Saurabh Garg
24 papers · 2018–2024 · 6 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 ↓+9 more ↓ Show less ↑
🗺️ Taxonomy Completionist (56) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird
👑
Triple Crown
👥
Mega-Team · Legion
🤝
Dynamic Duo
(11)
⚡
Prolific Year · Productive
🌈
Renaissance Researcher
(6)
💎
Century Club · Bronze
❓
The Questioner
(2)
🗃️
Keyword Collector
(114)
🔥
Unstoppable · Bronze
Top co-authors
Research topics
Machine Learning
(22)
Learning Types · Machine Learning
(16)
Application Areas
(11)
Deep Learning
(9)
Optimization & Theory · Machine Learning
(9)
Artificial Intelligence
(7)
Natural Language Processing
(5)
Core AI
(5)
Core Methods
(4)
Optimization & Theory · Deep Learning
(4)
Resources & Methods
(4)
Generation
(3)
Learning Types · Deep Learning
(3)
Models
(3)
Techniques
(3)
Keywords
distribution shift
(7)
domain adaptation
(5)
language model
(4)
label shift
(3)
semi-supervised learning
(2)
large language model
(2)
zero-shot learning
(2)
unsupervised learning
(2)
unlabeled data
(2)
reinforcement learning
(2)
vision-language model
(2)
neural network
(2)
transfer learning
(1)
domain generalization
(1)
double descent
(1)
model selection
(1)
few-shot learning
(1)
continual learning
(1)
image classification
(1)
policy gradient
(1)
Papers
DataComp-LM: In search of the next generation of training sets for language models
NeurIPS 2024
Medical Adaptation of Large Language and Vision-Language Models: Are We Making Progress?
EMNLP 2024
Post-Hoc Reversal: Are We Selecting Models Prematurely?
NeurIPS 2024
Prompting is a Double-Edged Sword: Improving Worst-Group Robustness of Foundation Models
ICML 2024
RL on Incorrect Synthetic Data Scales the Efficiency of LLM Math Reasoning by Eight-Fold
NeurIPS 2024
TiC-CLIP: Continual Training of CLIP Models
ICLR 2024
(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy
NeurIPS 2023
CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets
ICML 2023
Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift
NeurIPS 2023
Deconstructing Distributions: A Pointwise Framework of Learning
ICLR 2023
Disentangling the Mechanisms Behind Implicit Regularization in SGD
ICLR 2023
Downstream Datasets Make Surprisingly Good Pretraining Corpora
ACL 2023
Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms
NeurIPS 2023
RLSbench: Domain Adaptation Under Relaxed Label Shift
ICML 2023
Characterizing Datapoints via Second-Split Forgetting
NeurIPS 2022
Domain Adaptation under Open Set Label Shift
NeurIPS 2022
Leveraging unlabeled data to predict out-of-distribution performance
ICLR 2022
Unsupervised Learning under Latent Label Shift
NeurIPS 2022
Mixture Proportion Estimation and PU Learning:A Modern Approach
NeurIPS 2021
On Proximal Policy Optimization’s Heavy-tailed Gradients
ICML 2021
RATT: Leveraging Unlabeled Data to Guarantee Generalization
ICML 2021
A Unified View of Label Shift Estimation
NeurIPS 2020
Code-switched Language Models Using Dual RNNs and Same-Source Pretraining
EMNLP 2018
Dual Language Models for Code Switched Speech Recognition
Interspeech 2018