English
Related papers

Related papers: ULTra: Unveiling Latent Token Interpretability in …

200 papers

In meta-learning approaches, it is difficult for a practitioner to make sense of what kind of representations the model employs. Without this ability, it can be difficult to both understand what the model knows as well as to make meaningful…

Machine Learning · Computer Science 2022-04-05 Pedro Sandoval-Segura , Wallace Lawson

This paper presents an unsupervised method to learn a neural network, namely an explainer, to interpret a pre-trained convolutional neural network (CNN), i.e., explaining knowledge representations hidden in middle conv-layers of the CNN.…

Computer Vision and Pattern Recognition · Computer Science 2018-05-22 Quanshi Zhang , Yu Yang , Yuchen Liu , Ying Nian Wu , Song-Chun Zhu

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Computation and Language · Computer Science 2025-02-21 Lukas Stankevičius , Mantas Lukoševičius

Recent advances in interpretability suggest we can project weights and hidden states of transformer-based language models (LMs) to their vocabulary, a transformation that makes them more human interpretable. In this paper, we investigate LM…

Computation and Language · Computer Science 2023-11-27 Shahar Katz , Yonatan Belinkov

The recent vision transformer(i.e.for image classification) learns non-local attentive interaction of different patch tokens. However, prior arts miss learning the cross-scale dependencies of different pixels, the semantic correspondence of…

Computer Vision and Pattern Recognition · Computer Science 2021-06-29 Yuanfeng Ji , Ruimao Zhang , Huijie Wang , Zhen Li , Lingyun Wu , Shaoting Zhang , Ping Luo

Integrating symbolic knowledge and data-driven learning algorithms is a longstanding challenge in Artificial Intelligence. Despite the recognized importance of this task, a notable gap exists due to the discreteness of symbolic…

Artificial Intelligence · Computer Science 2024-05-24 Gaia Saveri , Laura Nenzi , Luca Bortolussi , Jan Křetínský

Transformers have transformed modern machine learning, driving breakthroughs in computer vision, natural language processing, and robotics. At the core of their success lies the attention mechanism, which enables the modeling of global…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Hemanth Saratchandran , Simon Lucey

The integration of visual inputs with large language models (LLMs) has led to remarkable advancements in multi-modal capabilities, giving rise to visual large language models (VLLMs). However, effectively harnessing VLLMs for intricate…

Computer Vision and Pattern Recognition · Computer Science 2023-11-14 Renjie Pi , Lewei Yao , Jiahui Gao , Jipeng Zhang , Tong Zhang

Augmenting large language models (LLMs) with auxiliary tokens has emerged as a promising strategy for enhancing model performance. In this work, we introduce a lightweight method termed latent tokens; these are dummy tokens that may be…

Machine Learning · Computer Science 2025-05-20 Yuchang Sun , Yanxi Chen , Yaliang Li , Bolin Ding

Mechanistic interpretability seeks to understand how Large Language Models (LLMs) represent and process information. Recent approaches based on dictionary learning and transcoders enable representing model computation in terms of sparse,…

This paper proposes a transformer over transformer framework, called Transformer$^2$, to perform neural text segmentation. It consists of two components: bottom-level sentence encoders using pre-trained transformers, and an upper-level…

Computation and Language · Computer Science 2021-10-15 Kelvin Lo , Yuan Jin , Weicong Tan , Ming Liu , Lan Du , Wray Buntine

Transformers have demonstrated strong potential in offline reinforcement learning (RL) by modeling trajectories as sequences of return-to-go, states, and actions. However, existing approaches such as the Decision Transformer(DT) and its…

Machine Learning · Computer Science 2025-10-27 Zhuojing Tian , Yushu Chen

Understanding Transformer-based models has attracted significant attention, as they lie at the heart of recent technological advances across machine learning. While most interpretability methods rely on running models over inputs, recent…

Computation and Language · Computer Science 2023-12-27 Guy Dar , Mor Geva , Ankit Gupta , Jonathan Berant

Adept traffic models are critical to both planning and closed-loop simulation for autonomous vehicles (AV), and key design objectives include accuracy, diverse multimodal behaviors, interpretability, and downstream compatibility. Recently,…

Machine Learning · Computer Science 2023-12-01 Yuxiao Chen , Sander Tonkens , Marco Pavone

Fully Convolutional Neural Networks (FCNNs) with contracting and expanding paths have shown prominence for the majority of medical image segmentation applications since the past decade. In FCNNs, the encoder plays an integral role by…

Image and Video Processing · Electrical Eng. & Systems 2021-10-12 Ali Hatamizadeh , Yucheng Tang , Vishwesh Nath , Dong Yang , Andriy Myronenko , Bennett Landman , Holger Roth , Daguang Xu

Deep neural networks have achieved remarkable performance in various text-based tasks but often lack interpretability, making them less suitable for applications where transparency is critical. To address this, we propose ProtoLens, a novel…

Computation and Language · Computer Science 2024-10-25 Bowen Wei , Ziwei Zhu

Due to their inherent capabilities of capturing non-local dependencies, Transformer neural networks have quickly been established as the paradigmatic architecture for large language models and image processing. Next to these traditional…

Quantum Gases · Physics 2024-08-01 Abhinav Suresh , Henning Schlömer , Baran Hashemi , Annabelle Bohrdt

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a…

Computer Vision and Pattern Recognition · Computer Science 2021-07-06 Suman Saha , Anton Obukhov , Danda Pani Paudel , Menelaos Kanakis , Yuhua Chen , Stamatios Georgoulis , Luc Van Gool

Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the…

Machine Learning · Computer Science 2019-11-13 Yao-Hung Hubert Tsai , Shaojie Bai , Makoto Yamada , Louis-Philippe Morency , Ruslan Salakhutdinov

Pre-trained language models in the past years have shown exponential growth in model parameters and compute time. ELECTRA is a novel approach for improving the compute efficiency of pre-trained language models (e.g. BERT) based on masked…

Computation and Language · Computer Science 2021-10-14 Junmo Kang , Suwon Shin , Jeonghwan Kim , Jaeyoung Jo , Sung-Hyon Myaeng