activity
20192026
most citedGeneration-Distillation for Efficient Natural Language Understanding in Low-Data Settings

7 citations · 7 across the 4 of their papers we have counts for

collaborators

6 papers

cs.SE2026

Composer 2 Technical Report

Cursor Research, :, Aaron Chan +53

Composer 2 is a specialized model designed for agentic software engineering. The model demonstrates strong long-term planning and coding intelligence while maintaining the ability…

eess.IV2025

3D Cardiac Anatomy Generation Using Mesh Latent Diffusion Models

Jolanta Mozyrska, Marcel Beetz, Luke Melas-Kyriazi +3

Diffusion models have recently gained immense interest for their generative capabilities, specifically the high quality and diversity of the synthesized data. However, examples of…

cs.CV2024

DreamBeast: Distilling 3D Fantastical Animals with Part-Aware Knowledge Transfer

Runjia Li, Junlin Han, Luke Melas-Kyriazi +6

We present DreamBeast, a novel method based on score distillation sampling (SDS) for generating fantastical 3D animal assets composed of distinct parts. Existing SDS methods often…

cs.CV2020

Show, Edit and Tell: A Framework for Editing Image Captions

Fawaz Sammani, Luke Melas-Kyriazi

Most image captioning frameworks generate captions directly from images, learning a mapping from visual features to natural language. However, editing existing captions can be easi…

cs.CL2020★ 7 cited

Generation-Distillation for Efficient Natural Language Understanding in Low-Data Settings

Luke Melas-Kyriazi, George Han, Celine Liang

Over the past year, the emergence of transfer learning with large-scale language models (LM) has led to dramatic performance improvements across a broad range of natural language u…

cs.CL2019

Encoder-Agnostic Adaptation for Conditional Language Generation

Zachary M. Ziegler, Luke Melas-Kyriazi, Sebastian Gehrmann +1

Large pretrained language models have changed the way researchers approach discriminative natural language understanding tasks, leading to the dominance of approaches that adapt a…