papers

Publications (11)

cs.LG2024

G-RepsNet: A Fast and General Construction of Equivariant Networks for Arbitrary Matrix Groups

Sourya Basu, Suhas Lohit, Matthew Brand

Group equivariance is a strong inductive bias useful in a wide range of deep learning tasks. However, constructing efficient equivariant networks for general groups and domains is…

cs.LG2025

TuneComp: Joint Fine-tuning and Compression for Large Foundation Models

Xiangyu Chen, Jing Liu, Ye Wang +4

To reduce model size during post-training, compression methods, including knowledge distillation, low-rank approximation, and pruning, are often applied after fine-tuning the model…

cs.RO2026

Embedding Morphology into Transformers for Cross-Robot Policy Learning

Kei Suzuki, Jing Liu, Ye Wang +4

Cross-robot policy learning -- training a single policy to perform well across multiple embodiments -- remains a central challenge in robot learning. Transformer-based policies, su…

cs.CV2024

SuperLoRA: Parameter-Efficient Unified Adaptation of Multi-Layer Attention Modules

Xiangyu Chen, Jing Liu, Ye Wang +4

Low-rank adaptation (LoRA) and its variants are widely employed in fine-tuning large models, including large language models for natural language processing and diffusion models fo…

cs.AI2012

Marginalizing Out Future Passengers in Group Elevator Control

Daniel N. Nikovski, Matthew Brand

Group elevator scheduling is an NP-hard sequential decision-making problem with unbounded state spaces and substantial uncertainty. Decision-theoretic reasoning plays a surprisingl…

math.NT2018

Choosing 1 of N with and without lucky numbers

Matthew Brand

How many fair coin tosses to choose 1 of options with uniform probability? Although a probability problem, the solution is essentially number-theoretic, with special roles for…