Cho, Minsik

13 publications

ICLRW 2025 From Dense to Dynamic: Token-Difficulty Driven MoEfication of Pre-Trained LLMs Kumari Nishu, Sachin Mehta, Samira Abnar, Mehrdad Farajtabar, Maxwell Horton, Mahyar Najibi, Moin Nabi, Minsik Cho, Devang Naik

ICML 2025 SPD: Sync-Point Drop for Efficient Tensor Parallelism of Large Language Models Han-Byul Kim, Duc N.M Hoang, Arnav Kundu, Mohammad Samragh, Minsik Cho

ICMLW 2024 Differentiable Soft Min-Max Loss to Restrict Weight Range for Model Quantization Arnav Kundu, Chungkuk Yoo, Minsik Cho, Saurabh Adya

ICML 2024 KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation Minsik Cho, Mohammad Rastegari, Devang Naik

ICMLW 2024 LazyLLM: Dynamic Token Pruning for Efficient Long Context LLM Inference Qichen Fu, Minsik Cho, Thomas Merth, Sachin Mehta, Mohammad Rastegari, Mahyar Najibi

NeurIPSW 2024 Simple LLM Compression Recovery Using Dynamic Prompting with Theoretical Analysis Duc N.M Hoang, Minsik Cho, Thomas Merth, Mohammad Rastegari, Zhangyang Wang

NeurIPS 2023 PDP: Parameter-Free Differentiable Pruning Is All You Need Minsik Cho, Saurabh Adya, Devang Naik

ICMLW 2023 PDP: Parameter-Free Differentiable Pruning Is All You Need Minsik Cho, Saurabh Adya, Devang Naik

ICLR 2022 DKM: Differentiable K-Means Clustering Layer for Neural Network Compression Minsik Cho, Keivan Alizadeh-Vahid, Saurabh Adya, Mohammad Rastegari

AAAI 2021 NASTransfer: Analyzing Architecture Transferability in Large Scale Neural Architecture Search Rameswar Panda, Michele Merler, Mayoore S. Jaiswal, Hui Wu, Kandan Ramakrishnan, Ulrich Finkler, Chun-Fu (Richard) Chen, Minsik Cho, Rogério Feris, David S. Kung, Bishwaranjan Bhattacharjee

CVPRW 2020 MUTE: Inter-Class Ambiguity Driven Multi-Hot Target Encoding for Deep Neural Network Design Mayoore S. Jaiswal, Bumsoo Kang, Jinho Lee, Minsik Cho

ICLR 2020 SNOW: Subscribing to Knowledge via Channel Pooling for Transfer & Lifelong Learning of Convolutional Neural Networks Chungkuk Yoo, Bumsoo Kang, Minsik Cho

ICML 2017 MEC: Memory-Efficient Convolution for Deep Neural Network Minsik Cho, Daniel Brand