activity
20242026
collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

How Data Shapes RoPE Frequency Usage: From Positional Scale Matching to Length Generalization

Xinyi Wu, Siyuan Liu, Ali Jadbabaie

Rotary Position Embeddings (RoPE) provide transformers with a fixed grid of positional frequencies, yet trained models use these frequencies highly non-uniformly. We study what det…

cs.LG2025

Is Your Conditional Diffusion Model Actually Denoising?

Daniel Pfrommer, Zehao Dou, Christopher Scarvelis +2

We study the inductive biases of diffusion models with a conditioning-variable, which have seen widespread application as both text-conditioned generative image models and observat…

cs.LG2025

A Test-Function Approach to Incremental Stability

Daniel Pfrommer, Max Simchowitz, Ali Jadbabaie

This paper presents a novel framework for analyzing Incremental-Input-to-State Stability (ISS) based on the idea of using rewards as "test functions." Whereas control theory tra…

cs.LG2025

The Pitfalls of Imitation Learning when Actions are Continuous

Max Simchowitz, Daniel Pfrommer, Ali Jadbabaie

We study the problem of imitating an expert demonstrator in a discrete-time, continuous state-and-action control system. We show that, even if the dynamics satisfy a control-theore…

cs.LG2025

On the Emergence of Position Bias in Transformers

Xinyi Wu, Yifei Wang, Stefanie Jegelka +1

Recent studies have revealed various manifestations of position bias in transformer architectures, from the "lost-in-the-middle" phenomenon to attention sinks, yet a comprehensive…