Davis Wertheimer

Researcher, International Business Machines

Joined

December 2019

Names

Davis Wertheimer

Emails

****@cornell.edu (Confirmed)

****@ibm.com (Confirmed)

Personal Links

Homepage

Google Scholar

DBLP

Career & Education History

Researcher

International Business Machines (ibm.com)

2022 – Present

PhD student

Cornell University (cornell.edu)

2016 – 2022

Undergrad student

Stanford University (stanford.edu)

2012 – 2016

Advisors, Relations & Conflicts

PhD Advisor

Bharath Hariharan

2017 – Present

Coauthor

Luming Tang

2019 – 2021

Expertise

machine learning

computer vision

few-shot learning

neural architectures

2017 – Present

Publications

Frayed RoPE and Long Inputs: A Geometric Perspective
Davis Wertheimer, Aozhong Zhang, Derrick Liu, Penghang Yin, Naigang Wang
- ICLR 2026 Poster
- Readers: Everyone
From Collapse to Control: Understanding and Extending Context Length in Emerging Hybrid Models via Universal Position Interpolation
Haochen Shen, Davis Wertheimer, Zheng Wang, Garrett Goon, Derrick Liu, Naigang Wang, Mudhakar Srivatsa, Raghu K. Ganti, Minjia Zhang
- ICLR 2026 Poster
- Readers: Everyone
SudokuSens: Enhancing Deep Learning Robustness for IoT Sensing Applications using a Generative Approach
Tianshi Wang, Jinyang Li, Ruijie Wang, Denizhan Kara, Shengzhong Liu, Davis Wertheimer, Antoni Viros-i-Martin, Raghu K. Ganti, Mudhakar Srivatsa, Tarek F. Abdelzaher
- CoRR 2024
- Readers: Everyone
INDUS: Effective and Efficient Language Models for Scientific Applications
Bishwaranjan Bhattacharjee, Aashka Trivedi, Masayasu Muraoka, Muthukumaran Ramasubramanian, Takuma Udagawa, Iksha Gurung, Rong Zhang, Bharath Dandala, Rahul Ramachandran, Manil Maskey, Kaylin M. Bugbee, Mike Little, Elizabeth Fancher, Lauren M. Sanders, Sylvain V. Costes, Sergi Blanco-Cuaresma, Kelly E. Lockhart, Thomas Allen, Félix Grèzes, Megan Ansdell et al. (14 additional authors not shown)
- CoRR 2024
- Readers: Everyone
Accelerating Production LLMs with Combined Token/Embedding Speculators
Davis Wertheimer, Joshua Rosenkranz, Thomas P. Parnell, Sahil Suneja, Pavithra Ranganathan, Raghu K. Ganti, Mudhakar Srivatsa
- CoRR 2024
- Readers: Everyone
INDUS: Effective and Efficient Language Models for Scientific Applications
Bishwaranjan Bhattacharjee, Aashka Trivedi, Masayasu Muraoka, Muthukumaran Ramasubramanian, Takuma Udagawa, Iksha Gurung, Nishan Pantha, Rong Zhang, Bharath Dandala, Rahul Ramachandran, Manil Maskey, Kaylin M. Bugbee, Michael Little, Elizabeth Fancher, Irina Gerasimov, Armin Mehrabian, Lauren M. Sanders, Sylvain Costes, Sergi Blanco-Cuaresma, Kelly E. Lockhart et al. (16 additional authors not shown)
- EMNLP (Industry Track) 2024
- Readers: Everyone
Diagnosing and Remedying Shot Sensitivity with Cosine Few-Shot Learners
Davis Wertheimer, Luming Tang, Bharath Hariharan
- CoRR 2022
- Readers: Everyone
NorBERT: NetwOrk Representations through BERT for Network Analysis and Management
Franck Le, Davis Wertheimer, Seraphin B. Calo, Erich M. Nahum
- CoRR 2022
- Readers: Everyone
NorBERT: NetwOrk Representations Through BERT for Network Analysis & Management
Franck Le, Davis Wertheimer, Seraphin B. Calo, Erich M. Nahum
- MASCOTS 2022
- Readers: Everyone

View all 19 publications

Co-Authors

View all 64 co-authors