Capsule Lens: Locating and Tracking Concept Geometry in Model Representations

• URL: http://arxiv.org/abs/2609.05575v1
• Date: Fri, 04 Sep 2026 09:15:04 GMT
• Title: Capsule Lens: Locating and Tracking Concept Geometry in Model Representations
• Abstract summary: We introduce Capsule Lens, a framework that matches the region a concept occupies with a simple, trackable geometric form.<n>On static representations, we demonstrate how to locate concept geometry across various models, and how the span and norm curves uncover important geometric characteristics.<n>On dynamic representations, we present three case studies tracking representation drifts induced by distinct training settings.
• Score: 8.78662595138283
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Understanding how concepts are encoded in the internal representations of machine learning models is a central problem in mechanistic interpretability, essential both for the science of deep learning and for the trustworthy deployment of increasingly capable models. Existing approaches to interpret model representations mainly map representations onto more interpretable spaces and do not directly characterize how concepts occupy representation space; various hypotheses have been proposed, but often lack of rigorous validation and largely focus on static representations. In this work, we introduce Capsule Lens, a framework that matches the region a concept occupies with a simple, trackable geometric form, a capsule, defined by several interpretable parameters, fitted in closed form to each concept's geometry and validated on held-out samples. We apply Capsule Lens in two major settings: static and dynamic representations. On static representations, we demonstrate how to locate concept geometry across various models, and how the span and norm curves uncover important geometric characteristics. On dynamic representations, we present three case studies tracking representation drifts induced by distinct training settings, CLIP pretraining, RL post-training on visual question answering, and RL post-training on mathematical reasoning. These analyses reveal qualitatively different geometric dynamics, ranging from broad network-wide restructuring in CLIP pretraining to localized and concept-specific changes in RL post-training. Our results include findings aligned with existing literature as well as novel observations. We believe Capsule Lens stands as a promising tool for locating, analyzing, and tracking concept geometry in both static and dynamic representations.

Related papers

• Panoramic Scene Analysis: A Survey from Distortion-Aware Engineering to Sphere-Native Foundation Modeling [1.8625021794520016]
  Panoramic images capture the complete visual sphere in a single frame, providing spatial context unattainable by conventional cameras.<n>Yet this completeness comes at a geometric cost: the 2-sphere cannot be faithfully mapped to the plane, and every planar representation introduces distortions that violate the assumptions underlying standard vision architectures.<n>This survey traces the evolution of panoramic scene analysis along a methodological trajectory, from projection-based adaptation, through distortion-aware engineering, to sphere-native modeling and geometry-aware tokenization for foundation models.
  arXiv  Detail & Related papers  (2026-06-26T05:54:38Z)
• PointVG-R: Internalizing Geometric Reasoning in MLLMs for Precise Pointing Localization via Visual Chain of Thought [19.680475189691965]
  Pointing-based visual grounding requires models to precisely locate target objects by deciphering complex spatial relationships between the visual scene and pointing gestures.<n>We propose PointVG-R, a reasoning-guided Multi-modal Large Language Model (MLLM)<n>We design a novel geometric reasoning pipeline that simulates the iterative cognitive process humans employ when interpreting pointing gestures.
  arXiv  Detail & Related papers  (2026-06-23T13:06:51Z)
• Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective [91.23306722968509]
  Generalizable feed-forward 3D reconstruction has witnessed rapid development in recent years.<n>Existing feed-forward approaches share similar high-level architectural patterns.<n>We propose a novel taxonomy centered on model design strategies that are agnostic to the output format.
  arXiv  Detail & Related papers  (2026-04-15T16:07:18Z)
• Shape Happens: Automatic Feature Manifold Discovery in LLMs via Supervised Multi-Dimensional Scaling [43.70541744169649]
  We introduce Supervised Multi-Dimensional Scaling (SMDS), a model-agnostic method to automatically discover feature manifold.<n>We find that different features form various geometric structures such as circles, lines, and clusters.<n>Our findings shed light on the functional role of feature manifold, supporting a model of entity-based reasoning in which LMs encode and transform structured representations.
  arXiv  Detail & Related papers  (2025-10-01T15:30:47Z)
• A Markov Categorical Framework for Language Modeling [9.910562011343009]
  Autoregressive language models achieve remarkable performance, yet a unified theory explaining their internal mechanisms, how training shapes their representations, and enables complex behaviors, remains elusive.<n>We introduce a new analytical framework that models the single-step generation process as a composition of information-processing stages using the language of Markov categories.<n>This work presents a powerful new lens for understanding how information flows through a model and how the training objective shapes its internal geometry.
  arXiv  Detail & Related papers  (2025-07-25T13:14:03Z)
• Geometry Distributions [51.4061133324376]
  We propose a novel geometric data representation that models geometry as distributions. Our approach uses diffusion models with a novel network architecture to learn surface point distributions. We evaluate our representation qualitatively and quantitatively across various object types, demonstrating its effectiveness in achieving high geometric fidelity.
  arXiv  Detail & Related papers  (2024-11-25T04:06:48Z)
• Deep Learning Through A Telescoping Lens: A Simple Model Provides Empirical Insights On Grokking, Gradient Boosting & Beyond [61.18736646013446]
  In pursuit of a deeper understanding of its surprising behaviors, we investigate the utility of a simple yet accurate model of a trained neural network. Across three case studies, we illustrate how it can be applied to derive new empirical insights on a diverse range of prominent phenomena.
  arXiv  Detail & Related papers  (2024-10-31T22:54:34Z)
• On the Emergence of Cross-Task Linearity in the Pretraining-Finetuning Paradigm [47.55215041326702]
  We discover an intriguing linear phenomenon in models that are from a common pretrained checkpoint and finetuned on different tasks, termed as Cross-Task Linearity (CTL) We show that if we linearly interpolate the weights of two finetuned models, the features in the weight-interpolated model are often approximately equal to the linearities of features in two finetuned models at each layer. We conjecture that in the pretraining-finetuning paradigm, neural networks approximately function as linear maps, mapping from the parameter space to the feature space.
  arXiv  Detail & Related papers  (2024-02-06T03:28:36Z)
• Internal Representations of Vision Models Through the Lens of Frames on Data Manifolds [8.67467876089153]
  We present a new approach to studying such representations inspired by the idea of a frame on the tangent bundle of a manifold. Our construction, which we call a neural frame, is formed by assembling a set of vectors representing specific types of perturbations of a data point. Using neural frames, we make observations about the way that models process, layer-by-layer, specific modes of variation within a small neighborhood of a datapoint.
  arXiv  Detail & Related papers  (2022-11-19T01:48:19Z)
• The Geometry of Self-supervised Learning Models and its Impact on Transfer Learning [62.601681746034956]
  Self-supervised learning (SSL) has emerged as a desirable paradigm in computer vision. We propose a data-driven geometric strategy to analyze different SSL models using local neighborhoods in the feature space induced by each.
  arXiv  Detail & Related papers  (2022-09-18T18:15:38Z)
• Towards Self-Supervised Category-Level Object Pose and Size Estimation [121.28537953301951]
  This work presents a self-supervised framework for category-level object pose and size estimation from a single depth image. We leverage the geometric consistency residing in point clouds of the same shape for self-supervision.
  arXiv  Detail & Related papers  (2022-03-06T06:02:30Z)
• Learning Monocular Depth in Dynamic Scenes via Instance-Aware Projection Consistency [114.02182755620784]
  We present an end-to-end joint training framework that explicitly models 6-DoF motion of multiple dynamic objects, ego-motion and depth in a monocular camera setup without supervision. Our framework is shown to outperform the state-of-the-art depth and motion estimation methods.
  arXiv  Detail & Related papers  (2021-02-04T14:26:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.