paper-with-me

Papers

MoST: Efficient Monarch Sparse Tuning for 3D Representation Learning

2025-03-24 · CVPR 2025 1 · Xu Han, Yuan Tang, Jinfeng Xu, Xianzhi Li

We introduce Monarch Sparse Tuning (MoST), the first reparameterization-based parameter-efficient fine-tuning (PEFT) method tailored for 3D representation learning. Unlike existing adapter-based and prompt-tuning 3D PEFT methods, MoST introduces no additional inference overhead and is compatible with many 3D representation learning backbones. At its core, we present a new family of structured matrices for 3D point clouds, Point Monarch, which can capture local geometric features of irregular points while offering high expressiveness. MoST reparameterizes the dense update weight matrices as our sparse Point Monarch matrices, significantly reducing parameters while retaining strong performance. Experiments on various backbones show that MoST is simple, effective, and highly generalizable. It captures local features in point clouds, achieving state-of-the-art results on multiple benchmarks, e.g., 97.5% acc. on ScanObjectNN (PB_50_RS) and 96.2% on ModelNet40 classification, while it can also combine with other matrix decompositions (e.g., Low-rank, Kronecker) to further reduce parameters.

📄 PDF Abstract BibTeX arXiv:2503.18368

Code (1)

xhanxu/most 공식 구현

Tasks

parameter-efficient fine-tuningRepresentation Learning

Similar Papers 제목 키워드 기반

Monarch: Expressive Structured Matrices for Efficient and Accurate Training

2022-04-01 · Tri Dao, Beidi Chen, Nimit Sohoni, Arjun Desai 외

Large neural networks excel in many domains, but they are expensive to train and fine-tune. A popular approach to reduce their compute or memory requirements is to replace dense weight matrices with structured ones (e.g.…

Language ModelingLanguage ModellingMRI Reconstruction

MonarchRT: Efficient Attention for Real-Time Video Generation

2026-02-12 · Krish Agarwal, Zhuoming Chen, Cheng Luo, Yongqi Chen 외 arxiv

Real-time video generation with Diffusion Transformers is bottlenecked by the quadratic cost of 3D self-attention, especially in real-time regimes that are both few-step and autoregressive, where errors compound across t…

Computational EfficiencyVideo Generation

VMonarch: Efficient Video Diffusion Transformers with Structured Attention

2026-01-29 · Cheng Liang, Haoxian Chen, Liang Hou, Qi Fan 외 arxiv

The quadratic complexity of the attention mechanism severely limits the context scalability of Video Diffusion Transformers (DiTs). We find that the highly sparse spatio-temporal attention patterns exhibited in Video DiT…

MoRe Fine-Tuning with 10x Fewer Parameters

2024-08-30 · Wenxuan Tan, Nicholas Roberts, Tzu-Heng Huang, Jitian Zhao 외

Parameter-efficient fine-tuning (PEFT) techniques have unlocked the potential to cheaply and easily specialize large pretrained models. However, the most prominent approaches, like low-rank adapters (LoRA), depend on heu…

Neural Architecture Searchparameter-efficient fine-tuning

MonarchNet: Differentiating Monarch Butterflies from Butterflies Species with Similar Phenotypes

2022-01-24 · Thomas Y. Chen

In recent years, the monarch butterfly's iconic migration patterns have come under threat from a number of factors, from climate change to pesticide use. To track trends in their populations, scientists as well as citize…