Results 251 to 260 of about 114,287 (303)
Some of the next articles are maybe not open access.
Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
AAAI Conference on Artificial IntelligenceRecent progress in Multimodal Large Language Models (MLLMs) often use large image tokens to compensate the visual shortcoming of MLLMs, which not only exhibits obvious redundancy but also greatly exacerbates the already high computation. Token pruning is
Weihao Ye +3 more
semanticscholar +1 more source
Proceedings of the 2010 ACM SIGMOD International Conference on Management of data, 2010
Fast query processing of complex objects, e.g. spatial or uncertain objects, depends on efficient spatial pruning of objects' approximations, which are typically minimum bounding rectangles (MBRs). In this paper, we propose a novel effective and efficient criterion to determine the spatial topology between multi-dimensional rectangles.
Tobias Emrich +4 more
openaire +1 more source
Fast query processing of complex objects, e.g. spatial or uncertain objects, depends on efficient spatial pruning of objects' approximations, which are typically minimum bounding rectangles (MBRs). In this paper, we propose a novel effective and efficient criterion to determine the spatial topology between multi-dimensional rectangles.
Tobias Emrich +4 more
openaire +1 more source
LLM Pruning and Distillation in Practice: The Minitron Approach
arXiv.orgWe present a comprehensive report on compressing the Llama 3.1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation.
Sharath Turuvekere Sreenivas +8 more
semanticscholar +1 more source
Beyond Text-Visual Attention: Exploiting Visual Cues for Effective Token Pruning in VLMs
IEEE International Conference on Computer VisionLarge Vision-Language Models (LVLMs) generally contain significantly more visual tokens than their textual counterparts, resulting in a considerable computational burden.
Qizhe Zhang +8 more
semanticscholar +1 more source
Shortened LLaMA: A Simple Depth Pruning for Large Language Models
arXiv.orgStructured pruning of modern large language models (LLMs) has emerged as a way of decreasing their high computational needs. Width pruning reduces the size of projection weight matrices (e.g., by removing attention heads) while maintaining the number of ...
Bo-Kyeong Kim +6 more
semanticscholar +1 more source
Perplexed by Perplexity: Perplexity-Based Data Pruning With Small Reference Models
International Conference on Learning RepresentationsIn this work, we investigate whether small language models can determine high-quality subsets of large-scale text datasets that improve the performance of larger language models.
Zachary Ankner +5 more
semanticscholar +1 more source
A guide to successful pruning. Pruning shrubs
2014Discusses different pruning techniques for shrubs.
French, Sue (Sue C.) +1 more
openaire +2 more sources
ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
Computer Vision and Pattern RecognitionLarge Vision Language Models (LVLMs) have achieved significant success across multi-modal tasks. However, the computational cost of processing long visual tokens can be prohibitively expensive on resource-limited devices. Previous methods have identified
Xubing Ye +4 more
semanticscholar +1 more source
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models
International Conference on Machine LearningDespite the remarkable capabilities, Large Language Models (LLMs) face deployment challenges due to their extensive size. Pruning methods drop a subset of weights to accelerate, but many of them require retraining, which is prohibitively expensive and ...
Peijie Dong +6 more
semanticscholar +1 more source
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
International Conference on Learning RepresentationsLarge language models (LLMs) have demonstrated outstanding performance in various tasks, such as text summarization, text question-answering, and etc.
Peng Xu +8 more
semanticscholar +1 more source