Desmond Elliott
- Papers
- 14
Cite
Notes
Only stored in your browser.
Authored papers
14LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs
arXiv 2026
CroCo: Cross-Lingual Contrastive Preference Tuning on Self-Generations
arXiv 2026
Efficient Test-Time Scaling for Small Vision-Language Models
arXiv 2025
Kaleidoscope: In-language Exams for Massively Multilingual Vision Evaluation
arXiv 2025
MuSeD: A Multimodal Spanish Dataset for Sexism Detection in Social Media Videos
arXiv 2025
AweDist: Attention-aware Embedding Distillation for New Input Token Embeddings
arXiv 2025
FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culture
arXiv 2024
CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation
arXiv 2024
LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks
arXiv 2024
Understanding Retrieval Robustness for Retrieval-Augmented Image Captioning
arXiv 2024
The Role of Data Curation in Image Captioning
arXiv 2023
PHD: Pixel-Based Language Modeling of Historical Documents
arXiv 2023
Revisiting Transformer-based Models for Long Document Classification
arXiv 2022
How2: A Large-scale Dataset for Multimodal Language Understanding
arXiv 2018
Affiliations
Frequent co-authors
10from 14 papers