English
Related papers

Related papers: Relational Rank Geometry in Transformers: Detectin…

200 papers

Under real-analytic assumptions on decoder-only Transformers, recent work shows that the map from discrete prompts to last-token hidden states is generically injective on finite prompt sets. We refine this picture: for each layer $\ell$ we…

Machine Learning · Computer Science 2025-11-20 Mikael von Strauss

Understanding the inner workings of Transformers is crucial for achieving more accurate and efficient predictions. In this work, we analyze the computation performed by Transformers in the layers after the top-1 prediction has become fixed,…

Computation and Language · Computer Science 2024-10-29 Daria Lioubashevski , Tomer Schlank , Gabriel Stanovsky , Ariel Goldstein

Changing the behavior of large language models (LLMs) can be as straightforward as editing the Transformer's residual streams using appropriately constructed "steering vectors." These modifications to internal neural activations, a form of…

Computation and Language · Computer Science 2025-05-20 Jian-Qiao Zhu , Haijiang Yan , Thomas L. Griffiths

Topology is critical in tubular structures such as blood vessels, nerve fibers, and road networks, where connectivity and loop structure govern downstream functional analysis. Vision-Language Models (VLMs) are promising candidates for…

Computer Vision and Pattern Recognition · Computer Science 2026-05-14 Meilong Xu , Qingqiao Hu , Xiaoling Hu , Shahira Abousamra , Xin Yu , Weimin Lyu , Kehan Qi , Dimitris Samaras , Chao Chen

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

Transformer models underpin many recent advances in practical machine learning applications, yet understanding their internal behavior continues to elude researchers. Given the size and complexity of these models, forming a comprehensive…

Transformers underpin modern large language models (LLMs) and are commonly assumed to be behaviorally unstructured at random initialization, with all meaningful preferences emerging only through large-scale training. We challenge this…

Machine Learning · Statistics 2026-02-06 Siquan Li , Yao Tong , Haonan Wang , Tianyang Hu

Conditional computation is a popular strategy to make Transformers more efficient. Existing methods often target individual modules (e.g., mixture-of-experts layers) or skip layers independently of one another. However, interpretability…

Machine Learning · Computer Science 2025-06-27 Tim Lawson , Laurence Aitchison

We seek to understand how the representations of individual tokens and the structure of the learned feature space evolve between layers in deep neural networks under different learning objectives. We focus on the Transformers for our…

Computation and Language · Computer Science 2019-09-05 Elena Voita , Rico Sennrich , Ivan Titov

Understanding the geometric structure of internal representations is a central goal of mechanistic interpretability. Prior work has shown that transformers trained on sequences generated by hidden Markov models encode probabilistic belief…

Machine Learning · Computer Science 2026-04-06 Matthew Levinson

Steering vectors work for some concepts and layers but fail for others, and practitioners have no way to predict which setting applies before running an intervention. We introduce the Linear Accessibility Profile (LAP), a per-layer…

Machine Learning · Computer Science 2026-04-20 Jayadev Billa

Image landmark detection aims to automatically identify the locations of predefined fiducial points. Despite recent success in this field, higher-ordered structural modeling to capture implicit or explicit relationships among anatomical…

Computer Vision and Pattern Recognition · Computer Science 2020-12-09 Weijian Li , Yuhang Lu , Kang Zheng , Haofu Liao , Chihung Lin , Jiebo Luo , Chi-Tung Cheng , Jing Xiao , Le Lu , Chang-Fu Kuo , Shun Miao

When training transformers on graph-structured data, incorporating information about the underlying topology is crucial for good performance. Topological masking, a type of relative position encoding, achieves this by upweighting or…

Spatial functional organization is a hallmark of biological brains: neurons are arranged topographically according to their response properties, at multiple scales. In contrast, representations within most machine learning models lack…

Computation and Language · Computer Science 2025-10-22 Taha Binhuraib , Greta Tuckute , Nicholas Blauch

Existing object detection frameworks are usually built on a single format of object/part representation, i.e., anchor/proposal rectangle boxes in RetinaNet and Faster R-CNN, center points in FCOS and RepPoints, and corner points in…

Computer Vision and Pattern Recognition · Computer Science 2020-10-30 Cheng Chi , Fangyun Wei , Han Hu

Language models can be used to identify relationships between financial entities in text. However, while structured output mechanisms exist, prompting-based pipelines still incur autoregressive decoding costs and decouple graph construction…

Computation and Language · Computer Science 2026-04-14 Yingjie Niu , Changhong Jin , Rian Dolphin , Ruihai Dong

In this paper, we propose and realize a new deep learning architecture for discovering symbolic representations for objects and their relations based on the self-supervised continuous interaction of a manipulator robot with multiple objects…

Robotics · Computer Science 2025-03-07 Alper Ahmetoglu , Batuhan Celik , Erhan Oztop , Emre Ugur

Representation learning on text-attributed graphs (TAGs) integrates structural connectivity with rich textual semantics, enabling applications in diverse domains. Current methods largely rely on contrastive learning to maximize cross-modal…

Graphics · Computer Science 2025-10-15 Heng Zhang , Tianyi Zhang , Yuling Shi , Xiaodong Gu , Yaomin Shen , Zijian Zhang , Yilei Yuan , Hao Zhang , Jin Huang

In order to predict the next token, LLMs must represent semantic and surface-level information about the current word. Previous work identified two types of attention heads that disentangle this information: (i) Concept induction heads,…

Computation and Language · Computer Science 2025-11-25 Sheridan Feucht , Byron Wallace , David Bau

Persistent homology analysis provides means to capture the connectivity structure of data sets in various dimensions. On the mathematical level, by defining a metric between the objects that persistence attaches to data sets, we can…

Machine Learning · Computer Science 2019-06-12 Henri Riihimäki , José Licón-Saláiz