# Scaling Up Test-Time Compute with Latent Reasoning with Jonas Geiping - #723

Page: https://stenobird.com/podcast/twiml-ai-podcast/scaling-up-test-time-compute-with-latent-reasoning-with-jonas-geiping-723
Text version: https://stenobird.com/podcast/twiml-ai-podcast/scaling-up-test-time-compute-with-latent-reasoning-with-jonas-geiping-723.md
Podcast: [The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)](https://stenobird.com/podcast/twiml-ai-podcast)
Published: 2025-03-17T15:37:00+00:00
Episode link: https://twimlai.com/podcast/twimlai/scaling-up-test-time-compute-with-latent-reasoning/
Audio file: https://pscrb.fm/rss/p/traffic.megaphone.fm/MLN5952508288.mp3?updated=1742226663
Processing state: failed
JSON: https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/scaling-up-test-time-compute-with-latent-reasoning-with-jonas-geiping-723
Duration seconds: 3518

## Resource

Today, we're joined by Jonas Geiping, research group leader at Ellis Institute and the Max Planck Institute for Intelligent Systems to discuss his recent paper, “Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach.” This paper proposes a novel language model architecture which uses recurrent depth to enable “thinking in latent space.” We dig into “internal reasoning” versus “verbalized reasoning”—analogous to non-verbalized and verbalized thinking in humans, and discuss how the model searches in latent space to predict the next token and dynamically allocates more compute based on token difficulty. We also explore how the recurrent depth architecture simplifies LLMs, the parallels to diffusion models, the model's performance on reasoning tasks, the challenges of comparing models with varying compute budgets, and architectural advantages such as zero-shot adaptive exits and natural speculative decoding. The complete show notes for this episode can be found at https://twimlai.com/go/723.

## Actions

- request_transcript: `POST https://stenobird.com/v1/public/podcasts/twiml-ai-podcast/episodes/scaling-up-test-time-compute-with-latent-reasoning-with-jonas-geiping-723/transcription-requests` — Idempotently request low-priority transcript generation for this episode.
- read_markdown: `GET https://stenobird.com/podcast/twiml-ai-podcast/scaling-up-test-time-compute-with-latent-reasoning-with-jonas-geiping-723.md` — Read the agent-friendly Markdown representation of this episode resource.

A page view does not enqueue transcription. Agents should invoke `request_transcript` explicitly when they need this episode processed.

## Transcript

Full transcripts are not published on public pages unless there is a clear rights basis.