Episode

Distilling Transformers and Diffusion Models for Robust Edge Use Cases with Fatih Porikli - #738

Podcast
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Published
Jul 9, 2025
Duration seconds
3629
Processing state
failed
Canonical source
https://twimlai.com/podcast/twimlai/distilling-transformers-and-diffusion-models-for-robust-edge-use-cases/
Audio
https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN4056797871.mp3?updated=1752077099
JSON
/v1/public/podcasts/twiml-ai-podcast/episodes/distilling-transformers-and-diffusion-models-for-robust-edge-use-cases-with-fatih-porikli-738
Markdown
/podcast/twiml-ai-podcast/distilling-transformers-and-diffusion-models-for-robust-edge-use-cases-with-fatih-porikli-738.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/distilling-transformers-and-diffusion-models-for-robust-edge-use-cases-with-fatih-porikli-738/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/twiml-ai-podcast/distilling-transformers-and-diffusion-models-for-robust-edge-use-cases-with-fatih-porikli-738.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Today, we're joined by Fatih Porikli, senior director of technology at Qualcomm AI Research for an in-depth look at several of Qualcomm's accepted papers and demos featured at this year’s CVPR conference. We start with “DiMA: Distilling Multi-modal Large Language Models for Autonomous Driving,” an end-to-end autonomous driving system that incorporates distilling large language models for structured scene understanding and safe planning motion in critical "long-tail" scenarios. We explore how DiMA utilizes LLMs' world knowledge and efficient transformer-based models to significantly reduce collision rates and trajectory errors. We then discuss “SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation,” a diffusion-distilled approach that combines generative models with metric depth estimation to produce sharp, accurate monocular depth maps. Additionally, Fatih also shares a look at Qualcomm’s on-device demos, including text-to-3D mesh generation, real-time image-to-video and video-to-video generation, and a multi-modal visual question-answering assistant. The complete show notes for this episode can be found at https://twimlai.com/go/738.