activity
20242026
collaborators

11 papers

cs.LG2026

On the Invariance and Generality of Neural Scaling Laws

Xing Han, Ziyin Liu, Suchi Saria +1

Neural scaling laws establish a predictable relationship between model performance and data or compute, offering crucial guidance for resource allocation in new domains and tasks.…

cs.LG2026

Neural Thermodynamics: Entropic Forces in Deep and Universal Representation Learning

Liu Ziyin, Yizhou Xu, Isaac Chuang

With the rapid discovery of emergent phenomena in deep learning and large language models, understanding their cause has become an urgent need. Here, we propose a rigorous entropic…

cs.LG2025

Proof of a perfect platonic representation hypothesis

Liu Ziyin, Isaac Chuang

In this note, we elaborate on and explain in detail the proof given by Ziyin et al. (2025) of the ``perfect" Platonic Representation Hypothesis (PRH) for the embedded deep linear n…

cs.LG2025

Topological Invariance and Breakdown in Learning

Yongyi Yang, Tomaso Poggio, Isaac Chuang +1

We prove that for a broad class of permutation-equivariant learning rules (including SGD, Adam, and others), the training process induces a bi-Lipschitz mapping between neurons and…

cs.LG2025

Remove Symmetries to Control Model Expressivity and Improve Optimization

Liu Ziyin, Yizhou Xu, Isaac Chuang

When symmetry is present in the loss function, the model is likely to be trapped in a low-capacity state that is sometimes known as a "collapse". Being trapped in these low-capacit…

cs.LG2025

Understanding the Emergence of Multimodal Representation Alignment

Megan Tjandrasuwita, Chanakya Ekbote, Liu Ziyin +1

Multimodal representation learning is fundamentally about transforming incomparable modalities into comparable representations. While prior research primarily focused on explicitly…