Jonathan Li
Machine Learning Engineer, SambaNova Systems
jonathanlingjieli [AT] gmail.com
Publications
Please find an up-to-date list of publications on my Google Scholar. Code published while at SambaNova uses my corporate GitHub account.
SnapStream: Efficient Long Sequence Decoding on Dataflow Accelerators PDF
Jonathan Li, Nasim Farahini, Evgenii Iuliugin, Magnus Vesterlund, Christian Häggström, Guangtao Wang, Shubhangi Upasani, Ayush Sachdeva, Rui Li, Faline Fu, Chen Wu, Ayesha Siddiqua, John Long, Tuowen Zhao, Matheen Musaddiq, Håkan Zeffer, Yun Du, Mingran Wang, Qinghua Li, Bo Li, Urmish Thakker, Raghu Prabhakar
Preprint (2025)
Synthetic Document Question Answering in Hungarian PDF Code Hugging Face
Jonathan Li, Zoltan Csaki, Nidhi Hiremath, Etash Guha, Fenglu Hong, Edward Ma, Urmish Thakker
Vision Language Models For All Workshop @ CVPR (2025)
LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference PDF
Guangtao Wang, Shubhangi Upasani, Chen Wu, Darshan Gandhi, Jonathan Lingjie Li, Changran Hu, Bo Li, Urmish Thakker
Workshop on Sparsity in LLMs @ ICLR (2025)
Training Domain Draft Models for Speculative Decoding: Best Practices and Insights PDF
Fenglu Hong, Ravi Raju, Jonathan Lingjie Li, Bo Li, Urmish Thakker, Avinash Ravichandran, Swayambhoo Jain, Changran Hu
Workshop on Scalable Optimization for Effiient and Adaptive Foundation Models @ ICLR (2025)
Composition of Experts: A Modular Compound AI System Leveraging Large Language Models PDF
Swayambhoo Jain, Ravi Raju, Bo Li, Zoltan Csaki, Jonathan Li, Kaizhao Liang, Guoyao Feng, Urmish Thakkar, Anand Sampat, Raghu Prabhakar, Sumati Jairath
Preprint (2024)
Constructing Domain-Specific Evaluation Sets for LLM-as-a-judge PDF
Ravi Shanker Raju, Swayambhoo Jain, Bo Li, Jonathan Lingjie Li, Urmish Thakker
First Workshop on Customizable NLP @ EMNLP (2024)
SambaLingo: Teaching Large Language Models New Languages PDF Hugging Face
Zoltan Csaki, Bo Li, Jonathan Lingjie Li, Qiantong Xu, Pian Pawakapan, Leon Zhang, Yun Du, Hengyu Zhao, Changran Hu, Urmish Thakker
Fourth Workshop on Multilingual Representation Learning @ EMNLP (2024)
HALOS: Hashing Large Output Space for Cheap Inference PDF
Zichang Liu, Zhaozhuo Xu, Alan Ji, Junyan Zhang, Jonathan Li, Beidi Chen, Anshumali Shrivastava
Fifth Conference on Machine Learning Systems (2022)
MONGOOSE: A Learnable LSH Framework for Efficient Neural Network Training PDF Code
Beidi Chen, Zichang Liu, Binghui Peng, Zhaozhuo Xu, Jonathan Lingjie Li, Tri Dao, Zhao Song, Anshumali Shrivastava, Christopher Re
Ninth International Conference on Learning Representations (2021)
Pipemare: Asynchronous Pipeline Parallel DNN Training PDF
Bowen Yang, Jian Zhang, Jonathan Li, Christopher Ré, Christopher Aberger, Christopher De Sa
Fourth Conference on Machine Learning Systems (2021)
Climbing the WOL: Training for Cheaper Inference PDF
Zichang Liu, Zhaozhuo Xu, Alan Ji, Jonathan Li, Beidi Chen, Anshumali Shrivastava
Preprint (2020)
Multirotor UAV State Prediction through Multi-Microphone Side-Channel Fusion PDF
Hendrik Vincent Koops, Kashish Garg, Munsung Kim, Jonathan Li, Anja Volk, Franz Franchetti
IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (2017)