{"total":24,"rows":[{"id":"2508.16433","title":"HAMSt3R: Human-Aware Multi-view Stereo 3D Reconstruction","created":"2025-08-22","cited_by_count":15,"area":null},{"id":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2512.17817","title":"Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding","created":"2025-12-19","cited_by_count":10,"area":null},{"id":"2603.22387","title":"Efficient Universal Perception Encoder","created":"2026-03-23","cited_by_count":10,"area":null},{"id":"2512.21331","title":"TICON: A Slide-Level Tile Contextualizer for Histopathology Representation Learning","created":"2025-12-24","cited_by_count":6,"area":null},{"id":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3,"area":null},{"id":"2602.19863","title":"Brewing Stronger Features: Dual-Teacher Distillation for Multispectral Earth Observation","created":"2026-02-23","cited_by_count":2,"area":null},{"id":"2603.22631","title":"CAM3R: Camera-Agnostic Model for 3D Reconstruction","created":"2026-03-23","cited_by_count":2,"area":null},{"id":"2604.11707","title":"Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction","created":"2026-04-13","cited_by_count":1,"area":null},{"id":"2606.21562","title":"Compressing History into Memory: Distilling Transformers into Recurrent Transformers","created":"2026-06-19","cited_by_count":1,"area":null},{"id":"2607.10762","title":"TOLiD: Bridging the Architecture Gap in Vision Foundation Model to LiDAR Pretraining via Token Lifting for Distillation","created":"2026-07-12","cited_by_count":1,"area":null},{"id":"2503.19947","title":"Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2511.12588","title":"Rank-Aware Agglomeration of Foundation Models for Immunohistochemistry Image Cell Counting","created":"2025-11-16","cited_by_count":0,"area":null},{"id":"2511.17750","title":"SPIDER: Spatial Image CorresponDence Estimator for Robust Calibration","created":"2025-11-21","cited_by_count":0,"area":null},{"id":"2604.03814","title":"InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset","created":"2026-04-04","cited_by_count":0,"area":null},{"id":"2604.12935","title":"Task Alignment: A Simple Proxy for Practical Model Merging Across Diverse Vision Tasks","created":"2026-04-14","cited_by_count":0,"area":null},{"id":"2605.00271","title":"REALM: An RGB- and Event-Aligned Latent Manifold for Cross-Modal Perception","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.31597","title":"SOCO: Benchmarking Semantic Object Correspondence in Vision Foundation Models","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2607.15058","title":"SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2608.23850","title":"DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.27226","title":"DINOcular: Self-Supervised Visuospatial Representations","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.36374","title":"OTT3R: Multi-View 3D Reconstruction and Fast Dataset Generation at 1% Compute","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.12574","title":"Scaling Multi-Teacher Distillation for Digital Pathology","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.16409","title":"Recovering from Pose-Selection Failures in Repeated Visual Localization","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}