BEW @ ICCV 2025

11 papers

Top Research Directions

The 15 research directions with BEW @ ICCV 2025 papers, ranked by paper count. Share is the fraction of the edition’s papers in the direction.

#DirectionPapersShare
1Hyperbolic Embeddings for Hierarchical Representation Learning327.3%
2Overcoming Euclidean Distortion with Hyperbolic Embeddings218.2%
3Attributing Synthetic Media to Source Models19.1%
4Beyond the Smooth Manifold Hypothesis19.1%
5Computational Overhead in Hyperbolic Deep Learning19.1%
6Controlling Manifold Drift in Guided Generative Models19.1%
7Geometric Inductive Biases for Representation Generalization19.1%
8Gyrovector Space Operations for Deep Learning19.1%
9Hierarchical Part-Whole Structure Modeling19.1%
10Learnable Manifold Curvature in Geometric Deep Learning19.1%
11Open Set Recognition and the Closed World Assumption19.1%
12Representation Learning in Mixed Curvature Product Spaces19.1%
13Robust Synthetic Image Detection Against Post Processing Degradation19.1%
14The Computational Overhead of Non-Euclidean Deep Learning19.1%
15Training Object Detectors with Alternative and Weak Supervision19.1%

Download all directions as CSV

Institutions

Institutions credited by BEW @ ICCV 2025 papers: a paper credits every institution named in its affiliations, once. 15 institutions share 7 credited papers.

#InstitutionPapersShare
1University of Amsterdam 228.6%
2Chennai Mathematical Institute 114.3%
3Indian Institute of Technology Bombay 114.3%
4Indian Institute of Technology Kharagpur 114.3%
5Institute of Informatics and Telematics 114.3%
6Mohamed bin Zayed University of Artificial Intelligence 114.3%
7Sapienza University of Rome 114.3%
8Technion – Israel Institute of Technology 114.3%
9University of British Columbia 114.3%
10University of California San Diego 114.3%
11University of Hong Kong 114.3%
12University of Modena and Reggio Emilia 114.3%
13University of Pisa 114.3%
14University of Southern California 114.3%
15Yale University 114.3%

Download all institutions as CSV

About this data

Papers. BEW @ ICCV 2025 lists 11 papers on Lacuna, duplicate versions counted once; rejected and withdrawn submissions are left out.

Directions. Directions are Lacuna’s clustering of the concept elements extracted from each paper, so a paper can belong to several and direction counts add up to more than the paper count. A direction’s share is its papers divided by the edition’s papers.

Institutions. A paper credits each institution named in its affiliations, resolved to a ROR record, once. 7 of 11 papers (63.6%) credit at least one institution and are the base for institution shares; the rest have no resolved affiliation yet.

Data. Counts come from Lacuna’s data build of 2026-11-22 and change as papers are added. Tables as CSV: directions · institutions. Cite as: Lacuna, “BEW @ ICCV 2025”, https://lacuna.tiptreesystems.com/venue/bew-iccv/2025.

Top Authors

AuthorPapers
Pascal Mettes3
Max van Spengler2
Tejaswi Kasarla2
Abhishek Jha1
Alberto Pepe1
Alessandro Flaborea1
Ana Manzano Rodríguez1
Andrea Fung1
Ang Nan Gu1
Avik Pal1
Biplab Banerjee1
Elisabeth Wetzer1
Fabio Galasso1
Gal Mishne1
Gowreesh Mago1
Guido D'Amely1
Hae Jin Song1
Hooman Vaseli1
Joan Lasenby1
Johan Mylius-Kroken1

Impactful Papers

Papers from BEW @ ICCV 2025 that shaped research clusters.

Influential

Papers

Title
Compositional Entailment Learning for Hyperbolic Vision-Language Model
Flatland and Beyond: Mutual Information Across Geometries
Geometric Inductive Priors in Diffusion-Based Optical Flow Estimation
HAPPI: Hyperbolic Hierarchical Part Prototypes for Image Recognition
HierVision: Standardized and Reproducible Hierarchical Sources for Vision Datasets
Hyperbolic Category Discovery
Hyperbolic Safety-Aware Vision-Language Models
Hyperbolic Uncertainty-Aware Few-Shot Incremental Point Cloud Segmentation
Riemannian-Geometric Fingerprints of Generative Models
Sparse Hyperbolic Convolutional Networks with Enhanced Object Localization via GradCAM Analysis
Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy