Druv Pai
9 papers · 2023–2025 · 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 ↓+4 more ↓ Show less ↑
🐣 Hot Topic Early Bird 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (16) 🌍 Conference Polyglot · Bronze 🏆 Keyword Champion (2)
🧭
Keyword Pioneer
👑
Triple Crown
❓
The Questioner
⚡
Prolific Year · Productive
Venues
Top co-authors
Research topics
Deep Learning
(9)
Architectures
(7)
Machine Learning
(6)
Core Methods
(4)
Techniques
(3)
Artificial Intelligence
(2)
Computer Vision
(2)
Core AI · Artificial Intelligence
(2)
Learning Types · Machine Learning
(2)
Models
(2)
Optimization & Theory
(2)
Mathematics & Optimization
(1)
Analysis
(1)
Core AI · Computer Vision
(1)
Learning Types · Deep Learning
(1)
Keywords
representation learning
(6)
white-box transformer
(2)
token compression
(2)
vision transformer
(2)
transformer architecture
(2)
sparse rate reduction
(2)
token representation
(2)
latent space
(1)
signal-to-noise ratio
(1)
semantic segmentation
(1)
model interpretability
(1)
diffusion model
(1)
self attention
(1)
downstream task
(1)
computational efficiency
(1)
structured representation
(1)
skip connection
(1)
sparse representation
(1)
masked autoencoder
(1)
model scaling
(1)
Papers
Attention-Only Transformers via Unrolled Subspace Denoising
ICML 2025
Simplifying DINO via Coding Rate Regularization
ICML 2025
Token Statistics Transformer: Linear-Time Attention via Variational Rate Reduction
ICLR 2025
A Global Geometric Analysis of Maximal Coding Rate Reduction
ICML 2024
Masked Completion via Structured Diffusion with White-Box Transformers
ICLR 2024
Representation Learning via Manifold Flattening and Reconstruction
JMLR 2024
Scaling White-Box Transformers for Vision
NeurIPS 2024
White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?
JMLR 2024
White-Box Transformers via Sparse Rate Reduction
NeurIPS 2023