arXiv:2606. 31119v1 Announce Type: new Abstract: Graphs are commonly visualized in 2D, where humans readily interpret spatial relationships, yet such layouts often distort higher-dimensional structure.
arXiv:2605. 23540v2 Announce Type: replace Abstract: Dimensionality Reduction (DR) methods are widely used to visualize high-dimensional data.
arXiv:2509. 03373v2 Announce Type: replace Abstract: Dimensionality reduction methods such as t-SNE and UMAP are popular methods for visualizing data with a potential (latent) clustered structure.
arXiv:2607. 28324v1 Announce Type: new Abstract: Quality metrics play a crucial role in the proper use of dimensionality reduction projections for visual analysis of high-dimensional data.
arXiv:2607. 08746v1 Announce Type: cross Abstract: While UMAP is widely used for exploring high-dimensional data, typical workflows focus on its lower-dimensional embedding, largely overlooking the rich k-nearest-neighbor (kNN) graph that UMAP constructs internally.
Geometry transformers such as VGGT achieve strong performance by jointly reasoning over multiple views with global attention. However, scaling them to large view collections remains challenging due to the quadratic cost of attention.
arXiv:2607. 08970v1 Announce Type: cross Abstract: Recent benchmarks for VLMs largely assess single- or limited-view perception, leaving untested the core cognitive ability to integrate observations across viewpoints into a coherent, world-centric (allocentric) 3D mental model.
arXiv:2607. 19362v1 Announce Type: new Abstract: Graph RAG mitigates hallucinations and stale knowledge in LLMs, particularly for multi-hop question answering.
arXiv:2502. 06819v2 Announce Type: replace Abstract: This paper presents a framework for generating 3D indoor scenes from text prompts.
arXiv:2605. 09883v2 Announce Type: replace-cross Abstract: As current Multimodal Large Language Models rapidly saturate canonical visual reasoning benchmarks, a key question emerges: do these strong scores genuinely reflect robust visual understanding?
Online 3D scene graph generation builds a persistent, structured representation of a scene by incrementally fusing 2D observations into a global 3D graph. Existing online methods treat this fusion as a fully deterministic pipeline, where we identify three sources of uncertainty that are overlooked: observation, 2D model, and 3D representation.
arXiv:2510. 16311v3 Announce Type: replace Abstract: Graph Contrastive Learning (GCL) has emerged as a powerful tool for extracting consistent representations from graphs, independent of labeled information.
arXiv:2605. 00972v2 Announce Type: replace-cross Abstract: Earth system science is producing increasingly large, high-dimensional datasets from both physics-based and AI-driven models.