iiinova — where your digital self keeps evolving

Declan Campbell @thisisadax.bsky.social · 05/02/2026

The visual world is composed of objects, and those objects are composed of features. But do VLMs exploit this compositional structure when processing multi-object scenes? In our 🆒🆕 #ICLR2026 paper, we find they do – via emergent symbolic mechanisms for visual binding. 🧵👇

18326

Reposted by Declan Campbell

Eghbal Hosseini @eghbal-hosseini.bsky.social · 04/02/2026

How do diverse context structures reshape representations in LLMs? In our new work, we explore this via representational straightening. We found LLMs are like a Swiss Army knife: they select different computational mechanisms reflected in different representational structures. 1/

13911

Reposted by Declan Campbell

Zhenglong Zhou @neurozz.bsky.social · 16/07/2025

Excited to share a new preprint w/ @annaschapiro.bsky.social! Why are there gradients of plasticity and sparsity along the neocortex–hippocampus hierarchy? We show that brain-like organization of these properties emerges in ANNs that meta-learn layer-wise plasticity and sparsity. bit.ly/4kB1yg5

bit.ly

A gradient of complementary learning systems emerges through meta-learning

Long-term learning and memory in the primate brain rely on a series of hierarchically organized subsystems extending from early sensory neocortical areas to the hippocampus. The components differ in t...

06425

Reposted by Declan Campbell

Taylor Webb @taylorwwebb.bsky.social · 10/03/2025

LLMs have shown impressive performance in some reasoning tasks, but what internal mechanisms do they use to solve these tasks? In a new preprint, we find evidence that abstract reasoning in LLMs depends on an emergent form of symbol processing arxiv.org/abs/2502.20332 (1/N)

arxiv.org

Emergent Symbolic Mechanisms Support Abstract Reasoning in Large Language Models

Many recent studies have found evidence for emergent reasoning capabilities in large language models, but debate persists concerning the robustness of these capabilities, and the extent to which they ...

511835

Reposted by Declan Campbell

Andrew Lampinen @lampinen.bsky.social · 10/12/2024

What counts as in-context learning (ICL)? Typically, you might think of it as learning a task from a few examples. However, we’ve just written a perspective (arxiv.org/abs/2412.03782) suggesting interpreting a much broader spectrum of behaviors as ICL! Quick summary thread: 1/7

arxiv.org

The broader spectrum of in-context learning

The ability of language models to learn a task from a few examples in context has generated substantial interest. Here, we provide a perspective that situates this type of supervised few-shot learning...

212232

Declan Campbell @thisisadax.bsky.social · 15/11/2024

(1) Vision language models can explain complex charts & decode memes, but struggle with simple tasks young kids find easy - like counting objects or finding items in cluttered scenes! Our 🆒🆕 #NeurIPS2024 paper shows why: they face the same 'binding problem' that constrains human vision! 🧵👇

58626