English
Related papers

Related papers: Disentangling MLP Neuron Weights in Vocabulary Spa…

200 papers

Structured pruning methods designed for Large Language Models (LLMs) generally focus on identifying and removing the least important components to optimize model size. However, in this work, we question this prevalent approach by instead…

Machine Learning · Computer Science 2026-02-26 Neha Verma , Kenton Murray , Kevin Duh

We propose a novel regularization method, called \textit{volumization}, for neural networks. Inspired by physics, we define a physical volume for the weight parameters in neural networks, and we show that this method is an effective way of…

Machine Learning · Computer Science 2020-04-02 Liu Ziyin , Zihao Wang , Makoto Yamada , Masahito Ueda

Position information is essential for language modeling. In softmax transformers, Rotary Position Embeddings (\textit{RoPE}) encode positions through \textit{fixed-angle} rotations, while in linear transformers, order is handled via…

Computation and Language · Computer Science 2026-04-27 Sajad Movahedi , Timur Carstensen , Arshia Afzal , Frank Hutter , Antonio Orvieto , Volkan Cevher

The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical cases, however, choosing the optimal architecture for a…

Machine Learning · Computer Science 2020-09-14 Nicolo Colombo , Yang Gao

Large language models (LLMs) have demonstrated remarkable reasoning capabilities when prompted with strategies such as Chain-of-Thought (CoT). However, these approaches focus on token-level output without considering internal weight…

Computation and Language · Computer Science 2025-04-16 Saif Punjwani , Larry Heck

In large multimodal models (LMMs), the perception of non-language modalities (e.g., visual representations) is usually not on par with the large language models (LLMs)' powerful reasoning capabilities, deterring LMMs' performance on…

Machine Learning · Computer Science 2025-03-04 Zhongyang Li , Ziyue Li , Tianyi Zhou

The advancement of robots, particularly those functioning in complex human-centric environments, relies on control solutions that are driven by machine learning. Understanding how learning-based controllers make decisions is crucial since…

Machine Learning · Computer Science 2023-11-14 Tsun-Hsuan Wang , Wei Xiao , Tim Seyde , Ramin Hasani , Daniela Rus

Large Language Models (LLMs) have recently achieved remarkable progress by leveraging Reinforcement Learning and extended Chain-of-Thought (CoT) techniques. However, the challenge of performing efficient language reasoning--especially…

Computation and Language · Computer Science 2025-06-17 Zhong-Zhi Li , Xiao Liang , Zihao Tang , Lei Ji , Peijie Wang , Haotian Xu , Xing W , Haizhen Huang , Weiwei Deng , Yeyun Gong , Zhijiang Guo , Xiao Liu , Fei Yin , Cheng-Lin Liu

Recent advancements in NLP have resulted in models with specialized strengths, such as processing multimodal inputs or excelling in specific domains. However, real-world tasks, like multimodal translation, often require a combination of…

Computation and Language · Computer Science 2024-11-05 Sai Koneru , Matthias Huck , Miriam Exel , Jan Niehues

Spatial reasoning over text is challenging as the models not only need to extract the direct spatial information from the text but also reason over those and infer implicit spatial relations. Recent studies highlight the struggles even…

Computation and Language · Computer Science 2023-10-26 Roshanak Mirzaee , Parisa Kordjamshidi

Understanding how the human brain progresses from processing simple linguistic inputs to performing high-level reasoning is a fundamental challenge in neuroscience. While modern large language models (LLMs) are increasingly used to model…

Computation and Language · Computer Science 2026-01-27 Linyang He , Tianjun Zhong , Richard Antonello , Gavin Mischler , Micah Goldblum , Nima Mesgarani

Disentangled representation learning (DRL) aims to identify and decompose underlying factors behind observations, thus facilitating data perception and generation. However, current DRL approaches often rely on the unrealistic assumption…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Baao Xie , Qiuyu Chen , Yunnan Wang , Zequn Zhang , Xin Jin , Wenjun Zeng

Finding human-understandable circuits in language models is a central goal of the field of mechanistic interpretability. We train models to have more understandable circuits by constraining most of their weights to be zeros, so that each…

Machine Learning · Computer Science 2025-11-18 Leo Gao , Achyuta Rajaram , Jacob Coxon , Soham V. Govande , Bowen Baker , Dan Mossing

Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which…

Grokking-the phenomenon where validation accuracy of neural networks on modular addition of two integers rises long after training data has been memorized-has been characterized in previous works as producing sinusoidal input weight…

Machine Learning · Computer Science 2026-03-26 Anand Swaroop

The impressive capabilities of Large Language Models (LLMs) have led to various efforts to enable robots to be controlled through natural language instructions, opening exciting possibilities for human-robot interaction The goal is for the…

Robotics · Computer Science 2024-03-19 Seif Ismail , Antonio Arbues , Ryan Cotterell , René Zurbrügg , Carmen Amo Alonso

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Computation and Language · Computer Science 2021-12-22 Junhao Xu , Jianwei Yu , Shoukang Hu , Xunying Liu , Helen Meng

Mechanistic interpretability is concerned with analyzing individual components in a (convolutional) neural network (CNN) and how they form larger circuits representing decision mechanisms. These investigations are challenging since CNNs…

Computer Vision and Pattern Recognition · Computer Science 2025-04-18 Robin Hesse , Jonas Fischer , Simone Schaub-Meyer , Stefan Roth

Mechanistic Interpretability (MI) seeks to explain how neural networks implement their capabilities, but the scale of Large Language Models (LLMs) has limited prior MI work in Machine Translation (MT) to word-level analyses. We study…

Computation and Language · Computer Science 2026-02-05 Théo Lasnier , Armel Zebaze , Djamé Seddah , Rachel Bawden , Benoît Sagot

In this paper, we address task-oriented (or goal-oriented) communications where an encoder at the transmitter learns compressed latent representations of data, which are then transmitted over a wireless channel. At the receiver, a decoder…

Machine Learning · Computer Science 2024-11-18 Yalin E. Sagduyu , Tugba Erpek , Aylin Yener , Sennur Ulukus