activity
20132026
most citedMultimodal Foundation Models for Material Property Prediction and Discovery

37 citations · 91 across the 22 of their papers we have counts for

collaborators
Showing cs.LGShow all

12 papers · 1 filter

cs.LG2025

A Comparative Analysis of LLM Adaptation: SFT, LoRA, and ICL in Data-Scarce Scenarios

Bernd Bohnet, Rumen Dangovski, Kevin Swersky +4

The remarkable capabilities of Large Language Models (LLMs) often need to be tailored for specific applications, requiring the integration of new knowledge or the acquisition of ne…

cs.LG2024★ 6 cited

QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation

Zhuo Chen, Rumen Dangovski, Charlotte Loh +3

We propose Quantum-informed Tensor Adaptation (QuanTA), a novel, easy-to-implement, fine-tuning method with no inference overhead for large-scale pre-trained language models. By le…

cs.LG2023★ 37 cited

Multimodal Foundation Models for Material Property Prediction and Discovery

Viggo Moro, Charlotte Loh, Rumen Dangovski +7

Artificial intelligence is transforming computational materials science, improving the prediction of material properties, and accelerating the discovery of novel materials. Recentl…

cs.LG2023

Model Stitching: Looking For Functional Similarity Between Representations

Adriano Hernandez, Rumen Dangovski, Peter Y. Lu +1

Model stitching (Lenc & Vedaldi 2015) is a compelling methodology to compare different neural network representations, because it allows us to measure to what degree they may be in…

cs.LG2023★ 1 cited

Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries

Charlotte Loh, Seungwook Han, Shivchander Sudalairaj +5

Deep ensembles (DE) have been successful in improving model performance by learning diverse members via the stochasticity of random initialization. While recent works have attempte…

cs.LG2022

On the Importance of Calibration in Semi-supervised Learning

Charlotte Loh, Rumen Dangovski, Shivchander Sudalairaj +5

State-of-the-art (SOTA) semi-supervised learning (SSL) methods have been highly successful in leveraging a mix of labeled and unlabeled data by combining techniques of consistency…