Harshil Vejendla
6 papers · 2025–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
🐝 Cross-Pollinator (15) 🌍 Conference Polyglot (2) 🌉 Interdisciplinary Bridge 🗺️ Taxonomy Completionist (13) 🐺 Lone Wolf (4)
⭐
Rising Star
(6)
⚡
Prolific Year
(6)
Conferences
AACL (2)
EMNLP (2)
IJCNLP (2)
Keywords
transformer model
(2)
string rewriting
(2)
length extrapolation
(2)
curriculum learning
(2)
neural architecture
(1)
approximate nearest neighbor
(1)
generative model
(1)
algorithmic reasoning
(1)
mixture of expert
(1)
sequence model
(1)
systematic generalization
(1)
inference efficiency
(1)
load balancing
(1)
embedding model
(1)
vector database
(1)
neural network
(1)
model upgrade
(1)
structural inductive bia
(1)
sparse routing
(1)
representation learning
(1)
Papers
Drift-Adapter: A Practical Approach to Near Zero-Downtime Embedding Model Upgrades in Vector Databases
EMNLP 2025
SliceMoE: Routing Embedding Slices Instead of Tokens for Fine-Grained and Balanced Transformer Scaling
EMNLP 2025
Teaching by Failure: Counter-Example–Driven Curricula for Transformer Self-Improvement
IJCNLP 2025
RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling
IJCNLP 2025
Teaching by Failure: Counter-Example–Driven Curricula for Transformer Self-Improvement
AACL 2025
RewriteNets: End-to-End Trainable String-Rewriting for Generative Sequence Modeling
AACL 2025