iiinova — where your digital self keeps evolving

Reposted by Linyang He

Pinyuan Feng (Tony) @tonyfeng.bsky.social · 15/06/2026

Excited to announce #CCN2026 satellite event: Modeling and Understanding Human Brain Computation at Scale Organized with Hossein Adeli, Fan Cheng, Andrew Luo, Nikolaus Kriegeskorte Link for details and registration: tinyurl.com/3jf2urze @cogcompneuro.bsky.social

052

Reposted by Linyang He

Columbia University's Zuckerman Institute @zuckermanbrain.bsky.social · 11/05/2026

Hearing aids amplify all incoming sound, and so struggle with noisy surroundings. Brain-controlled hearing tech from Nima Mesgarani, Vishal Choudhari & team could lead to a new generation of hearing systems that help people single out a voice in a crowd. youtube.com/shorts/TONWQ...

youtube.com

Can Mind-Reading Tech Help People Hear Better?

YouTube video by Columbia University's Zuckerman Institute

156

Reposted by Linyang He

Siyuan Song @siyuansong.bsky.social · 24/04/2026

🚀 Announcing the Chinese BabyLM Challenge: the first shared task on data-efficient pretraining for Chinese. 📍 Co-located with NLPCC 2026 (Nov 3–5, Macau🇨🇳🇲🇴) Can you train a strong Chinese LM on just ~100M words? chinese-babylm.github.io 🧵 👇(1/6)

chinese-babylm.github.io

Chinese BabyLM Challenge

1114

Linyang He @linyanghe.bsky.social · 30/10/2025

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

000

Linyang He @linyanghe.bsky.social · 30/10/2025

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

100

Linyang He @linyanghe.bsky.social · 30/10/2025

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

100

Linyang He @linyanghe.bsky.social · 30/10/2025

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

100

Linyang He @linyanghe.bsky.social · 30/10/2025

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.

100

Linyang He @linyanghe.bsky.social · 30/10/2025

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.

110

Linyang He @linyanghe.bsky.social · 30/10/2025

🧠 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...

184

Linyang He @linyanghe.bsky.social · 30/10/2025

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)

000

Linyang He @linyanghe.bsky.social · 30/10/2025

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)

100

Reposted by Linyang He

Jaap Jumelet @jumelet.bsky.social · 15/10/2025

🌍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!

14416

Reposted by Linyang He

RJ Antonello @rjantonello.bsky.social · 18/08/2025

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

1259