Gargi Ghosh
17 papers · 2019–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+9 more ↓ Show less ↑
π Renaissance Researcher (5) π Cross-Pollinator (11) π Conference Polyglot (7) π Academic Marathon (6) π Interdisciplinary Bridge
πΊοΈ
Taxonomy Completionist
(33)
π§
Keyword Pioneer
π
Conference Polyglot
(7)
π€
Dynamic Duo
(12)
π§¬
Topic Evolution
β‘
Prolific Year
(5)
π
Century Club
(17)
ποΈ
Keyword Collector
(53)
π₯
Unstoppable
(7)
Conferences
ACL (6)
NIPS (3)
EMNLP (2)
ICLR (2)
IJCNLP (2)
ICCV (1)
ICML (1)
Top co-authors
Keywords
contrastive learning
(3)
few-shot learning
(3)
multimodal learning
(2)
neural retrieval
(2)
large language model
(2)
domain adaptation
(2)
open-domain question answering
(2)
self-supervised learning
(2)
zero-shot learning
(2)
multi-task learning
(2)
image captioning
(1)
information retrieval
(1)
question answering
(1)
efficient training
(1)
synthetic data generation
(1)
attention mechanism
(1)
deep learning
(1)
text-to-image generation
(1)
working memory
(1)
audio-visual learning
(1)
Papers
Memory Layers at Scale
ICML 2025
Byte Latent Transformer: Patches Scale Better Than Tokens
ACL 2025
Improving Factuality with Explicit Working Memory
ACL 2025
Altogether: Image Captioning via Re-aligning Alt-text
EMNLP 2024
Demystifying CLIP Data
ICLR 2024
LIMA: Less Is More for Alignment
NIPS 2023
ALERT: Adapt Language Models to Reasoning Tasks
ACL 2023
MAViL: Masked Audio-Video Learners
NIPS 2023
CiT: Curation in Training for Effective Vision-Language Data
ICCV 2023
HTLM: Hyper-Text Pre-Training and Prompting of Language Models
ICLR 2022
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
IJCNLP 2021
Multi-Task Retrieval for Knowledge-Intensive Tasks
ACL 2021
VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding
ACL 2021
VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding
EMNLP 2021
Multi-Task Retrieval for Knowledge-Intensive Tasks
IJCNLP 2021
Pre-training via Paraphrasing
NIPS 2020
Exploring Deep Multimodal Fusion of Text and Photo for Hate Speech Classification
ACL 2019