{"total":39,"rows":[{"id":"2505.14683","title":"Emerging Properties in Unified Multimodal Pretraining","created":"2025-05-20","cited_by_count":897,"area":null},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2505.05472","title":"Mogao: An Omni Foundation Model for Interleaved Multi-Modal Generation","created":"2025-05-08","cited_by_count":109,"area":null},{"id":"2509.06945","title":"Interleaving Reasoning for Better Text-to-Image Generation","created":"2025-09-08","cited_by_count":41,"area":null},{"id":"2506.24086","title":"MotionGPT3: Human Motion as a Second Modality","created":"2025-06-30","cited_by_count":37,"area":null},{"id":"2607.08639","title":"Native Video-Action Pretraining for Generalizable Robot Control","created":"2026-07-09","cited_by_count":36,"area":null},{"id":"2601.03193","title":"UniCorn: Towards Self-Improving Unified Multimodal Models through Self-Generated Supervision","created":"2026-01-06","cited_by_count":26,"area":null},{"id":"2604.24763","title":"Tuna-2: Pixel Embeddings Beat Vision Encoders for Multimodal Understanding and Generation","created":"2026-04-27","cited_by_count":18,"area":null},{"id":"2510.03506","title":"OneFlow: Concurrent Mixed-Modal and Interleaved Generation with Edit Flows","created":"2025-10-03","cited_by_count":17,"area":null},{"id":"2510.20888","title":"Video-As-Prompt: Unified Semantic Control for Video Generation","created":"2025-10-23","cited_by_count":14,"area":null},{"id":"2510.04961","title":"SSDD: Single-Step Diffusion Decoder for Efficient Image Tokenization","created":"2025-10-06","cited_by_count":7,"area":null},{"id":"2502.00075","title":"BTS: Harmonizing Specialized Experts into a Generalist LLM","created":"2025-01-31","cited_by_count":6,"area":null},{"id":"2512.10730","title":"IRG-MotionLLM: Interleaving Motion Generation, Assessment and Refinement for Text-to-Motion Generation","created":"2025-12-11","cited_by_count":6,"area":null},{"id":"2606.06194","title":"ActiveMimic: Egocentric Video Pretraining with Active Perception","created":"2026-06-04","cited_by_count":6,"area":null},{"id":"2606.30534","title":"Orca: The World is in Your Mind","created":"2026-06-29","cited_by_count":6,"area":null},{"id":"2602.15772","title":"Understanding vs. Generation: Navigating Optimization Dilemma in Multimodal Models","created":"2026-02-17","cited_by_count":5,"area":null},{"id":"2603.25706","title":"Wan-Weaver: Interleaved Multi-modal Generation via Decoupled Training","created":"2026-03-26","cited_by_count":5,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2512.05103","title":"TV2TV: A Unified Framework for Interleaved Language and Video Generation","created":"2025-12-04","cited_by_count":3,"area":null},{"id":"2605.05781","title":"Steering Visual Generation in Unified Multimodal Models with Understanding Supervision","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2608.05000","title":"Towards Physics of Multimodal Pretraining: Knowledge Flow, Modality Synergy, Early Unification, and Recipes","created":"2026-08-05","cited_by_count":3,"area":null},{"id":"2512.01816","title":"Envision: Benchmarking Unified Understanding & Generation for Causal World Process Insights","created":"2025-12-01","cited_by_count":2,"area":null},{"id":"2601.04339","title":"Unified Text-Image Generation with Weakness-Targeted Post-Training","created":"2026-01-07","cited_by_count":2,"area":null},{"id":"2604.26341","title":"SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness","created":"2026-04-29","cited_by_count":2,"area":null},{"id":"2606.13289","title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","created":"2026-06-11","cited_by_count":2,"area":null},{"id":"2606.29941","title":"Seeing Touch from Motion: A Unified Modality-Aware Visuo-Tactile Policy with Tactile Motion Correlation","created":"2026-06-29","cited_by_count":2,"area":null},{"id":"2609.01607","title":"Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System","created":"2026-09-01","cited_by_count":2,"area":null},{"id":"2601.17673","title":"Uni-RS: A Spatially Faithful Unified Understanding and Generation Model for Remote Sensing","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2606.28133","title":"Translation as a Bridging Action: Transferring Manipulation Skills from Humans to Robots","created":"2026-06-26","cited_by_count":1,"area":null},{"id":"2609.03377","title":"SimpleDesign: A Joint Model for Protein Sequence and Structure Codesign","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2603.09217","title":"TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomy","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2606.29013","title":"Mural: Transferring LLM knowledge to image generation via Mixture-of-Transformers","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2608.17564","title":"Where a New Concept Must Enter: Entry Point Gates Cross-Task Usability in Unified Multimodal Models","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2609.23796","title":"Mira-Scene: Pixel-Aligned Layouts for Generative 3D Scene Reconstruction","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.38485","title":"Beyond Layers: Position-Resolved Gradient Conflict and Position-Aware Modulation for Unified Multimodal Models","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.02388","title":"Octrees as an Explicit 3D Language","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.08726","title":"EgoLAP: Learning from Egocentric Human Data through Language-Action Reasoning","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.20610","title":"Can Learning to Answer Spatial Questions Improve Novel-View Generation?","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}