Mostafa Dehghani
33 papers · 2018–2024 · 10 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (63) π Academic Marathon Β· Sprint π Conference Polyglot Β· Gold π Interdisciplinary Bridge Β· Silver π£ Hot Topic Early Bird
π±
Topic Pioneer
π
Triple Crown
π€
Dynamic Duo
(16)
π₯
Mega-Team Β· Squad
π¬
Deep Specialist
(18)
π
Conference Pioneer
β
The Questioner
(2)
β‘
Prolific Year Β· Productive
π
Century Club Β· Bronze
π
Trend Setter
ποΈ
Keyword Collector
(132)
Venues
Top co-authors
Research topics
Deep Learning
(26)
Machine Learning
(22)
Architectures
(19)
Artificial Intelligence
(13)
Core AI
(11)
Application Areas
(9)
Learning Types Β· Machine Learning
(9)
Techniques
(9)
Computer Vision
(7)
Optimization & Theory Β· Machine Learning
(6)
Optimization & Theory Β· Deep Learning
(6)
Natural Language Processing
(5)
Analysis
(5)
Learning Types Β· Deep Learning
(4)
Models
(4)
Keywords
vision transformer
(5)
transformer architecture
(5)
few-shot learning
(5)
model scaling
(4)
transfer learning
(4)
representation learning
(3)
model architecture
(3)
large language model
(3)
scaling law
(3)
image recognition
(2)
video understanding
(2)
adaptive computation
(2)
action recognition
(2)
video transformer
(2)
image classification
(2)
language modeling
(2)
object detection
(2)
in-context learning
(2)
computer vision
(2)
machine translation
(2)
Papers
End-to-End Spatio-Temporal Action Localisation with Video Transformers
CVPR 2024
Fractal Patterns May Illuminate the Success of Next-Token Prediction
NeurIPS 2024
Frozen Feature Augmentation for Few-Shot Image Classification
CVPR 2024
Low-Rank Adaptation for Multilingual Summarization: An Empirical Study
NAACL 2024
On Scaling Up a Multilingual Vision and Language Model
CVPR 2024
Scaling Instruction-Finetuned Language Models
JMLR 2024
Ξ-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
ICLR 2023
Adaptive Computation with Elastic Input Sequence
ICML 2023
DSI++: Updating Transformer Memory with New Documents
EMNLP 2023
Patch nβ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution
NeurIPS 2023
Scaling Laws vs Model Architectures: How does Inductive Bias Influence Scaling?
EMNLP 2023
Scaling Vision Transformers to 22 Billion Parameters
ICML 2023
Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints
ICLR 2023
Transcending Scaling Laws with 0.1% Extra Compute
EMNLP 2023
UL2: Unifying Language Learning Paradigms
ICLR 2023
Confident Adaptive Language Modeling
NeurIPS 2022
Discrete Representations Strengthen Vision Transformer Robustness
ICLR 2022
Exploring the Limits of Large Scale Pre-training
ICLR 2022
Scale Efficiently: Insights from Pretraining and Finetuning Transformers
ICLR 2022
Scenic: A JAX Library for Computer Vision Research and Beyond
CVPR 2022
Simple Open-Vocabulary Object Detection with Vision Transformers
ECCV 2022
The Efficiency Misnomer
ICLR 2022
Transformer Memory as a Differentiable Search Index
NeurIPS 2022
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
ICLR 2021
Are Pretrained Convolutions Better than Pretrained Transformers?
ACL 2021
IDF++: Analyzing and Improving Integer Discrete Flows for Lossless Compression
ICLR 2021
Long Range Arena : A Benchmark for Efficient Transformers
ICLR 2021
OmniNet: Omnidirectional Representations from Transformers
ICML 2021
Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks
ACL 2021
TokenLearner: Adaptive Space-Time Tokenization for Videos
NeurIPS 2021
ViViT: A Video Vision Transformer
ICCV 2021
Universal Transformers
ICLR 2019
Fidelity-Weighted Learning
ICLR 2018