Nikunj Saunshi
19 papers · 2018–2025 · 4 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 ↓+7 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (38) π Academic Marathon Β· Sprint π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze π£ Hot Topic Early Bird
π
Triple Crown
π€
Dynamic Duo
(11)
π
Conference Pioneer
π
Century Club Β· Bronze
β
The Questioner
ποΈ
Keyword Collector
(89)
π₯
Unstoppable Β· Bronze
Venues
Top co-authors
Research topics
Machine Learning
(18)
Artificial Intelligence
(10)
Core Methods
(9)
Optimization & Theory
(9)
Learning Types Β· Machine Learning
(7)
Deep Learning
(6)
Natural Language Processing
(6)
Core AI
(6)
Learning Paradigms Β· Artificial Intelligence
(5)
Application Areas
(3)
Learning Paradigms Β· Machine Learning
(3)
Learning Types Β· Deep Learning
(3)
Applications
(2)
Generation
(2)
Models
(2)
Keywords
representation learning
(6)
neural network optimization
(4)
sample complexity
(4)
gradient descent
(2)
reasoning ability
(2)
few-shot learning
(2)
inductive bia
(2)
self-supervised learning
(2)
downstream task
(2)
transfer learning
(2)
language model
(2)
contrastive learning
(2)
mathematical reasoning
(1)
symbolic reasoning
(1)
zero-shot learning
(1)
text classification
(1)
domain adaptation
(1)
continual learning
(1)
feature attribution
(1)
imitation learning
(1)
Papers
Efficient stagewise pretraining via progressive subnetworks
ICLR 2025
Learning to Keep a Promise: Scaling Language Model Decoding Parallelism with Learned Asynchronous Decoding
ICML 2025
Reasoning with Latent Thoughts: On the Power of Looped Transformers
ICLR 2025
Can Looped Transformers Learn to Implement Multi-step Gradient Descent for In-context Learning?
ICML 2024
On the Inductive Bias of Stacking Towards Improving Reasoning
NeurIPS 2024
Reasoning in Large Language Models Through Symbolic Math Word Problems
ACL 2023
Task-Specific Skill Localization in Fine-tuned Language Models
ICML 2023
Understanding Influence Functions and Datamodels via Harmonic Analysis
ICLR 2023
New Definitions and Evaluations for Saliency Methods: Staying Intrinsic, Complete and Sound
NeurIPS 2022
On Predicting Generalization using GANs
ICLR 2022
Understanding Contrastive Learning Requires Incorporating Inductive Biases
ICML 2022
A Mathematical Exploration of Why Language Models Help Solve Downstream Tasks
ICLR 2021
A Representation Learning Perspective on the Importance of Train-Validation Splitting in Meta-Learning
ICML 2021
Predicting What You Already Know Helps: Provable Self-Supervised Learning
NeurIPS 2021
A Sample Complexity Separation between Non-Convex and Convex Meta-Learning
ICML 2020
Provable Representation Learning for Imitation Learning via Bi-level Optimization
ICML 2020
A Theoretical Analysis of Contrastive Unsupervised Representation Learning
ICML 2019
A Compressed Sensing View of Unsupervised Text Embeddings, Bag-of-n-Grams, and LSTMs
ICLR 2018
A La Carte Embedding: Cheap but Effective Induction of Semantic Feature Vectors
ACL 2018