Vimal Thilak
4 papers · 2024–2025 · 3 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 ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(12)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Machine Learning
(4)
Artificial Intelligence
(2)
Core AI
(2)
Core Methods
(2)
Learning Types · Machine Learning
(2)
Deep Learning
(1)
Natural Language Processing
(1)
Application Areas
(1)
Learning Types · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Optimization & Theory · Deep Learning
(1)
Resources & Methods
(1)
Keywords
self-supervised learning
(2)
feature learning
(1)
policy gradient
(1)
linear discriminant analysis
(1)
sparsity
(1)
reward function
(1)
implicit bia
(1)
scaling law
(1)
linear probing
(1)
masked autoencoder
(1)
joint embedding predictive architecture
(1)
latent space prediction
(1)
vanishing gradient
(1)
model performance
(1)
joint embedding
(1)
representation quality
(1)
reinforcement fine-tuning
(1)
mixture-of-experts
(1)
flops
(1)
representation learning
(1)
Papers
Parameters vs FLOPs: Scaling Laws for Optimal Sparsity for Mixture-of-Experts Language Models
ICML 2025
How JEPA Avoids Noisy Features: The Implicit Bias of Deep Linear Self Distillation Networks
NeurIPS 2024
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
ICLR 2024
Vanishing Gradients in Reinforcement Finetuning of Language Models
ICLR 2024