Sujan Kumar Gonugondla

Machine Learning Researcher · Meta FAIR-MSL

About

A little about me

I'm a Machine Learning Researcher at Meta Superintelligence Labs (MSL), where I work on pretraining research. I am a core contributor to Muse Glimmer 30B, Meta's open-source on-device agentic model. Before that, I worked on the Llama 4 reasoning model.

Before Meta, I was a founding member of Amazon Q (now Amazon Kiro) at AWS AI Labs. I hold a Ph.D. from the University of Illinois at Urbana-Champaign, and a B.Tech and M.Tech from IIT Madras.

Research

Selected Publications

2026

Muse Glimmer 30B: An On-Device Agentic Model

Arash Ebrahim Abtahizadeh, Muna Aghamelu, Adil Ahmed, et al.

arXiv 2026 arXiv Meta AI

2025

AdvancedIF: Rubric-Based Benchmarking and Reinforcement Learning for Advancing LLM Instruction Following

Yun He, Wenzhe Li, Hejia Zhang, Songlin Li, Karishma Mandyam, Sopan Khosla, et al.

ACL 2026 arXiv Meta AI

2024

The N-Grammys: Accelerating Autoregressive Inference with Learning-Free Batched Speculation

Lawrence Stewart, Matthew Trager, Sujan Kumar Gonugondla, Stefano Soatto

ENLSP @ NeurIPS 2024 arXiv

2024

Approximately Aligned Decoding

Daniel Melcer, Sujan Kumar Gonugondla, Pramuditha Perera, Haifeng Qian, Wen-Hao Chiang, Yanjun Wang, Nihal Jain, Pranav Garg, Xiaofei Ma, Anoop Deoras

ICML 2025 arXiv

2024

BASS: Batched Attention-optimized Speculative Sampling

Haifeng Qian^*, Sujan Kumar Gonugondla^*, Sungsoo Ha, Mingyue Shang, Sanjay Krishna Gouda, Ramesh Nallapati, Sudipta Sengupta, Xiaofei Ma, Anoop Deoras

^* Equal contribution

ACL 2024 arXiv

2024

Token Alignment via Character Matching for Subword Completion

Ben Athiwaratkun, Shiqi Wang, Mingyue Shang, Yuchen Tian, Zijian Wang, Sujan Kumar Gonugondla, Sanjay Krishna Gouda, Robert Kwiatkowski, Ramesh Nallapati, Bing Xiang

ACL 2024 ACL

2024

Bifurcated Attention for Single-Context Large-Batch Sampling

Ben Athiwaratkun^*, Sujan Kumar Gonugondla^*, Sanjay Krishna Gouda, Haifeng Qian, Hantian Ding, Qing Sun, Jun Wang, Liangfu Chen, Jiacheng Guo, Parminder Bhatia, et al.

^* Equal contribution

ICML 2024 arXiv

2023

Greener yet Powerful: Taming Large Code Generation Models with Quantization

Xiaokai Wei^*, Sujan Kumar Gonugondla^*, Wasi Ahmad, Shiqi Wang, Baishakhi Ray, Haifeng Qian, Xiaopeng Li, Varun Kumar, Zijian Wang, Yuchen Tian, et al.

^* Equal contribution

EMNLP 2023 arXiv

2022

Multi-lingual Evaluation of Code Generation Models

Ben Athiwaratkun, Sanjay Krishna Gouda, Zijian Wang, Xiaopeng Li, Yuchen Tian, Ming Tan, Wasi Uddin Ahmad, Shiqi Wang, Qing Sun, Mingyue Shang, Sujan Kumar Gonugondla, et al.

ICLR 2023

2022

IMPQ: Reduced Complexity Neural Networks via Granular Precision Assignment

Sujan Kumar Gonugondla, Naresh R. Shanbhag

IEEE 2022 IEEE

2022

Fundamental Limits on Energy-Delay-Accuracy of In-Memory Architectures in Inference Applications

Sujan K. Gonugondla, Charbel Sakr, Hassan Dbouk, Naresh R. Shanbhag

IEEE 2022 arXiv

For the complete list, visit Google Scholar ↗

Press