{"total":29,"rows":[{"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":"2507.15852","title":"Advancing Complex Video Object Segmentation via Progressive Concept Construction","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2506.19848","title":"ScaleCap: Inference-Time Scalable Image Captioning via Dual-Modality Debiasing","created":"2025-06-24","cited_by_count":15,"area":null},{"id":"2508.15360","title":"An Empirical Study on How Video-LLMs Answer Video Questions","created":"2025-08-21","cited_by_count":4,"area":null},{"id":"2506.14356","title":"EVA02-AT: Egocentric Video-Language Understanding with Spatial-Temporal Rotary Positional Embeddings and Symmetric Optimization","created":"2025-06-17","cited_by_count":3,"area":null},{"id":"2511.08368","title":"A Circular Argument : Does RoPE need to be Equivariant for Vision?","created":"2025-11-11","cited_by_count":3,"area":null},{"id":"2502.05928","title":"ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2507.09068","title":"Infinite Video Understanding","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2510.15231","title":"Extending Audio Context for Long-Form Understanding in Large Audio-Language Models","created":"2025-10-17","cited_by_count":2,"area":null},{"id":"2512.07525","title":"Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2602.21735","title":"SigVLP: Sigmoid Volume-Language Pre-Training for Self-Supervised CT-Volume Adaptive Representation Learning","created":"2026-02-25","cited_by_count":2,"area":null},{"id":"2603.17651","title":"Anchoring and Rescaling Attention for Semantically Coherent Inbetweening","created":"2026-03-18","cited_by_count":2,"area":null},{"id":"2605.00968","title":"Adaptive 3D-RoPE: Physics-Aligned Rotary Positional Encoding for Wireless Foundation Models","created":"2026-05-01","cited_by_count":2,"area":null},{"id":"2606.11751","title":"AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.12146","title":"nD-RoPE: A Generalized RoPE for n-Dimensional Position Embedding","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2510.10489","title":"Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation","created":"2025-10-12","cited_by_count":1,"area":null},{"id":"2511.10979","title":"PAS: A Training-Free Stabilizer for Temporal Encoding in Video LLMs","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2603.06973","title":"T2SGrid: Temporal-to-Spatial Gridification for Video Temporal Grounding","created":"2026-03-07","cited_by_count":1,"area":null},{"id":"2604.22554","title":"Video Analysis and Generation via a Semantic Progress Function","created":"2026-04-24","cited_by_count":1,"area":null},{"id":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2603.04165","title":"PlaneCycle: Training-Free 2D-to-3D Lifting of Foundation Models Without Adapters","created":"2026-03-04","cited_by_count":0,"area":null},{"id":"2603.25977","title":"Diffusion MRI Transformer with a Diffusion Space Rotary Positional Embedding (D-RoPE)","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2606.27332","title":"RoPEMover: Depth-Aware Object Relocation via Positional Embeddings","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2607.17675","title":"ShotPlan: Cinematic Video Generation with Learnable Planning Token","created":"2026-07-20","cited_by_count":0,"area":null},{"id":"2608.05154","title":"RIG-RoPE: Relation-Stratified Multimodal Attention with Instance-Local Rotary Geometry and Representation-Aware Traversal Coordinates","created":"2026-05-21","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":"2610.10114","title":"Mechanics of Long-Context Hybrid Models Part 1.1: From Hybrid Attention to Hybrid Position","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.13929","title":"Chronos Policy: Learning Robot Policies on Physical Time","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.16337","title":"WorldRoPE: Probabilistic World-Centric Rotary Embedding for Multi-View Attention","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}