6 papers
SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention
Yuan Cao, Dong Wang
While Transformer architecture excel at modeling long-range dependencies contributing to its widespread adoption in vision tasks the quadratic complexity of softmax-based attention…
EO-1: An Open Unified Embodied Foundation Model for General Robot Control
Delin Qu, Haoming Song, Qizhi Chen +13
The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general purpose embodied intelligent systems. Recent visi…
Physics informed learning of orthogonal features with applications in solving partial differential equations
Qianxing Jia, Dong Wang
The random feature method (RFM) constructs approximation spaces by initializing features from generic distributions, which provides universal approximation properties to solve gene…
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
Forget the Data and Fine-Tuning! Just Fold the Network to Compress
Dong Wang, Haris Å ikiÄ, Lothar Thiele +1
We introduce model folding, a novel data-free model compression technique that merges structurally similar neurons across layers, significantly reducing the model size without the…
Alternately-optimized SNN method for acoustic scattering problem in unbounded domain
Haoming Song, Zhiqiang Sheng, Dong Wang +1
In this paper, we propose a novel machine learning-based method to solve the acoustic scattering problem in unbounded domain. We first employ the Dirichlet-to-Neumann (DtN) operato…