English
Related papers

Related papers: Lambda-Skip Connections: the architectural compone…

200 papers

This thesis investigates two key phenomena in large language models (LLMs): in-context learning (ICL) and model collapse. We study ICL in a linear transformer with tied weights trained on linear regression tasks, and show that minimising…

Artificial Intelligence · Computer Science 2026-01-06 Josef Ott

Contrastive learning has emerged as a powerful method in deep learning, excelling at learning effective representations through contrasting samples from different distributions. However, dimensional collapse, where embeddings converge into…

Machine Learning · Computer Science 2025-12-10 Huanran Li , Manh Nguyen , Daniel Pimentel-Alarcón

Advanced deep neural networks (DNNs), designed by either human or AutoML algorithms, are growing increasingly complex. Diverse operations are connected by complicated connectivity patterns, e.g., various types of skip connections. Those…

Machine Learning · Computer Science 2022-10-13 Wuyang Chen , Wei Huang , Xinyu Gong , Boris Hanin , Zhangyang Wang

Learning predictive models for unlabeled spatiotemporal data is challenging in part because visual dynamics can be highly entangled in real scenes, making existing approaches prone to overfit partial modes of physical processes while…

Machine Learning · Computer Science 2021-10-14 Zhiyu Yao , Yunbo Wang , Haixu Wu , Jianmin Wang , Mingsheng Long

The recent empirical success of Mamba and other selective state space models (SSMs) has renewed interest in non-attention architectures for sequence modeling, yet their theoretical foundations remain underexplored. We present a first-step…

Machine Learning · Computer Science 2026-02-16 Mugunthan Shandirasegaran , Hongkang Li , Songyang Zhang , Meng Wang , Shuai Zhang

Recent advances in foundation models have led to a promising trend of developing large recommendation models to leverage vast amounts of available data. Still, mainstream models remain embarrassingly small in size and na\"ive enlarging does…

Machine Learning · Computer Science 2024-06-07 Xingzhuo Guo , Junwei Pan , Ximei Wang , Baixu Chen , Jie Jiang , Mingsheng Long

The success of Large Language Models (LLMs) hinges on the stable training of deep Transformer architectures. A critical design choice is the placement of normalization layers, leading to a fundamental trade-off: the ``PreNorm'' architecture…

Computation and Language · Computer Science 2026-02-02 Chao Wang , Bei Li , Jiaqi Zhang , Xinyu Liu , Yuchun Fan , Linkun Lyu , Xin Chen , Jingang Wang , Tong Xiao , Peng Pei , Xunliang Cai

Augmenting neural networks with skip connections, as introduced in the so-called ResNet architecture, surprised the community by enabling the training of networks of more than 1,000 layers with significant performance gains. This paper…

Computer Vision and Pattern Recognition · Computer Science 2020-04-24 Alireza Zaeemzadeh , Nazanin Rahnavard , Mubarak Shah

Skip connections in deep networks have improved both segmentation and classification performance by facilitating the training of deeper network architectures, and reducing the risks for vanishing gradients. They equip encoder-decoder-like…

Computer Vision and Pattern Recognition · Computer Science 2018-05-04 Saeid Asgari Taghanaki , Aicha Bentaieb , Anmol Sharma , S. Kevin Zhou , Yefeng Zheng , Bogdan Georgescu , Puneet Sharma , Sasa Grbic , Zhoubing Xu , Dorin Comaniciu , Ghassan Hamarneh

A wide range of graph embedding objectives decompose into two components: one that enforces similarity, attracting the embeddings of nodes that are perceived as similar, and another that enforces dissimilarity, repelling the embeddings of…

Machine Learning · Computer Science 2025-06-03 David Liu , Arjun Seshadri , Tina Eliassi-Rad , Johan Ugander

Transformers are widely used across data modalities, and yet the principles distilled from text models often transfer imperfectly to models trained to other modalities. In this paper, we analyze Transformers through the lens of rank…

Over past few years afterward the birth of ResNet, skip connection has become the defacto standard for the design of modern architectures due to its widespread adoption, easy optimization and proven performance. Prior work has explained the…

Machine Learning · Computer Science 2023-03-03 Dengsheng Chen , Jie Hu , Wenwen Qiang , Xiaoming Wei , Enhua Wu

Whereas it is believed that techniques such as Adam, batch normalization and, more recently, SeLU nonlinearities "solve" the exploding gradient problem, we show that this is not the case in general and that in a range of popular MLP…

Machine Learning · Computer Science 2018-04-10 George Philipp , Dawn Song , Jaime G. Carbonell

Structured state-space models (SSMs) such as S4, stemming from the seminal work of Gu et al., are gaining popularity as effective approaches for modeling sequential data. Deep SSMs demonstrate outstanding performance across a diverse set of…

Machine Learning · Computer Science 2025-01-07 Nicola Muca Cirone , Antonio Orvieto , Benjamin Walker , Cristopher Salvi , Terry Lyons

Sample-level rankings are increasingly used in data-centric NLP for analysis, filtering, debugging, and curation, yet existing pipelines typically score training examples pointwise and rank them as if they were independent. This assumption…

Information Retrieval · Computer Science 2026-05-05 Xu Zheng , Feiyu Wu , Linhong Wu , Zhuocheng Wang , Hui Li

Time series forecasting is a critical task that provides key information for decision-making. After traditional statistical and machine learning approaches, various fundamental deep learning architectures such as MLPs, CNNs, RNNs, and GNNs…

Machine Learning · Computer Science 2025-05-02 Jongseon Kim , Hyungjoon Kim , HyunGi Kim , Dongjun Lee , Sungroh Yoon

Catastrophic forgetting is a major problem in continual learning, and lots of approaches arise to reduce it. However, most of them are evaluated through task accuracy, which ignores the internal model structure. Recent research suggests…

Machine Learning · Computer Science 2026-03-06 Yunqin Zhu , Jun Jin

In this paper, we introduce the novel concept of densely connected layers into recurrent neural networks. We evaluate our proposed architecture on the Penn Treebank language modeling task. We show that we can obtain similar perplexity…

Computation and Language · Computer Science 2017-07-20 Fréderic Godin , Joni Dambre , Wesley De Neve

With the proliferation of mobile devices and the Internet of Things, deep learning models are increasingly deployed on devices with limited computing resources and memory, and are exposed to the threat of adversarial noise. Learning deep…

Computer Vision and Pattern Recognition · Computer Science 2021-12-30 Xian Wei , Yanhui Huang , Yangyu Xu , Mingsong Chen , Hai Lan , Yuanxiang Li , Zhongfeng Wang , Xuan Tang

We introduce the Probability Navigation Architecture (PNA) framework, which treats neural computation as navigation through a probability manifold governed by thermodynamic principles. We train State Space Models (SSMs) and Transformers…

Machine Learning · Computer Science 2026-03-05 Jay Noon