10 papers
Compressing LLMs with MoP: Mixture of Pruners
Bruno Lopes Yamamoto, Lucas Lauton de Alcantara, Victor Zacarias +7
The high computational demands of Large Language Models (LLMs) motivate methods that reduce parameter count and accelerate inference. In response, model pruning emerges as an effec…
Layer-wise LoRA fine-tuning: a similarity metric approach
Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara +5
Pre-training Large Language Models (LLMs) on web-scale datasets becomes fundamental for advancing general-purpose AI. In contrast, enhancing their predictive performance on downstr…
Technical Report on Text Dataset Distillation
Keith Ando Ogawa, Bruno Lopes Yamamoto, Lucas Lauton de Alcantara +6
In the vision domain, dataset distillation arises as a technique to condense a large dataset into a smaller synthetic one that exhibits a similar result in the training process. Wh…
The Virtues of Brevity: Avoid Overthinking in Parallel Test-Time Reasoning
Raul Cavalcante Dinardi, Bruno Yamamoto, Anna Helena Reali Costa +1
Reasoning models represent a significant advance in LLM capabilities, particularly for complex reasoning tasks such as mathematics and coding. Previous studies confirm that paralle…
One Period to Rule Them All: Identifying Critical Learning Periods in Deep Networks
Vinicius Yuiti Fukase, Heitor Gama, Barbara Bueno +3
Critical Learning Periods comprehend an important phenomenon involving deep learning, where early epochs play a decisive role in the success of many training recipes, such as data…
Pruning Everything, Everywhere, All at Once
Gustavo Henrique do Nascimento, Ian Pons, Anna Helena Reali Costa +1
Deep learning stands as the modern paradigm for solving cognitive tasks. However, as the problem complexity increases, models grow deeper and computationally prohibitive, hindering…