Samir Yitzhak Gadre
10 papers · 2021–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+6 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (28) π Interdisciplinary Bridge π Conference Polyglot (4) π Renaissance Researcher (5) π§ Keyword Pioneer
π
Conference Polyglot
(4)
π
Renaissance Researcher
(5)
π₯
Mega-Team
(34)
β‘
Prolific Year
(5)
π
Century Club
(10)
β
The Questioner
Conferences
NIPS (5)
CVPR (2)
ICLR (2)
ICCV (1)
Top co-authors
Keywords
vision-language model
(3)
zero-shot learning
(3)
data filtering
(2)
multimodal learning
(2)
in-context learning
(1)
language grounding
(1)
robot navigation
(1)
visual navigation
(1)
data augmentation
(1)
corpus construction
(1)
embodied ai
(1)
model merging
(1)
3d vision
(1)
motion segmentation
(1)
multimodal dataset
(1)
part discovery
(1)
image-text pair
(1)
image captioning
(1)
zero-shot generalization
(1)
scene understanding
(1)
Papers
Language models scale reliably with over-training and on downstream tasks
ICLR 2025
Should VLMs be Pre-trained with Image Data?
ICLR 2025
Improving multimodal datasets with image captioning
NIPS 2023
DataComp: In search of the next generation of multimodal datasets
NIPS 2023
Objaverse-XL: A Universe of 10M+ 3D Objects
NIPS 2023
Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text
NIPS 2023
CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation
CVPR 2023
Continuous Scene Representations for Embodied AI
CVPR 2022
Patching open-vocabulary models by interpolating weights
NIPS 2022
Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery
ICCV 2021