α
Research
Alpha Leak
Conferences
Topics
Top Authors
Rankings
Browse All
EN
中
Home
/
Authors
/
Suhas Kotha
Suhas Kotha
4
papers
198
total citations
papers (4)
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
ICLR 2024
arXiv
114
citations
Repetition Improves Language Model Embeddings
ICLR 2025
arXiv
60
citations
Provably Bounding Neural Network Preimages
NEURIPS 2023
arXiv
24
citations
Position: A Safe Harbor for AI Evaluation and Red Teaming
ICML 2024
0
citations