Linyang He

Many thanks to my amazing co-authors:
@tianjunzhong.bsky.social, @rjantonello.bsky.social, Gavin Mischler, Prof. Micah Goldblum and my advisor Prof. Nima Mesgarani!

#NeuroAI #LLM #NeurIPS2025 #NeurIPS

5️⃣ Takeaway:
- Raw LLM embeddings = biased toward shallow linguistic features.
- Residual disentanglement exposes the deeper, reasoning-specific representations shared by brains and models.

4️⃣Spatial pattern: reasoning even recruits visual cortex beyond classical language areas.

3️⃣ Temporal dynamics: reasoning peaks later (~350–400 ms) than shallow features.

2️⃣ We introduce the first "reasoning embedding", a disentangled representation that isolates reasoning from lexicon, syntax, and meaning.
- The disentangled representations are orthogonal to each other.

1️⃣ Why "Far from the Shallow"?
- Traditional LLM embeddings are entangled, they mix shallow linguistic features (lexicon/syntax) with deeper signals.
- This makes brain encoding studies misleading: success often comes from shallow correlations, not true semantics/reasoning alignment.

🧠 New at #NeurIPS2025!
🎵 We're far from the shallow now🎵
TL;DR: We introduce the first "reasoning embedding" and uncover its unique spatio-temporal pattern in the brain.

🔗 arxiv.org/abs/2510.228...

3️⃣ Unique spatial-temporal pattern of reasoning:
- Temporal dynamics: reasoning peaks later (~350–400 ms).
- Spatially: it even recruits visual cortex beyond classical language areas (IFG/STG), suggesting reasoning involves multimodal integration.
(4/6)

2️⃣ Our contribution:
- We introduce the first “reasoning embedding”, a disentangled representation that isolates reasoning from lexicon, syntax, and meaning.
- It captures variance in brain activity that shallow features can't explain, revealing a distinct neural signature for reasoning.
(3/6)

🌍Introducing BabyBabelLM: A Multilingual Benchmark of Developmentally Plausible Training Data!

LLMs learn from vastly more data than humans ever experience. BabyLM challenges this paradigm by focusing on developmentally plausible data

We extend this effort to 45 new languages!

Temporal integration in human auditory cortex is predominantly yoked to absolute time - Nature Neuroscience Temporal integration throughout the human auditory cortex is predominantly locked to absolute time and does not vary with the duration of speech structures such as phonemes or words.

What happens when you listen to speech a different speeds? Does your brain change its processing speed too? It turns out, no
@samnorman-haignere.bsky.social & researchers at
@zuckermanbrain.bsky.social found the auditory part of the brain keeps clocking in at a fixed time
via @natneuro.nature.com

In our new paper, we explore how we can build encoding models that are both powerful and understandable. Our model uses an LLM to answer 35 questions about a sentence's content. The answers linearly contribute to our prediction of how the brain will respond to that sentence. 1/6