{"total":30,"rows":[{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236,"area":null},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"area":null},{"id":"2403.16407","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","created":"2024-03-25","cited_by_count":40,"area":null},{"id":"2412.05263","title":"Mind the Time: Temporally-Controlled Multi-Event Video Generation","created":"2024-12-06","cited_by_count":40,"area":null},{"id":"2511.15684","title":"Walrus: A Cross-Domain Foundation Model for Continuum Dynamics","created":"2025-11-19","cited_by_count":36,"area":null},{"id":"2403.00522","title":"VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks","created":"2024-03-01","cited_by_count":28,"area":null},{"id":"2410.22655","title":"FlowDCN: Exploring DCN-like Architectures for Fast Image Generation with Arbitrary Resolution","created":"2024-10-30","cited_by_count":16,"area":null},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2505.21501","title":"Vision Transformers with Self-Distilled Registers","created":"2025-05-27","cited_by_count":12,"area":null},{"id":"2505.20288","title":"Hierarchical Masked Autoregressive Models with Low-Resolution Token Pivots","created":"2025-05-26","cited_by_count":8,"area":null},{"id":"2507.21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","created":"2025-07-29","cited_by_count":8,"area":null},{"id":"2509.15185","title":"Understand Before You Generate: Self-Guided Training for Autoregressive Image Generation","created":"2025-09-18","cited_by_count":7,"area":null},{"id":"2602.03227","title":"Spiral RoPE: Rotate Your Rotary Positional Embeddings in the 2D Plane","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2407.08418","title":"PredBench: Benchmarking Spatio-Temporal Prediction across Diverse Disciplines","created":"2024-07-11","cited_by_count":6,"area":null},{"id":"2503.11129","title":"Direction-Aware Diagonal Autoregressive Image Generation","created":"2025-03-14","cited_by_count":5,"area":null},{"id":"2504.06308","title":"Rethinking RoPE: A Mathematical Blueprint for N-dimensional Positional Embedding","created":"2025-04-07","cited_by_count":4,"area":null},{"id":"2505.20535","title":"Rotary Masked Autoencoders are Versatile Learners","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2409.19700","title":"2D-TPE: Two-Dimensional Positional Encoding Enhances Table Understanding for Large Language Models","created":"2024-09-29","cited_by_count":3,"area":null},{"id":"2603.00180","title":"NNiT: Width-Agnostic Neural Network Generation with Structurally Aligned Weight Spaces","created":"2026-02-26","cited_by_count":3,"area":null},{"id":"2510.06295","title":"Efficient High-Resolution Image Editing with Hallucination-Aware Loss and Adaptive Tiling","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2512.04963","title":"GeoPE:A Unified Geometric Positional Embedding for Structured Tensors","created":"2025-12-04","cited_by_count":2,"area":null},{"id":"2605.05331","title":"ViTok-v2: Scaling Native Resolution Auto-Encoders to 5 Billion Parameters","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2509.03973","title":"SAC-MIL: Spatial-Aware Correlated Multiple Instance Learning for Histopathology Whole Slide Image Classification","created":"2025-09-04","cited_by_count":0,"area":null},{"id":"2604.01864","title":"MAR-MAER: Metric-Aware and Ambiguity-Adaptive Autoregressive Image Generation","created":"2026-04-02","cited_by_count":0,"area":null},{"id":"2605.09151","title":"MultiMedVision: Multi-Modal Medical Vision Framework","created":"2026-05-09","cited_by_count":0,"area":null},{"id":"2605.12491","title":"Do Vision Transformers Need All-to-All Attention? Global Communication Through Elastic Learned Cores","created":"2026-05-12","cited_by_count":0,"area":null},{"id":"2605.15908","title":"RaPD: Resolution-Agnostic Pixel Diffusion via Semantics-Enriched Implicit Representations","created":"2026-05-15","cited_by_count":0,"area":null},{"id":"2609.33804","title":"MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.05416","title":"Prism: Dynamic Sparse Attention for Native 2K Joint Video-Audio Generation Model Training","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}