{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:20:33Z","timestamp":1778048433582,"version":"3.51.4"},"reference-count":74,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00121","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"1180-1190","source":"Crossref","is-referenced-by-count":0,"title":["Beyond Real Weights: Hypercomplex Representations for Stable Quantization"],"prefix":"10.1109","author":[{"given":"Jawad Ibn","family":"Ahad","sequence":"first","affiliation":[{"name":"RobotBulls Labs,Artificial Intelligence Department,Geneva,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maisha","family":"Rahman","sequence":"additional","affiliation":[{"name":"RobotBulls Labs,Artificial Intelligence Department,Geneva,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amrijit","family":"Biswas","sequence":"additional","affiliation":[{"name":"RobotBulls Labs,Artificial Intelligence Department,Geneva,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muhammad Rafsan","family":"Kabir","sequence":"additional","affiliation":[{"name":"RobotBulls Labs,Artificial Intelligence Department,Geneva,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Robin","family":"Krambroeckers","sequence":"additional","affiliation":[{"name":"RobotBulls Labs,Artificial Intelligence Department,Geneva,Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sifat","family":"Momen","sequence":"additional","affiliation":[{"name":"North South University,Machine Intelligence Lab (MILab),Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nabeel","family":"Mohammed","sequence":"additional","affiliation":[{"name":"North South University,Machine Intelligence Lab (MILab),Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shafin","family":"Rahman","sequence":"additional","affiliation":[{"name":"North South University,Machine Intelligence Lab (MILab),Bangladesh"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"NeurIPS","author":"Tsimpoukelli"},{"key":"ref2","article-title":"Glm-130b: An open bilingual pre-trained model","volume-title":"ICLR","author":"Zeng"},{"key":"ref3","first-page":"1550","article-title":"Clip meets multimodality: A survey of vision-and-language models","volume":"11","author":"Gadre","year":"2023","journal-title":"Transactions of the Association for Computational Linguistics"},{"key":"ref4","article-title":"A survey on multimodal pre-trained models","author":"Xu","year":"2022","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"key":"ref5","article-title":"Foundational models in robotics: Applications, challenges, and opportunities","volume-title":"RSS","author":"Vasudevan"},{"key":"ref6","article-title":"Gpt-4 technical report","year":"2023"},{"key":"ref7","article-title":"A comprehensive survey of multimodal large language models","author":"Zhao","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref9","article-title":"Towards unified parameter-efficient tuning","volume-title":"ACL","author":"He"},{"key":"ref10","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref11","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume-title":"NeurIPS","author":"Mahabadi"},{"key":"ref12","article-title":"Multitask instruction tuning of pretrained transformers","volume-title":"EMNLP","author":"Asai"},{"key":"ref13","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Fedus"},{"key":"ref14","article-title":"Unified scaling laws for sparsity and quantization in neural networks","volume-title":"Proceedings of the International Conference on Machine Learning (ICML)","author":"Clark"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.804"},{"key":"ref16","article-title":"Knowledge distillation: A comprehensive survey","author":"Jin","year":"2023","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref17","article-title":"Distilling large language models for efficient deployment","author":"Hsieh","year":"2023","journal-title":"Foundations and Trends in Machine Learning"},{"key":"ref18","article-title":"Multimodal knowledge distillation for efficient multimodal transformers","volume-title":"ACL","author":"Zhou"},{"key":"ref19","article-title":"Cross-modal distillation with semantic alignment","volume-title":"ICCV","author":"Fang"},{"key":"ref20","article-title":"Quaternion recurrent neural networks","volume-title":"ICLR","author":"Parcollet"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489651"},{"key":"ref22","first-page":"148","article-title":"Octonion recurrent neural networks","volume":"402","author":"Zhu","year":"2020","journal-title":"Neurocomputing"},{"issue":"5","key":"ref23","first-page":"3781","article-title":"Survey on quaternion and hypercomplex neural networks","volume":"54","author":"Zhang","year":"2021","journal-title":"Artificial Intelligence Review"},{"key":"ref24","article-title":"Parameterized hypercomplex multiplication layers","volume-title":"ICML","author":"Zhang"},{"key":"ref25","article-title":"Phm-transformers: Parameterized hypercomplex multiplication for transformers","volume-title":"TMLR","author":"Mao"},{"key":"ref26","article-title":"Hypercomplex vision transformers","volume-title":"CVPR","author":"Gao"},{"key":"ref27","article-title":"Residual hypercomplex networks for stable deep training","author":"Cheng","year":"2024","journal-title":"Neural Networks"},{"issue":"12","key":"ref28","first-page":"12345","article-title":"Hypercomplex neural networks with enhanced residual connections","volume":"33","author":"Wang","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref29","article-title":"Hybrid hypercomplex transformers for multimodal learning","volume-title":"AAAI","author":"Kim"},{"key":"ref30","article-title":"Hypercomplex neural architectures for large-scale multimodal learning","author":"Zhang","year":"2024","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"ref31","article-title":"Hybrid hypercomplex models for cross-modal alignment","volume-title":"ACL","author":"Lee"},{"key":"ref32","article-title":"Distilling the knowledge in a neural network","volume-title":"NIPS Workshop","author":"Hinton"},{"key":"ref33","article-title":"Fitnets: Hints for thin deep nets","volume-title":"ICLR","author":"Romero"},{"key":"ref34","article-title":"Paying more attention to attention","volume-title":"ICLR","author":"Zagoruyko"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1441"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref38","article-title":"Distilbert: Smaller, faster, cheaper and lighter","volume-title":"NeurIPS Workshop","author":"Sanh"},{"key":"ref39","article-title":"Multimodal knowledge distillation for visual question answering","author":"Gupta","year":"2022","journal-title":"IEEE Transactions on Multimedia"},{"key":"ref40","article-title":"Efficient multimodal knowledge distillation","volume-title":"AAAI","author":"Li"},{"key":"ref41","article-title":"Cross-modal knowledge distillation with adaptive teachers","author":"Wu","year":"2024","journal-title":"Pattern Recognition"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"ref43","article-title":"Progressive knowledge distillation for efficient visual recognition","volume-title":"ECCV","author":"Shen"},{"key":"ref44","article-title":"Learning from multiple teachers","volume-title":"ICML","author":"You"},{"key":"ref45","article-title":"Multi-teacher knowledge distillation with meta learning","author":"Yang","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"ref46","article-title":"Reinforcement learning with knowledge distillation","volume-title":"ICLR","author":"Wang"},{"key":"ref47","article-title":"Cross-modal knowledge distillation for vision-language pretraining","volume-title":"ACL","author":"Tang"},{"key":"ref48","article-title":"Cross-modal knowledge distillation for retrieval and pretraining","volume-title":"ACL","author":"Chen"},{"key":"ref49","article-title":"Parameter-efficient transfer learning for nlp","volume-title":"ICML","author":"Houlsby"},{"key":"ref50","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu"},{"key":"ref51","article-title":"Adaptive low-rank adaptation for parameter-efficient fine-tuning","volume-title":"ICLR","author":"Zhang"},{"key":"ref52","article-title":"Dora: Weight-decomposed low-rank adaptation","volume-title":"NeurIPS","author":"Liu"},{"key":"ref53","article-title":"Mixlora: Composable parameter-efficient adaptation via mixtures of low-rank experts","volume-title":"ACL","author":"Chen"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref55","article-title":"The power of scale: Parameter-efficient adaptation for pretrained language models","volume-title":"EMNLP","author":"Lester"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref57","article-title":"Multimodal lora for vision-language models","author":"Zhang","year":"2023"},{"key":"ref58","article-title":"Parameter-efficient multimodal learning with low-rank adaptation","volume-title":"NeurIPS","author":"Chen"},{"key":"ref59","article-title":"Peft for multimodal transformers","author":"Mukherjee","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref60","article-title":"Unified parameter-efficient fine-tuning for instruction-tuned models","volume-title":"ICLR","author":"He"},{"key":"ref61","article-title":"Sparse-tuning: Parameter-efficient fine-tuning with sparse updates","volume-title":"ACL","author":"Ma"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755433"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00394"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1426"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"issue":"8","key":"ref71","article-title":"Llava-next: Improved reasoning, ocr, and world knowledge, january 2024","volume-title":"URL https:\/\/llava-vl.github.io\/blog\/2024-01-30-llava-next","volume":"1","author":"Liu","year":"2024"},{"key":"ref72","article-title":"Large multilingual models pivot zero-shot multimodal learning across languages","author":"Hu","year":"2023"},{"key":"ref73","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref74","article-title":"Deepseek-vl2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492223.pdf?arnumber=11492223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:05:25Z","timestamp":1778047525000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00121","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}