collaborators

6 papers

cs.LG2025

An Equivariance Toolbox for Learning Dynamics

Yongyi Yang, Liu Ziyin

Many theoretical results in deep learning can be traced to symmetry or equivariance of neural networks under parameter transformations. However, existing analyses are typically pro…

cs.AI2025

When Reasoning Meets Its Laws

Junyu Zhang, Yifan Sun, Tianang Leng +4

Despite the superior performance of Large Reasoning Models (LRMs), their reasoning behaviors are often counterintuitive, leading to suboptimal reasoning capabilities. To theoretica…

cs.LG2025

Does Feedback Alignment Work at Biological Timescales?

Marc Gong Bacvanski, Liu Ziyin, Tomaso Poggio

Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in d…

stat.ML2025

A universal compression theory for lottery ticket hypothesis and neural scaling laws

Hong-Yi Wang, Di Luo, Tomaso Poggio +2

When training large-scale models, the performance typically scales with the number of parameters and the dataset size according to a slow power law. A fundamental theoretical and p…

q-bio.NC2025

Heterosynaptic Circuits Are Universal Gradient Machines

Liu Ziyin, Isaac Chuang, Tomaso Poggio

We propose a design principle for the learning circuits of the biological brain. The principle states that almost any dendritic weights updated via heterosynaptic plasticity can im…

cs.LG2025

Compositional Generalization via Forced Rendering of Disentangled Latents

Qiyao Liang, Daoyuan Qian, Liu Ziyin +1

Composition-the ability to generate myriad variations from finite means-is believed to underlie powerful generalization. However, compositional generalization remains a key challen…