed secondary sources are available.