Publications

Our research appears in international conferences and journals.

2026

KnapSpec: Self-Speculative Decoding via Adaptive Layer Selection as a Knapsack Problem
Seongjin Cha*, Gyuwan Kim*, Dongsu Han, Tao Yang, Insu Han (* Equal contribution)
Under Review
DNAChunker: Learnable Tokenization for DNA Language Models
Taewon Kim, Jihwan Shin, Hyomin Kim, Youngmok Jung, Jonhoon Lee, Won-Chul Lee, Sungsoo Ahn, Insu Han
Under Review
PolarQuant: Quantizing KV Caches with Polar Transformation
Insu Han, Praneeth Kacham, Amin Karbasi, Vahab Mirrokni, Amir Zandieh
International Conference on Artificial Intelligence and Statistics (AISTATS 2026)

2025

Streaming Attention Approximation via Discrepancy Theory
Ekaterina Kochetkova, Kshiteej Sheth, Insu Han, Amir Zandieh, Michael Kapralov
Advances in Neural Information Processing Systems (NeurIPS 2025) — Spotlight
PDF
Mamba Drafters for Speculative Decoding
Daewon Choi, Seunghyuk Oh, Saket Dingliwal, Jihoon Tack, Kyuyoung Kim, Woomin Song, Seojin Kim, Insu Han, Jinwoo Shin, Aram Galstyan, Shubham Katiyar, Sravan Babu Bodapati
Conference on Empirical Methods in Natural Language Processing (EMNLP Findings 2025)
PDF
CalibQuant: 1-Bit KV Cache Quantization for Multimodal LLMs
Insu Han, Zeliang Zhang, Zhiyuan Wang, Yifan Zhu, Susan Liang, Jiani Liu, Haiting Lin, Mingjie Zhao, Chenliang Xu, Kun Wan, Wentian Zhao
International Conference on Machine Learning (ICML 2025) Long Context Foundation Model (LCFM) Workshop
ClusterGen: Token Generation in Sublinear Time and Memory
Amir Zandieh*, Insu Han*, Vahab Mirrokni, Amin Karbasi (* Equal Contribution)
International Conference on Learning Representations (ICLR 2025) SLLM Workshop
QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
Amir Zandieh, Majid Daliri, Insu Han
Association for the Advancement of Artificial Intelligence (AAAI 2025)

2024

Cell2Sentence: Teaching Large Language Models the Language of Biology
Daniel Levine*, Syed Asad Rizvi*, Sacha Levy, Nazreen Pallikkavaliyaveetil, David Zhang, Xingyu Chen, Sina Ghadermarzi, Ruiming Wu, Zihe Zheng, Ivan Vrkic, Anna Zhong, Daphne Raskin, Insu Han, Antonio Henrique de Oliveira Fonseca, Josue Ortega Caro, Amin Karbasi, Rahul M. Dhodapkar, David van Dijk
International Conference on Machine Learning (ICML 2024)
HyperAttention: Long-context Attention in Near-Linear Time
Insu Han, Rajesh Jayaram, Amin Karbasi, Vahab Mirrokni, David P. Woodruff, Amir Zandieh
International Conference on Learning Representations (ICLR 2024)

2023

Near Optimal Reconstruction of Spherical Harmonic Expansions
Amir Zandieh, Insu Han, Haim Avron
Advances in Neural Information Processing Systems (NeurIPS 2023)
KDEformer: Accelerating Transformers via Kernel Density Estimation
Amir Zandieh, Insu Han, Majid Daliri, Amin Karbasi
International Conference on Machine Learning (ICML 2023)

2022

Fast Neural Kernel Embeddings for General Activations
Insu Han, Amir Zandieh, Jaehoon Lee, Roman Novak, Amin Karbasi
Advances in Neural Information Processing Systems (NeurIPS 2022)
PDF
Scalable MCMC Sampling for Nonsymmetric Determinantal Point Processes
Insu Han, Mike Gartrell, Elvis Dohmatob, Amin Karbasi
International Conference on Machine Learning (ICML 2022) — Oral (2.1%)
PDF
Random Gegenbauer Features for Scalable Kernel Methods
Insu Han, Amir Zandieh, Haim Avron
International Conference on Machine Learning (ICML 2022) — Oral (2.1%)
PDF
Scalable Sampling for Nonsymmetric Determinantal Point Processes
Insu Han, Mike Gartrell, Jennifer Gillenwater, Elvis Dohmatob, Amin Karbasi
International Conference on Learning Representations (ICLR 2022) — Spotlight
PDF

2021

Scaling Neural Tangent Kernels via Sketching and Random Features
Insu Han, Amir Zandieh, Haim Avron, Neta Shoham, Chaewon Kim, Jinwoo Shin
Advances in Neural Information Processing Systems (NeurIPS 2021)
PDF
Scalable Learning and MAP Inference for Nonsymmetric Determinantal Point Processes
Mike Gartrell, Insu Han, Elvis Dohmatob, Jennifer Gillenwater, Victor-Emmanuel Brunel
International Conference on Learning Representations (ICLR 2021) — Oral (1.8%)
PDF

2015–2020

Polynomial Tensor Sketch for Element-wise Function of Low-Rank Matrix
Insu Han, Haim Avron, Jinwoo Shin
International Conference on Machine Learning (ICML 2020)
PDF
MAP Inference for Customized Determinantal Point Processes via Maximum Inner Product Search
Insu Han, Jennifer Gillenwater
International Conference on Artificial Intelligence and Statistics (AISTATS 2020)
PDF
Stochastic Chebyshev Gradient Descent for Spectral Optimization
Insu Han, Haim Avron, Jinwoo Shin
Neural Information Processing Systems (NeurIPS 2018) — Spotlight (3.5%)
PDF
Faster Greedy MAP Inference for Determinantal Point Processes
Insu Han, Prabhanjan Kambadur, Kyoungsoo Park, Jinwoo Shin
International Conference on Machine Learning (ICML 2017)
PDF
Approximating Spectral Sums of Large-scale Matrices using Stochastic Chebyshev Approximations
Insu Han, Dmitry Malioutov, Haim Avron, Jinwoo Shin
SIAM Journal on Scientific Computing (SISC 2017)
PDF
Large-scale Log-determinant Computation through Stochastic Chebyshev Expansions
Insu Han, Dmitry Malioutov, Jinwoo Shin
International Conference on Machine Learning (ICML 2015)
PDF