collaborators

8 papers

cs.LG2026

The Sparsity Whisperer

Linghao Kong, Inimai Subramanian, Micah Adler +3

Pruning reduces the inference cost of large language models, but existing criteria primarily preserve large activations or reconstruct layer outputs. We argue that this overlooks a…

cs.LG2026

Expand Neurons, Not Parameters

Linghao Kong, Inimai Subramanian, Yonadav Shavit +3

This work demonstrates how increasing the number of neurons in a network without increasing its total number of non-zero parameters improves performance. We show that this gain cor…

cs.LG2026

Negative Pre-activations Differentiate Syntax

Linghao Kong, Angelina Ning, Micah Adler +1

Modern large language models increasingly use smooth activation functions such as GELU or SiLU, allowing negative pre-activations to carry both signal and gradient. Nevertheless, m…

cs.CC2026

On the Complexity of Neural Computation in Superposition

Micah Adler, Nir Shavit

Superposition, the ability of neural networks to represent more features than neurons, is increasingly seen as key to the efficiency of large models. This paper investigates the th…

cs.LG2026

Understanding Empirical Unlearning with Combinatorial Interpretability

Shingo Kodama, Niv Cohen, Micah Adler +1

While many recent methods aim to unlearn or remove knowledge from pretrained models, seemingly erased knowledge often persists and can be recovered in various ways. Because large f…

cs.LG2026

A Capacity-Based Rationale for Multi-Head Attention

Micah Adler

We study the capacity of the self-attention key-query channel: for a fixed budget, how many distinct token-token relations can a single layer reliably encode? We introduce Relation…