{"total":36,"rows":[{"id":"2512.10794","title":"What matters for Representation Alignment: Global Information or Spatial Structure?","created":"2025-12-11","cited_by_count":84,"area":null},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"id":"2605.18324","title":"Improved Baselines with Representation Autoencoders","created":"2026-05-18","cited_by_count":31,"area":null},{"id":"2603.16195","title":"S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight","created":"2026-03-17","cited_by_count":17,"area":null},{"id":"2602.14941","title":"AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories","created":"2026-02-16","cited_by_count":15,"area":null},{"id":"2604.24764","title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","created":"2026-04-27","cited_by_count":11,"area":null},{"id":"2602.06959","title":"CineScene: Implicit 3D as Effective Scene Representation for Cinematic Video Generation","created":"2026-02-06","cited_by_count":7,"area":null},{"id":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2511.22815","title":"Captain Safari: A World Engine with Pose-Aligned 3D Memory","created":"2025-11-28","cited_by_count":5,"area":null},{"id":"2512.07821","title":"WorldReel: 4D Video Generation with Consistent Geometry and Motion Modeling","created":"2025-12-08","cited_by_count":5,"area":null},{"id":"2512.19402","title":"Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2603.26193","title":"MemCam: Memory-Augmented Camera Control for Consistent Video Generation","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2608.26671","title":"RECAP-Forcing: Retaining Content Appearances for Long Video Generation","created":"2026-08-27","cited_by_count":3,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2605.19539","title":"Trust It or Not: Evidential Uncertainty for Feed-Forward 3D Reconstruction with Trust3R","created":"2026-05-19","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":"2605.24962","title":"Tempered Self-Similarity Alignment for Physically Plausible Video Generation","created":"2026-05-24","cited_by_count":1,"area":null},{"id":"2606.10656","title":"Envision4D: Envisioning Visual Futures via Feed-forward 4D Gaussian Splatting for Autonomous Driving","created":"2026-06-09","cited_by_count":1,"area":null},{"id":"2606.13345","title":"JointEdit3D: Feed-Forward 3D Scene Editing in a Unified Latent Space","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2606.27192","title":"LISA: Likelihood Score Alignment for Visual-condition Controllable Generation","created":"2026-06-25","cited_by_count":1,"area":null},{"id":"2608.27529","title":"Revisiting Local Context for Long-Horizon Streaming 3D Reconstruction","created":"2026-08-27","cited_by_count":1,"area":null},{"id":"2603.05506","title":"FaceCam: Portrait Video Camera Control via Scale-Aware Conditioning","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2603.13357","title":"Bi-CamoDiffusion: A Boundary-informed Diffusion Approach for Camouflaged Object Detection","created":"2026-03-09","cited_by_count":0,"area":null},{"id":"2605.30855","title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.04291","title":"A Cookbook of 3D Vision: Data, Learning Paradigms, and Application","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.28581","title":"ROAD: Reciprocal-Objective Alignment of Discriminative Semantics for 3D Shape Generation","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.16863","title":"SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.02847","title":"RoGe: Novel View Synthesis via End-to-End Implicit Reconstruction and Generation","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.03563","title":"FlashRender: Few-Step Generative Rendering via Camera-Controlled Video MeanFlow","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.24981","title":"GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation","created":"2026-09-21","cited_by_count":0,"area":null},{"id":"2609.35023","title":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35734","title":"GeoVerse: World-Consistent Novel View Synthesis in Geometric Latent Space","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.01914","title":"DecomVoxel: Harnessing 3D-Native Priors with Guided In-situ Denoising Optimization for Decompositional Scene Reconstruction","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.06687","title":"ChronoWorld: Camera-Controlled Consistent 4D World Generation via Spatiotemporal Cues and Geometric Reflections","created":"2026-10-05","cited_by_count":0,"area":null}],"next_cursor":null}