{"total":25,"rows":[{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"area":null},{"id":"2603.28480","title":"INSID3: Training-Free In-Context Segmentation with DINOv3","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2511.16301","title":"Upsample Anything: A Simple and Hard to Beat Baseline for Feature Upsampling","created":"2025-11-20","cited_by_count":6,"area":null},{"id":"2511.18452","title":"NAF: Zero-Shot Feature Upsampling via Neighborhood Attention Filtering","created":"2025-11-23","cited_by_count":6,"area":null},{"id":"2603.27222","title":"HD-VGGT: High-Resolution Visual Geometry Transformer","created":"2026-03-28","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2601.17950","title":"UPLiFT: Efficient Pixel-Dense Feature Upsampling with Local Attenders","created":"2026-01-25","cited_by_count":2,"area":null},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2603.27365","title":"Falcon Perception","created":"2026-03-28","cited_by_count":1,"area":null},{"id":"2604.01388","title":"LESV: Language Embedded Sparse Voxel Fusion for Open-Vocabulary 3D Scene Understanding","created":"2026-04-01","cited_by_count":1,"area":null},{"id":"2605.03175","title":"DINO Soars: DINOv3 for Open-Vocabulary Semantic Segmentation of Remote Sensing Imagery","created":"2026-05-04","cited_by_count":1,"area":null},{"id":"2512.16415","title":"CountZES: Counting via Zero-Shot Exemplar Selection","created":"2025-12-18","cited_by_count":0,"area":null},{"id":"2603.05787","title":"Spectral Probing of Feature Upsamplers in 2D-to-3D Scene Reconstruction","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2603.13571","title":"DiveUp: Learning Feature Upsampling from Diverse Vision Foundation Models","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2603.19531","title":"dinov3.seg: Open-Vocabulary Semantic Segmentation with DINOv3","created":"2026-03-19","cited_by_count":0,"area":null},{"id":"2604.02252","title":"SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2604.14582","title":"MapSR: Prompt-Driven Land Cover Map Super-Resolution via Vision Foundation Models","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2604.16758","title":"Frozen Vision Transformers for Dense Prediction on Small Datasets: A Case Study in Arrow Localization","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.17472","title":"Weighted Reverse Convolution for Feature Upsampling","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.14024","title":"ViT-Up: Faithful Feature Upsampling for Vision Transformers","created":"2026-06-12","cited_by_count":0,"area":null},{"id":"2606.20559","title":"UNIEGO: Proxies as Mediators for Unified Egocentric Video Representation Learning","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.22749","title":"RaysUp: Ultra-light Universal Feature Upsampling via Geometry-Aware Ray Representation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2606.23486","title":"From Reconstruction to Decision: A Post-Encoder Plug-in Adapter for Curvilinear Segmentation","created":"2026-06-22","cited_by_count":0,"area":null},{"id":"2609.37986","title":"ORMA: Optimization-based Monocular 4D Reconstruction of Articulated Animals","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.04853","title":"One Tile, Multiple Instances: Rethinking MIL for Sparse Diagnostic Evidence","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}