Where can I listen to this podcast?

This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.

Does this podcast accept guests?

No, this podcast does not typically feature guests.

Latent State

Claim This Podcast

by Shengbin Cui

11 episodes

Updated Daily

Accepts GuestsHas SponsorsLocation 🇯🇵

Podcast Overview

Welcome to Latent State, the podcast that decodes the hidden structure of the mind. We bridge the gap between complex data and clear insight, covering the most exciting research in computational neuroscience, cognitive science, and AI. We focus on the signal, not the noise. Each episode, we unpack a groundbreaking paper, translating advanced methods and models into the stories that matter. Whether you are a researcher, a data scientist, or just obsessed with the code of the human mind, this is your briefing.

Language

🇺🇲

Publishing Since

3/28/2026

Visit Website View on Apple Podcasts RSS Feed

Reach the team behind Latent State

Verified contact details for this show aren't on file yet — sign up to get notified when they land.

Recent Episodes

July 6, 2026

Ep.11. The Planning Machine

Paper discussedTaylor Webb, Shanka Subhra Mondal & Ida Momennejad (2025). A brain-inspired agentic architecture to improve planning with LLMs. Nature Communications.One-sentence summaryThis episode explores how a brain-inspired modular architecture, the Modular Agentic Planner, improves LLM planning by dividing the planning process into specialized components for action proposal, monitoring, prediction, evaluation, task decomposition, and orchestration.Key ideas<ul><li>Large language models can often perform planning-related functions in isolation, while coordination across those functions remains difficult.</li><li>MAP treats planning as an interaction between specialized LLM modules.</li><li>The architecture is inspired by component processes associated with prefrontal cortex, including conflict monitoring, state prediction, state evaluation, task decomposition, and task coordination.</li><li>The Monitor module is especially important because many LLM planning failures involve invalid actions or rule violations.</li><li>MAP improved performance across Tower of Hanoi, graph traversal, PlanBench, and StrategyQA compared with several standard and agentic baselines.</li><li>The paper’s strongest contribution is the demonstration that cognitive neuroscience can inspire useful AI architectures.</li></ul>Important cautionMAP is not a detailed computational model of the prefrontal cortex. It is a high-level, brain-inspired engineering architecture. The tasks are mostly fully observable and deterministic, and the approach still faces challenges involving cost, prompting, generalization, interpretability, and open-ended real-world planning.

June 15, 2026

Ep.10. The Adaptive Machine

Paper discussedMackenzie Mathis. Leveraging insights from neuroscience to build adaptive artificial intelligence. Nature Neuroscience, 2026.One-sentence summaryThis episode explores how neuroscience can inspire more adaptive AI systems by studying how animals learn online, update internal models, use prediction errors, replay memory, and adapt to changing environments.Key ideas<ul><li>Biological intelligence is inherently adaptive.</li></ul><ul><li>Many AI systems still follow a train-test-deploy cycle and are not truly adaptive after deployment.</li><li>Animals continuously update internal models based on feedback.</li><li>Prediction errors act as biological teaching signals across sensory, motor, and reward systems.</li><li>Continual learning in AI faces the stability-plasticity problem and catastrophic forgetting.</li><li>Memory replay connects biological hippocampal replay with machine learning strategies for preserving old knowledge during new learning.</li><li>Spiking neural networks and neuromorphic computing may offer energy-efficient, time-dependent computation.</li><li>Future adaptive AI may require modular agentic systems with specialized encoders, prediction-error monitoring, and selective updating.</li><li>The goal is not to copy the brain literally, but to extract useful design principles.</li></ul>Important cautionThis paper is a Perspective and research agenda, not a single empirical demonstration. It argues that neuroscience can inspire adaptive AI, but it does not prove that any specific brain-inspired architecture will outperform current AI systems.

June 8, 2026

Ep.09. The Sound of Thought

PaperDenk, T. I., Takagi, Y., Matsuyama, T., Agostinelli, A., Nakai, T., Frank, C., & Nishimoto, S. Text-to-music generation models capture musical semantic representations in the human brain. Nature Communications.One-sentence summaryA NeuroAI study shows that music-generation models can help reveal how the human auditory cortex represents musical meaning, linking music, language, and brain activity through shared semantic structure.Key ideas<ul><li>The study used fMRI while participants listened to short music clips.</li><li>The researchers predicted high-level music embeddings from brain activity.</li><li>MusicLM generated new music from those predicted embeddings.</li><li>The reconstructions preserved genre, mood, and instrumentation better than fine timing.</li><li>Human raters matched reconstructed music to original music roughly three out of four times.</li><li>Beats per minute were not recovered well.</li><li>Music-derived and text-derived representations predicted overlapping auditory-cortex regions.</li><li>The results suggest musical semantics are centered on auditory cortices, but not exclusive to them.</li><li>The study shows functional correspondence, not mechanistic equivalence.</li></ul>Important cautionThis is not “AI reads music from the brain” in a literal sense.The method does not reconstruct the exact song or the full musical experience. It reconstructs high-level musical semantics: the kind of music, not the precise temporal unfolding.

11 total episodes available

Deep-dive analytics for Latent State

Frequently asked questions

Have a different question and can't find the answer you're looking for? Reach out to our support team by sending us an email and we'll get back to you as soon as we can.

What is Latent State?: Welcome to Latent State, the podcast that decodes the hidden structure of the mind. We bridge the gap between complex data and clear insight, covering the most exciting research in computational neuroscience, cognitive science, and AI.

We focus on the signal, not the noise. Each episode, we unpack a groundbreaking paper, translating advanced methods and models into the stories that matter.

Whether you are a researcher, a data scientist, or just obsessed with the code of the human mind, this is your briefing.
How often does this podcast release new episodes?: This podcast updates daily.
Where can I listen to this podcast?: This podcast is available on 4 platforms including Apple Podcasts, Spotify, and more. You can also use the RSS feed directly.
Does this podcast accept guests?: No, this podcast does not typically feature guests.

Legal Disclaimer

Pod Engine is not affiliated with, endorsed by, or officially connected with any of the podcasts displayed on this platform. We operate independently as a podcast discovery and analytics service.

All podcast artwork, thumbnails, and content displayed on this page are the property of their respective owners and are protected by applicable copyright laws. This includes, but is not limited to, podcast cover art, episode artwork, show descriptions, episode titles, transcripts, audio snippets, and any other content originating from the podcast creators or their licensors.

We display this content under fair use principles and/or implied license for the purpose of podcast discovery, information, and commentary. We make no claim of ownership over any podcast content, artwork, or related materials shown on this platform. All trademarks, service marks, and trade names are the property of their respective owners.

While we strive to ensure all content usage is properly authorized, if you are a rights holder and believe your content is being used inappropriately or without proper authorization, please contact us immediately at hey@podengine.ai for prompt review and appropriate action, which may include content removal or proper attribution.

By accessing and using this platform, you acknowledge and agree to respect all applicable copyright laws and intellectual property rights of content owners. Any unauthorized reproduction, distribution, or commercial use of the content displayed on this platform is strictly prohibited.