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

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

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.

Avsnitt(782)

The Biological Path Towards Strong AI - Matthew Taylor - TWiML Talk #71

The Biological Path Towards Strong AI - Matthew Taylor - TWiML Talk #71

This week, we’ll be featuring a series of shows recorded from Strange Loop, a great developer-focused conference that takes place every year right in my backyard! The conference is a multi-disciplinar...

22 Nov 201737min

Pytorch: Fast Differentiable Dynamic Graphs in Python with Soumith Chintala - TWiML Talk #70

Pytorch: Fast Differentiable Dynamic Graphs in Python with Soumith Chintala - TWiML Talk #70

This week, we’ll be featuring a series of shows recorded from Strange Loop, a great developer-focused conference that takes place every year right in my backyard! The conference is a multi-disciplinar...

21 Nov 201742min

Accessible Machine Learning for the Enterprise Developer with Ryan Sevey & Jason Montgomery

Accessible Machine Learning for the Enterprise Developer with Ryan Sevey & Jason Montgomery

This week, we’ll be featuring a series of shows recorded from Strange Loop, a great developer-focused conference that takes place every year right in my backyard! The conference is a multi-disciplinar...

20 Nov 201745min

Bridging the Gap Between Academic and Industry Careers with Ross Fadely - TWiML Talk #68

Bridging the Gap Between Academic and Industry Careers with Ross Fadely - TWiML Talk #68

We close out our NYU Future Labs AI Summit interview series with Ross Fadely, a New York based AI lead with Insight Data Science. Insight is an interesting company offering a free seven week post-doct...

16 Nov 201719min

The Limitations of Human-in-the-Loop AI with Dennis Mortensen - TWiML Talk #67

The Limitations of Human-in-the-Loop AI with Dennis Mortensen - TWiML Talk #67

We continue our NYU Future Labs AI Summit interview series with Dennis Mortensen, founder and CEO of X.ai, a company whose AI-based personal assistant Amy helps users with scheduling meetings. I caugh...

13 Nov 201735min

Nexus Lab Cohort 2 - Second Mind - TWiML Talk #66

Nexus Lab Cohort 2 - Second Mind - TWiML Talk #66

The podcast you’re about to hear is the fourth of a series of shows recorded at the NYU Future Labs AI Summit last week in New York City. In this show, I speak with Kul Singh, CEO and Founder of Secon...

9 Nov 201721min

Nexus Lab Cohort 2 - Bite.ai - TWiML Talk #65

Nexus Lab Cohort 2 - Bite.ai - TWiML Talk #65

The podcast you’re about to hear is the second of a series of shows recorded at the NYU Future Labs AI Summit last week in New York City.In this episode, you’ll hear from Bite.ai, a startup founded by...

8 Nov 201726min

Nexus Lab Cohort 2 - Bowtie - TWiML Talk #64

Nexus Lab Cohort 2 - Bowtie - TWiML Talk #64

The podcast you’re about to hear is the second of a series of shows recorded at the NYU Future Labs AI Summit last week in New York City. In this episode, I speak with Ron Fisher and Mike Wang, who, a...

7 Nov 201725min

Populärt inom Politik & nyheter

svenska-fall
p3-krim
rss-krimstad
fordomspodden
aftonbladet-krim
spar
flashback-forever
rss-sanning-konsekvens
aftonbladet-daily
motiv
rss-vad-fan-hande
rss-krimreportrarna
rss-klubbland-en-podd-mest-om-frolunda
krimmagasinet
politiken
rss-frandfors-horna
dagens-eko
rss-aftonbladet-krim
blenda-2
rss-flodet