Gabriel Ilharco
25 papers · 2019–2025 · 10 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+10 more ↓ Show less ↑
π Renaissance Researcher (7) π Interdisciplinary Bridge π Conference Polyglot (10) π Academic Marathon (6) πΊοΈ Taxonomy Completionist (64)
πΊοΈ
Taxonomy Completionist
(64)
π§
Keyword Pioneer
π£
Hot Topic Early Bird
π€
Dynamic Duo
(14)
π₯
Mega-Team
(60)
π
Keyword Champion
(4)
π₯
Unstoppable
(7)
ποΈ
Keyword Collector
(113)
π
Century Club
(25)
β‘
Prolific Year
(6)
Conferences
EMNLP (6)
NIPS (5)
CVPR (3)
ICLR (3)
ICCV (2)
ICML (2)
ACL (1)
CONLL (1)
IJCNLP (1)
NAACL (1)
Top co-authors
Keywords
contrastive learning
(5)
zero-shot learning
(5)
data filtering
(4)
multimodal learning
(4)
vision-language model
(3)
distribution shift
(3)
zero-shot performance
(2)
transfer learning
(2)
multimodal entailment
(2)
image-text pair
(2)
model ensemble
(2)
knowledge distillation
(2)
model merging
(2)
out-of-distribution performance
(2)
semantic alignment
(2)
distributional robustness
(2)
inference efficiency
(2)
efficient computing
(2)
representation learning
(2)
text classification
(1)
Papers
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
DataComp-LM: In search of the next generation of training sets for language models
NIPS 2024
Improving multimodal datasets with image captioning
NIPS 2023
DataComp: In search of the next generation of multimodal datasets
NIPS 2023
TaskWeb: Selecting Better Source Tasks for Multi-task NLP
EMNLP 2023
Adaptive Testing of Computer Vision Models
ICCV 2023
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
CVPR 2023
Reproducible Scaling Laws for Contrastive Language-Image Learning
CVPR 2023
Editing models with task arithmetic
ICLR 2023
Exploring The Landscape of Distributional Robustness for Question Answering Models
EMNLP 2022
Patching open-vocabulary models by interpolating weights
NIPS 2022
Quality Not Quantity: On the Interaction between Dataset Design and Robustness of CLIP
NIPS 2022
Robust Fine-Tuning of Zero-Shot Models
CVPR 2022
Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time
ICML 2022
Data Determines Distributional Robustness in Contrastive Language Image Pre-training (CLIP)
ICML 2022
Probing Contextual Language Models for Common Ground with Visual Representations
NAACL 2021
Recognizing Multimodal Entailment
ACL 2021
Documenting Large Webtext Corpora: A Case Study on the Colossal Clean Crawled Corpus
EMNLP 2021
Finetuning Pretrained Transformers into RNNs
EMNLP 2021
Contrasting Contrastive Self-Supervised Representation Learning Pipelines
ICCV 2021
MultiModalQA: complex question answering over text, tables and images
ICLR 2021
Recognizing Multimodal Entailment
IJCNLP 2021
High Performance Natural Language Processing
EMNLP 2020
Evaluating Modelsβ Local Decision Boundaries via Contrast Sets
EMNLP 2020
Large-Scale Representation Learning from Visually Grounded Untranscribed Speech
CONLL 2019