English
Related papers

Related papers: Knee-Deep in C-RASP: A Transformer Depth Hierarchy

200 papers

Depth completion aims to predict dense depth maps with sparse depth measurements from a depth sensor. Currently, Convolutional Neural Network (CNN) based models are the most popular methods applied to depth completion tasks. However,…

Computer Vision and Pattern Recognition · Computer Science 2024-09-13 Jian Qian , Miao Sun , Ashley Lee , Jie Li , Shenglong Zhuo , Patrick Yin Chiang

Transformers have had a profound impact on the field of artificial intelligence, especially on large language models and their variants. However, as was the case with neural networks, their black-box nature limits trust and deployment in…

Machine Learning · Computer Science 2026-04-13 Abhiram Vellore , Niraj K. Jha

Depth estimation attracts widespread attention in the computer vision community. However, it is still quite difficult to recover an accurate depth map using only one RGB image. We observe a phenomenon that existing methods tend to fail in…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Shuwei Shao , Ran Li , Zhongcai Pei , Zhong Liu , Weihai Chen , Wentao Zhu , Xingming Wu , Baochang Zhang

Recursive processing is considered a hallmark of human linguistic abilities. A recent study evaluated recursive processing in recurrent neural language models (RNN-LMs) and showed that such models perform below chance level on embedded…

Computation and Language · Computer Science 2021-10-15 Yair Lakretz , Théo Desbordes , Dieuwke Hupkes , Stanislas Dehaene

Deep state-space models (SSMs) have gained increasing popularity in sequence modelling. While there are numerous theoretical investigations of shallow SSMs, how the depth of the SSM affects its expressiveness remains a crucial problem. In…

Machine Learning · Computer Science 2025-06-25 Zeyu Bao , Penghao Yu , Haotian Jiang , Qianxiao Li

We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured…

Computation and Language · Computer Science 2019-09-25 Kazuki Irie , Albert Zeyer , Ralf Schlüter , Hermann Ney

We study in this work the importance of depth in convolutional models for text classification, either when character or word inputs are considered. We show on 5 standard text classification and sentiment analysis tasks that deep models…

Computation and Language · Computer Science 2017-07-14 Hoa T. Le , Christophe Cerisara , Alexandre Denis

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer…

Machine Learning · Computer Science 2025-06-05 Peng Wang , Yifu Lu , Yaodong Yu , Druv Pai , Qing Qu , Yi Ma

Deep neural networks are surprisingly efficient at solving practical tasks, but the theory behind this phenomenon is only starting to catch up with the practice. Numerous works show that depth is the key to this efficiency. A certain class…

Machine Learning · Computer Science 2018-02-09 Valentin Khrulkov , Alexander Novikov , Ivan Oseledets

Transformers have proven highly effective across various applications, especially in handling sequential data such as natural languages and time series. However, transformer models often lack clear interpretability, and the success of…

Machine Learning · Computer Science 2025-12-01 Wei Shi , Yuan Cao

Large language models exhibit surprising emergent generalization properties, yet also struggle on many simple reasoning tasks such as arithmetic and parity. This raises the question of if and when Transformer models can learn the true…

Machine Learning · Computer Science 2023-10-25 Hattie Zhou , Arwen Bradley , Etai Littwin , Noam Razin , Omid Saremi , Josh Susskind , Samy Bengio , Preetum Nakkiran

One way to interpret the reasoning power of transformer-based language models is to describe the types of logical rules they can resolve over some input text. Recently, Chiang et al. (2023) showed that finite-precision transformers can be…

Machine Learning · Computer Science 2025-09-12 William Merrill , Ashish Sabharwal

Positional encodings are a core part of transformer-based models, enabling processing of sequential data without recurrence. This paper presents a theoretical framework to analyze how various positional encoding methods, including…

Machine Learning · Computer Science 2025-06-10 Yin Li

The Transformer model has achieved state-of-the-art performance in many sequence modeling tasks. However, how to leverage model capacity with large or variable depths is still an open challenge. We present a probabilistic framework to…

Computation and Language · Computer Science 2020-10-19 Xian Li , Asa Cooper Stickland , Yuqing Tang , Xiang Kong

In spite of their huge success, transformer models remain difficult to scale in depth. In this work, we develop a unified signal propagation theory and provide formulae that govern the moments of the forward and backward signal through the…

Computation and Language · Computer Science 2024-07-19 Akhil Kedia , Mohd Abbas Zaidi , Sushil Khyalia , Jungho Jung , Harshith Goka , Haejun Lee

Accurate depth estimation remains an open problem for robotic manipulation; even state of the art techniques including structured light and LiDAR sensors fail on reflective or transparent surfaces. We address this problem by training a…

Computer Vision and Pattern Recognition · Computer Science 2020-06-17 Ben Goodrich , Alex Kuefler , William D. Richards

Training and using modern neural-network based latent-variable generative models (like Variational Autoencoders) often require simultaneously training a generative direction along with an inferential(encoding) direction, which approximates…

Machine Learning · Computer Science 2021-07-13 Divyansh Pareek , Andrej Risteski

Attention layers, as commonly used in transformers, form the backbone of modern deep learning, yet there is no mathematical description of their benefits and deficiencies as compared with other architectures. In this work we establish both…

Machine Learning · Computer Science 2023-11-17 Clayton Sanford , Daniel Hsu , Matus Telgarsky

Recent research has demonstrated that transformers, particularly linear attention models, implicitly execute gradient-descent-like algorithms on data provided in-context during their forward inference step. However, their capability in…

Machine Learning · Computer Science 2024-10-31 Max Vladymyrov , Johannes von Oswald , Mark Sandler , Rong Ge

Yes, they do. This paper provides the first empirical demonstration that deep convolutional models really need to be both deep and convolutional, even when trained with methods such as distillation that allow small or shallow models of high…