Why Image Generation Needs More Than Bigger Models with Fatih Porikli
Machine Learning, Computer Vision and Deep Learning podcast with Fatih Porikli
The TWIML AI Podcast, Hosted by Sam Charrington
Wednesday 57 min
About
Fatih Porikli examines why scaling image models alone does not guarantee visually correct results. He discusses separating scene planning from rendering, improving controllability and editing, and bringing high-resolution generation to edge devices, including the role of training objectives and reinforcement learning.
Topics
Related episodes
- Image Generation and Visual Intelligence with Black Forest LabsJul 2, 2026 · 48 min
- World Models and the Future of Spatial AI with Justin JohnsonSep 1, 2026 · 1 h 6 min
- Why AI Agents Break the GenAI Security Model with Devvret RishiJun 16, 2026 · 56 min
- Why Models Are AI’s Next Training Dataset with Damian BorthJul 27, 2026 · 47 min
- From Voice Agents to AI Avatars with Alexander SmolaSep 16, 2026 · 1 h 5 min
More from The TWIML AI Podcast
All episodesFrom Math Olympiads to Navier-Stokes: How Fast Is AI Progressing?
Sep 29, 2026The TWIML AI PodcastDo AI Tokenomics Matter More Than Model Benchmarks? with Christopher Potts
Sep 9, 2026The TWIML AI PodcastWhy the Next AI Breakthrough May Come from Physics with Max Welling
Aug 25, 2026The TWIML AI PodcastHow AI Learns to Smell with Alex Wiltschko
Jul 8, 2026The TWIML AI Podcast
More with Sam Charrington
All their workNew episodes in Machine Learning
All episodesYuandong Tian on Recursive Self-Improvement
Oct 5, 2026The Information BottleneckOpen models and the future of Physical AI with NVIDIA
Oct 1, 2026Practical AIChris Manning: Language Is the Real Unlock for Intelligence
Sep 27, 2026The Information BottleneckFrom AGENTS.md to Enterprise Deployment
Sep 24, 2026Practical AI
Upcoming talks in Machine Learning
All seminarsBig Boxes, Not Black Boxes: What we can compute about LLMs, and what it may say about AGI
Oct 7, 2026Zohar RingelLarge-Scale Multilingual Evaluation of Large Language Models on Real-World Clinical Data
Oct 7, 2026Jie YangNon-Parametric Rehearsal Learning via Conditional Mean Embeddings
Oct 8, 2026Wen-Bo DuSeeing Biology in a New Light: Nanosensors for Real-Time Biosensing
Oct 9, 2026Daniel Roxbury