paper-with-me

홈 › Papers

Position: Enough of Scaling LLMs! Lets Focus on Downscaling

2025-05-02 · Ayan Sengupta, Yash Goel, Tanmoy Chakraborty

We challenge the dominant focus on neural scaling laws and advocate for a paradigm shift toward downscaling in the development of large language models (LLMs). While scaling laws have provided critical insights into performance improvements through increasing model and dataset size, we emphasize the significant limitations of this approach, particularly in terms of computational inefficiency, environmental impact, and deployment constraints. To address these challenges, we propose a holistic framework for downscaling LLMs that seeks to maintain performance while drastically reducing resource demands. This paper outlines practical strategies for transitioning away from traditional scaling paradigms, advocating for a more sustainable, efficient, and accessible approach to LLM development.

📄 PDF Abstract BibTeX arXiv:2505.00985

Code (1)

lcs2-iiitd/downscaling 공식 구현

Tasks

Position

Methods 이 논문이 사용한 방법론

Focus 설명 없음

Similar Papers 제목 키워드 기반

Is Haar Enough? Exploring Symlets and Coiflets for Wavelet Convolution Layers

2026-08-18 · Md Rifat Ur Rahman arxiv

Wavelet convolution layers have recently emerged as an efficient mechanism for enlarging receptive fields through multiresolution analysis, but prior work has fixed the wavelet basis to Haar or Daubechies at a chosen dec…

Semantic SegmentationImage Classification

A Unified Framework for Knowledge Transfer in Bidirectional Model Scaling

2026-03-08 · Jianlu Shen, Fu Feng, Jiaze Xu, Yucheng Xie 외 arxiv

Transferring pre-trained knowledge from a source model to a target model of a different architectural size is a key challenge for flexible and efficient model scaling. However, current parameter-space methods treat Small…

Towards New Multiwavelets: Associated Filters and Algorithms. Part I: Theoretical Framework and Investigation of Biomedical Signals, ECG and Coronavirus Cases

2021-03-09 · Malika Jallouli, Makerem Zemni, Anouar Ben Mabrouk, Mohamed Ali Mahjoub

Biosignals are nowadays important subjects for scientific researches from both theory and applications especially with the appearance of new pandemics threatening humanity such as the new Coronavirus. One aim in the pres…

NaViL: Rethinking Scaling Properties of Native Multimodal Large Language Models under Data Constraints

2025-10-09 · Changyao Tian, Hao Li, Gen Luo, Xizhou Zhu 외 arxiv

Compositional training has been the de-facto paradigm in existing Multimodal Large Language Models (MLLMs), where pre-trained vision encoders are connected with pre-trained LLMs through continuous multimodal pre-training…

On The Continuous Steering of the Scale of Tight Wavelet Frames

2015-12-07 · Zsuzsanna Püspöki, John Paul Ward, Daniel Sage, Michael Unser

In analogy with steerable wavelets, we present a general construction of adaptable tight wavelet frames, with an emphasis on scaling operations. In particular, the derived wavelets can be "dilated" by a procedure compara…