Yash Sharma
20 papers · 2018–2024 · 11 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+11 more ↓ Show less ↑
π Academic Marathon (6) π Conference Polyglot (11) π§ Keyword Pioneer π Interdisciplinary Bridge π Cross-Pollinator (11)
π
Cross-Pollinator
(11)
π
Renaissance Researcher
(6)
πΊοΈ
Taxonomy Completionist
(41)
π
Triple Crown
β‘
Prolific Year
(7)
π
Conference Pioneer
π₯
Unstoppable
(7)
β
The Questioner
π
Century Club
(20)
π
Trend Setter
ποΈ
Keyword Collector
(84)
Conferences
NIPS (5)
ICLR (3)
ICML (3)
EMNLP (2)
CLEAR (1)
CORL (1)
IJCAI (1)
INTERSPEECH (1)
JMLR (1)
MIDL (1)
MLHC (1)
Top co-authors
Keywords
unsupervised learning
(3)
representation learning
(3)
generative model
(3)
independent component analysis
(2)
image generation
(2)
self-supervised learning
(2)
adversarial example
(2)
data augmentation
(2)
object-centric representation
(2)
multi-instance learning
(1)
scene understanding
(1)
text classification
(1)
transfer learning
(1)
human perception
(1)
natural language processing
(1)
feature extraction
(1)
adversarial robustness
(1)
model robustness
(1)
attention mechanism
(1)
visual question answering
(1)
Papers
Attribute Diversity Determines the Systematicity Gap in VQA
EMNLP 2024
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
NIPS 2024
MOSAIC: Modular Foundation Models for Assistive and Interactive Cooking
CORL 2024
On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks
NIPS 2023
Provably Learning Object-Centric Representations
ICML 2023
Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought
NIPS 2023
Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA
CLEAR 2022
Weakly Supervised Deep Instance Nuclei Detection using Points Annotation in 3D Cardiovascular Immunofluorescent Images
MLHC 2022
Spatially Structured Recurrent Modules
ICLR 2021
Self-Supervised Learning with Data Augmentations Provably Isolates Content from Style
NIPS 2021
Unsupervised Learning of Compositional Energy Concepts
NIPS 2021
Towards Nonlinear Disentanglement in Natural Data with Temporal Sparse Coding
ICLR 2021
Contrastive Learning Inverts the Data Generating Process
ICML 2021
Benchmarking Unsupervised Object Representations for Video Sequences
JMLR 2021
Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification
MIDL 2021
Improving Low Resource Code-Switched ASR Using Augmented Code-Switched TTS
INTERSPEECH 2020
MMA Training: Direct Input Space Margin Maximization through Adversarial Training
ICLR 2020
On the Effectiveness of Low Frequency Perturbations
IJCAI 2019
Are Generative Classifiers More Robust to Adversarial Attacks?
ICML 2019
Generating Natural Language Adversarial Examples
EMNLP 2018