Amita Kamath
7 papers · 2020–2024 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π Cross-Pollinator (15) π Conference Polyglot (5) π§ Keyword Pioneer π£ Hot Topic Early Bird π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(13)
π±
Topic Pioneer
β
The Questioner
Conferences
ECCV (2)
EMNLP (2)
ACL (1)
CVPR (1)
NIPS (1)
Top co-authors
Keywords
vision-language model
(4)
multimodal learning
(2)
transfer learning
(1)
domain adaptation
(1)
visual question answering
(1)
question answering
(1)
confidence calibration
(1)
out-of-domain detection
(1)
efficient inference
(1)
selective prediction
(1)
benchmark dataset
(1)
foundation model
(1)
out-of-distribution detection
(1)
matryoshka representation
(1)
spatial reasoning
(1)
text encoder
(1)
domain shift
(1)
visual token compression
(1)
spatial relation
(1)
image caption
(1)
Papers
The Hard Positive Truth about Vision-Language Compositionality
ECCV 2024
Matryoshka Query Transformer for Large Vision-Language Models
NIPS 2024
Text encoders bottleneck compositionality in contrastive vision-language models
EMNLP 2023
Whatβs βupβ with vision-language models? Investigating their struggle with spatial reasoning
EMNLP 2023
Webly Supervised Concept Expansion for General Purpose Vision Models
ECCV 2022
Towards General Purpose Vision Systems: An End-to-End Task-Agnostic Vision-Language Architecture
CVPR 2022
Selective Question Answering under Domain Shift
ACL 2020