{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:49:21Z","timestamp":1763059761382,"version":"3.45.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T00:00:00Z","timestamp":1759190400000},"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":[[2025,9,30]]},"DOI":"10.1109\/sibgrapi67909.2025.11223371","type":"proceedings-article","created":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T18:26:15Z","timestamp":1762885575000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Tiny Titans: Efficient Large Vision, Language and Multimodal Models Through Pruning"],"prefix":"10.1109","author":[{"given":"Carolina","family":"Tavares","sequence":"first","affiliation":[{"name":"Universidade Federal Fluminense"}]},{"given":"Leandro","family":"Mugnaini","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Gustavo Henrique do","family":"Nascimento","sequence":"additional","affiliation":[{"name":"Universidade Federal Fluminense"}]},{"given":"Ian","family":"Pons","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Keith","family":"Ogawa","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Guilherme","family":"Stern","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Lucas","family":"Libanio","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Aline","family":"Paes","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Anna Helena Reali","family":"Costa","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]},{"given":"Artur","family":"Jordao","sequence":"additional","affiliation":[{"name":"Universidade de Sao Paulo,Brazil"}]}],"member":"263","reference":[{"journal-title":"Artificial intelligence index report","year":"2024","author":"Maslej","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.70777\/si.v2i2.14755"},{"key":"ref3","article-title":"Holistically evaluating the environmental impact of creating language models","volume-title":"ICLR","author":"Morrison","year":"2025"},{"key":"ref4","article-title":"Llmcarbon: Modeling the end-to-end carbon footprint of large language models","volume-title":"ICLR","author":"Faiz","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00886"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00098"},{"key":"ref8","article-title":"Optimal brain damage","volume-title":"NeurIPS","author":"LeCun","year":"1989"},{"key":"ref9","article-title":"Second order derivatives for network pruning: Optimal brain surgeon","volume-title":"NeurIPS","author":"Hassibi","year":"1992"},{"key":"ref10","article-title":"Shortened llama: A simple depth pruning for large language models","volume-title":"ICLR","author":"Kim","year":"2024"},{"key":"ref11","article-title":"Modegpt: Modular decomposition for large language model compression","volume-title":"ICLR","author":"Lin","year":"2025"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00877"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00882"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01873"},{"key":"ref15","article-title":"Structural pruning via latency-saliency knapsack","volume-title":"NeurIPS","author":"Shen","year":"2022"},{"key":"ref16","article-title":"Compact language models via pruning and knowledge distillation","volume-title":"NeurIPS","author":"Muralidharan","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01520"},{"key":"ref18","article-title":"Learning both weights and connections for efficient neural network","volume-title":"NeurIPS","author":"Han","year":"2015"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3334614"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IPDPS57955.2024.00064"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICNN.1993.298572"},{"key":"ref23","article-title":"A simple and effective pruning approach for large language models","volume-title":"ICLR","author":"Sun","year":"2024"},{"key":"ref24","article-title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","volume-title":"ICML","author":"Frantar","year":"2023"},{"key":"ref25","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"ICLR","author":"Frankle","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01193"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/786"},{"key":"ref28","article-title":"Learning N: M fine-grained structured sparse neural networks from scratch","volume-title":"ICLR","author":"Zhou","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"ref30","article-title":"Pruning filters for efficient convnets","volume-title":"ICLR","author":"Li","year":"2017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00208"},{"key":"ref32","article-title":"Group fisher pruning for practical network compression","volume-title":"ICML","author":"Liu","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00160"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00269"},{"key":"ref35","article-title":"Residual networks behave like ensembles of relatively shallow networks","volume-title":"NeurIPS","author":"Veit","year":"2016"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2874634"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3059529"},{"key":"ref38","article-title":"Are all layers created equal?","author":"Zhang","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78169-8_28"},{"key":"ref40","article-title":"Layer folding: Neural network depth reduction using activation linearization","volume-title":"ICPR","author":"Santos","year":"2024"},{"key":"ref41","article-title":"Depthshrinker: A new compression paradigm towards boosting real-hardware efficiency of compact neural networks","volume-title":"ICML","author":"Zhang","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01403"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5954"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00478"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00447"},{"key":"ref46","article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"ICLR","author":"Lee","year":"2021"},{"key":"ref47","article-title":"Progressive skeletonization: Trimming more fat from a network at initialization","volume-title":"ICLR","author":"de Jorge","year":"2021"},{"key":"ref48","article-title":"Network pruning that matters: A case study on retraining variants","volume-title":"ICLR","author":"Le","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00029"},{"key":"ref50","article-title":"What makes a good prune? maximal unstructured pruning for maximal cosine similarity","volume-title":"ICLR","author":"Mason-Williams","year":"2024"},{"key":"ref51","article-title":"Pruning everything, everywhere, all at once","volume-title":"IJCNN","author":"do Nascimento","year":"2025"},{"key":"ref52","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume-title":"ICLR","author":"Han","year":"2016"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02216"},{"key":"ref54","article-title":"Improved regularization and robustness for fine-tuning in neural networks","volume-title":"NeurIPS","author":"Li","year":"2021"},{"key":"ref55","article-title":"Once-for-all: Train one network and specialize it for efficient deployment","volume-title":"ICLR","author":"Cai","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i10.29004"},{"key":"ref57","article-title":"SliceGPT: Compress large language models by deleting rows and columns","volume-title":"ICLR","author":"Ashkboos","year":"2024"},{"key":"ref58","article-title":"Llm-pruner: On the structural pruning of large language models","volume-title":"NeurIPS","author":"Ma","year":"2023"},{"key":"ref59","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2305"},{"key":"ref61","doi-asserted-by":"crossref","DOI":"10.20944\/preprints202310.1487.v2","article-title":"Plug-and-play: An efficient post-training pruning method for large language models","volume-title":"ICLR","author":"Zhang","year":"2024"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"}],"event":{"name":"2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)","start":{"date-parts":[[2025,9,30]]},"location":"Salvador, Brazil","end":{"date-parts":[[2025,10,3]]}},"container-title":["2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11223285\/11223275\/11223371.pdf?arnumber=11223371","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T18:42:31Z","timestamp":1763059351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223371\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,30]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/sibgrapi67909.2025.11223371","relation":{},"subject":[],"published":{"date-parts":[[2025,9,30]]}}}