{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T06:00:36Z","timestamp":1780639236564,"version":"3.54.1"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,20]],"date-time":"2026-04-20T00:00:00Z","timestamp":1776643200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,20]]},"DOI":"10.23919\/date69613.2026.11539395","type":"proceedings-article","created":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T19:53:10Z","timestamp":1780602790000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["DynaMo: Runtime Switchable Quantization for MoE with Cross-Dataset Adaptation"],"prefix":"10.23919","author":[{"given":"Zihao","family":"Zheng","sequence":"first","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiuping","family":"Cui","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Size","family":"Zheng","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maoliang","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiayu","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Liang","sequence":"additional","affiliation":[{"name":"Peking University,School of Integrated Circuits,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Chen","sequence":"additional","affiliation":[{"name":"Peking University,School of Computer Science,Beijing,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.172055626.64129172\/v1","article-title":"A survey on mixture of experts","author":"Cai","year":"2024"},{"issue":"1","key":"ref2","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103664"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3412713"},{"key":"ref5","article-title":"Home: Hierarchy of multi-gate experts for multi-task learning at kuaishou","author":"Wang","year":"2024"},{"key":"ref6","article-title":"Fedmoe: Personalized federated learning via heterogeneous mixture of experts","author":"Mei","year":"2024"},{"key":"ref7","article-title":"Da-moe: Towards dynamic expert allocation for mixture-of-experts models","author":"Aghdam","year":"2024"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.1109\/DAC63849.2025.11133274","article-title":"Hybrimoe: Hybrid cpu-gpu scheduling and cache management for efficient moe inference","author":"Zhong","year":"2025"},{"key":"ref9","doi-asserted-by":"crossref","DOI":"10.2139\/ssrn.4996660","article-title":"A survey of low-bit large language models: Basics, systems, and algorithms","author":"Gong","year":"2024"},{"key":"ref10","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2023"},{"key":"ref11","article-title":"Quantease: Optimization-based quantization for language models","author":"Behdin","year":"2023"},{"key":"ref12","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","author":"Xiao","year":"2024"},{"key":"ref13","article-title":"Awq: Activation-aware weight quantization for llm compression and acceleration","author":"Lin","year":"2024"},{"key":"ref14","article-title":"Rptq: Reorder-based post-training quantization for large language models","author":"Yuan","year":"2023"},{"key":"ref15","article-title":"Atom: Low-bit quantization for efficient and accurate llm serving","author":"Zhao","year":"2024"},{"key":"ref16","article-title":"Mixture of quantized experts (moqe): Complementary effect of low-bit quantization and robustness","author":"Kim","year":"2023"},{"key":"ref17","article-title":"Examining post-training quantization for mixture-of-experts: A benchmark","author":"Li","year":"2024"},{"key":"ref18","article-title":"Jetmoe: Reaching llama2 performance with 0.1m dollars","author":"Shen","year":"2024"},{"key":"ref19","article-title":"Olmoe: Open mixture-of-experts language models","author":"Muennighoff","year":"2024"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3669940.3707272"},{"key":"ref21","first-page":"29 335","article-title":"Dselect-k: Differentiable selection in the mixture of experts with applications to multi-task learning","volume":"34","author":"Hazimeh","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3676536.3676741"},{"key":"ref23","article-title":"Pointer sentinel mixture models","volume-title":"5th International Conference on Learning Representations, ICLR 2017, Toulon, France, April 24-26, 2017, Conference Track Proceedings","author":"Merity"},{"key":"ref24","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume-title":"J. Mach. Learn. Res","volume":"21","author":"Raffel","year":"2020"},{"key":"ref25","article-title":"Moe-girl","year":"2024"},{"key":"ref26","article-title":"Qwen1.5-moe: Matching 7b model performance with 1\/3 activated parameters","author":"Team","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-2607"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ssdm.2003.1214975"},{"key":"ref31","article-title":"Choice of plausible alternatives: An evaluation of commonsense causal reasoning","volume-title":"Logical Formalizations of Commonsense Reasoning, Papers from the 2011 AAAI Spring Symposium, Technical Report SS-11-06, Stanford, California, USA, March 21-23, 2011","author":"Roemmele"},{"key":"ref32","article-title":"Superglue: A stickier benchmark for general-purpose language understanding systems","volume-title":"Advances in Neural Information Processing Systems","volume":"32","author":"Wang","year":"2019"}],"event":{"name":"2026 Design, Automation & Test in Europe Conference (DATE)","location":"Verona, Italy","start":{"date-parts":[[2026,4,20]]},"end":{"date-parts":[[2026,4,22]]}},"container-title":["2026 Design, Automation & Test in Europe Conference (DATE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11539023\/11539024\/11539395.pdf?arnumber=11539395","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:07:41Z","timestamp":1780636061000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11539395\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":32,"URL":"https:\/\/doi.org\/10.23919\/date69613.2026.11539395","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]}}}