Author name cluster

John Cooper

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

ICML Conference 2025 Conference Paper

Everything Everywhere All at Once: LLMs can In-Context Learn Multiple Tasks in Superposition

Zheyang Xiong
Ziyang Cai
John Cooper
Albert Ge
Vasilis Papageorgiou
Zack Sifakis
Angeliki Giannou
Ziqian Lin

Large Language Models (LLMs) have demonstrated remarkable in-context learning (ICL) capabilities. In this study, we explore a surprising phenomenon related to ICL: LLMs can perform multiple, computationally distinct ICL tasks simultaneously, during a single inference call, a capability we term task superposition". We provide empirical evidence of this phenomenon across various LLM families and scales and show that this phenomenon emerges even if we train the model to in-context learn one task at a time. We offer theoretical explanations that this capability is well within the expressive power of transformers. We also explore how LLMs internally compose task vectors during superposition. Furthermore, we show that larger models can solve more ICL tasks in parallel, and better calibrate their output distribution. Our findings offer insights into the latent capabilities of LLMs, further substantiate the perspective of "LLMs as superposition of simulators", and raise questions about the mechanisms enabling simultaneous task execution.

Details

ICLR Conference 2025 Conference Paper

Weak-to-Strong Generalization Through the Data-Centric Lens

Changho Shin
John Cooper
Frederic Sala

The weak-to-strong generalization phenomenon is the driver for important machine learning applications including highly data-efficient learning and, most recently, performing superalignment. While decades of research have resulted in numerous algorithms that produce strong empirical performance, understanding what aspects of data enable weak-to-strong generalization has been understudied. We propose a simple data-centric mechanism that characterizes weak-to-strong generalization: the overlap density. Intuitively, generalization tracks the number of points that contain overlaps, i.e., both easy patterns (learnable by a weak model) and challenging patterns (only learnable by a stronger model), as with such points, weak predictions can be used to learn challenging patterns by stronger models. And, we provide a practical overlap detection algorithm to find overlap density from data. Finally, we provide an algorithm to learn, among multiple sources of data, which to query when seeking to maximize overlap density and thereby enhance weak-to-strong generalization. We provide a theoretical result showing that the generalization benefit is a function of the overlap density and a regret bound of our data selection algorithm. Empirically, we validate the mechanism and the overlap detection algorithm on a wide array of settings.

Details

AAMAS Conference 2019 Conference Paper

Inverse Kinematics and Sensitivity Minimization of an n-Stack Stewart Platform

David Balaban
John Cooper
Erik Komendera

An autonomous system is presented to solve the problem of in space assembly, which can be used to further the NASA goal of deep space exploration. A prototype of an autonomous manipulator called "Assemblers" was fabricated from an aggregation of Stewart Platform robots for the purpose of researching autonomous in space assembly capabilities. Selecting inverse kinematic poses, deined by a set of translations and rotations, for the Assembler requires coordination between each Stewart Platform and is an underconstrained non-linear optimization problem. For assembly tasks, it is ideal that the pose selected has the least sensitivity to disturbances possible. A method of sensitivity reduction is proposed by minimizing the Frobenius Norm (FN) of the Jacobian of the forward kinematics. The efectiveness of the FN method will be demonstrated through a Monte Carlo simulation to model random motion internal to the structure.

PDF

IROS Conference 2019 Conference Paper

Inverse Kinematics and Sensitivity Minimization of an n-Stack Stewart Platform

David Balaban
John Cooper
Erik Komendera

The method of Frobenius Norm (FN) minimization of forward kinematic Jacobians is presented to minimize the sensitivity of a robotic manipulator. We demonstrate the effectiveness of this approach with a Monte Carlo simulation of an Assembler robot. The Assembler is described as a stack of Stewart Platforms designed for in-space assembly to aide NASA in deep space exploration. The translations and rotations between each Stewart Platform define the forward kinematics of the Assember, which analytically determine the end effector position and orientation. However, selecting the poses of each Stewart Platform which yield a desired end effector state, defined as the inverse kinematics, is an underconstrained nonlinear optimization problem for large Assembler stacks.

Details