2026-08-18

12 papers from arXiv

← Back to history

How Sampling Strategy Affects Imbalance Mitigation in LiDAR Segmentation: A Study of Structured vs. Random Point-Based Architectures

Antonis Savva, Christos Kyrkou, Theocharis Theocharides

Class imbalance in LiDAR point clouds poses challenges for semantic segmentation in autonomous navigation and urban mapping. While 2D vision has numerous mitigation techniques, their effectiveness in 3D remains unclear. We benchmark six reweighting schemes and five imbalance-aware losses across three datasets (DALES, S3DIS, STPLS3D) using two architectures (KPConv, RandLA-Net). Inverse-frequency w...

cs.CVPR

Training-Free Reconstruction-Based AI-Generated Image Detectors Are Inherently Vulnerable to Adversarial Examples

Roman Demchenko, Jonas Ricker, Asja Fischer

The impressive visual quality and ubiquity of AI-generated images call for reliable and robust detection methods. Reconstruction-based detectors have emerged as a promising direction for transparent and training-free identification of synthetic images. However, due to their fundamentally different mode of operation (compared to standard, classifier-based methods), little is known about their adver...

cs.CVECCV

Hypergraph-based Multimodal Retrieval-Augmented Generation with Incremental Refinement

Shenao Chen, Yidan Xu, Xiangmin Han, Rundong Xue, Duanpo Wu et al.

Modern Multimodal Retrieval-Augmented Generation (M-RAG) systems are fundamentally limited by the binary connectivity paradigm of traditional simple graphs, which fails to capture the intricate, high-order correlations among heterogeneous entities, such as the N-ary relationships between a visual chart, its scattered textual descriptions, and underlying numerical data. Furthermore, existing refine...

cs.AIACM MM

Unsupervised Learning of Cell Instances with Generative Routing Pyramids

Ziwen Liu, Martin Weigert

Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workflows typically use supervised detection or segmentation followed by feature extraction or classification, which requires manual annotations and treats instance segmentation and cell representation as separate stages. We describe a new unsupervised m...

cs.CVcs.LGq-bio.QMECCV

LAVA: Logic-Aware Validation and Augmentation Framework for Large-Scale Financial Document Auditing

Ruoqi Shu, Xuhui Wang, Isaac Wang, Yanming Mai, Bo Wan

Financial document validation in production, such as payroll auditing, tax compliance, and loan underwriting, demands exceptional accuracy, consistency, and reproducibility under strict enterprise constraints. In practice, documents arrive with heterogeneous layouts and formats, semantically rich and context-dependent content, and embedded business rules that current pipelines struggle to process ...

cs.AIPR

Bounded Semantic Planning and Deterministic Compilation for Reliable Enterprise Text-to-SQL

Yi Ai

Direct text-to-SQL asks a language model to do two jobs: interpret the business question and construct the complete relational query. In enterprise schemas, SQL can execute successfully while using the wrong relationship role or aggregation grain. We study an alternative placement of the stochastic boundary. A multi-turn planner grounds phrases and selects from question-specific governed options; ...

cs.DBcs.AIPR

Cost Scales with Change, Not Corpus Size: Incrementally Maintaining an Evolving Semantic Substrate

Yusuke Takahashi, Kyle Wild, Asako Uraki

Retrieval-augmented and agentic question-answering systems increasingly re-derive the meaning of a corpus at query time. Put plainly, instead of re-deriving what a corpus means on every question, the work is done once when a document arrives and is thereafter merely consulted -- a compiler, not an interpreter, of meaning. An alternative is to compile that meaning once, at ingest time, into a compa...

cs.AIcs.DBcs.IRPR

Automatic Cephalometric Landmark Localization on CBCT-Derived Digitally Reconstructed Radiographs for Skeletal Malocclusion Classification

Benjamin Hou, Konstantinia Almpani, Janice S. Lee, Zhiyong Lu

Manual cephalometric landmark annotation is important for craniofacial assessment but is labor-intensive and difficult to scale. We introduce CephViT, a Vision Transformer-based model for automated 2D lateral cephalometric landmark localization, and evaluate its use in downstream skeletal malocclusion classification. CephViT was trained and benchmarked on a public lateral cephalogram dataset, achi...

cs.CVPR

OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction

Hongbo Gao, Wei Zhang, Zeyu Ni, Dihao Zhu, Ruifeng Li et al.

Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing active 3DGS methods primarily plan viewpoints according to geometric information gain, treating object-induced hidden regions in the same manner as general unexplored space. Under tight frame budgets, such geometry-driven strategies may prioritize global scene cov...

cs.ROcs.CVPR

Towards Real-Time and Adaptable LiDAR Scene Completion

Azhar Hussian, Martin Vossiek, Vasileios Belagiannis

LiDAR scene completion is a key component of 3D perception in autonomous driving, where the scene must be completed in real time to be usable in downstream tasks. Existing approaches typically follow an initialize-and-refine paradigm, in which a coarse initialization of the scene is first constructed, then refined into complete 3D geometry. Generative models are slower because they iteratively ref...

cs.CVECCV

Localized TabICLv2: Scaling Tabular In-Context Learning through k-NN

Beimnet Bekele Guta

Foundational models for tabular data have made significant progress in recent years, with TabICLv2 reporting state-of-the-art performance on several tabular classification tasks. However, full-context tabular ICL still suffers from attention cost that grows with the training-context size, which limits its ability to handle large datasets efficiently. Localized TabICLv2 introduces a method that red...

cs.LGICML

Self-Routed Tensor Adapters for Parameter-Efficient Universal Visual Adaptation

Suraj Yadav

Universal visual representations require adaptation mechanisms that adapt across heterogeneous domains without fragmenting knowledge into domain-specific modules. Parameter-efficient fine-tuning adapts frozen visual foundation models efficiently, but standard low-rank adapters use a fixed subspace for all inputs, which can be restrictive when domains differ in style, background, and semantic conte...

cs.CVcs.LGECCV