{"total":65,"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":"2509.20317","title":"SIM-CoT: Supervised Implicit Chain-of-Thought","created":"2025-09-24","cited_by_count":70,"area":"lr"},{"id":"2504.07957","title":"MM-IFEngine: Towards Multimodal Instruction Following","created":"2025-04-10","cited_by_count":42,"area":"mllm"},{"id":"2506.14429","title":"LongLLaDA: Unlocking Long Context Capabilities in Diffusion LLMs","created":"2025-06-17","cited_by_count":40,"area":"diffusion"},{"id":"2509.22647","title":"CapRL: Stimulating Dense Image Caption Capabilities via Reinforcement Learning","created":"2025-09-26","cited_by_count":38,"area":"lr"},{"id":"2506.19225","title":"Video-XL-2: Towards Very Long-Video Understanding Through Task-Aware KV Sparsification","created":"2025-06-24","cited_by_count":37,"area":"mllm"},{"id":"2507.15852","title":"Advancing Complex Video Object Segmentation via Progressive Concept Construction","created":"2025-07-21","cited_by_count":26,"area":null},{"id":"2607.06403","title":"From Foundation to Application: Improving VLA Models in Practice","created":"2026-07-07","cited_by_count":26,"area":"vla"},{"id":"2507.08801","title":"Lumos-1: On Autoregressive Video Generation with Discrete Diffusion from a Unified Model Perspective","created":"2025-07-11","cited_by_count":22,"area":"diffusion"},{"id":"2510.24821","title":"Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation","created":"2025-10-28","cited_by_count":22,"area":"moe"},{"id":"2510.14979","title":"From Pixels to Words -- Towards Native Vision-Language Primitives at Scale","created":"2025-10-16","cited_by_count":18,"area":"mllm"},{"id":"2510.23095","title":"Revisiting Multimodal Positional Encoding in Vision-Language Models","created":"2025-10-27","cited_by_count":16,"area":"mllm"},{"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":"2608.07408","title":"Addressable Memory for Video World Models","created":"2026-08-07","cited_by_count":15,"area":"wm"},{"id":"2505.16416","title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","created":"2025-05-22","cited_by_count":14,"area":"mllm"},{"id":"2510.24693","title":"STAR-Bench: Probing Deep Spatio-Temporal Reasoning as Audio 4D Intelligence","created":"2025-10-28","cited_by_count":11,"area":"lr"},{"id":"2509.22624","title":"SPARK: Synergistic Policy And Reward Co-Evolving Framework","created":"2025-09-26","cited_by_count":10,"area":"mllm"},{"id":"2602.03152","title":"FASA: Frequency-aware Sparse Attention","created":"2026-02-03","cited_by_count":8,"area":"inference"},{"id":"2510.26027","title":"Enhancing Temporal Understanding in Video-LLMs through Stacked Temporal Attention in Vision Encoders","created":"2025-10-29","cited_by_count":6,"area":"mllm"},{"id":"2512.10324","title":"EchoingPixels: Aliasing-Resistant Joint Token Reduction for Audio-Visual LLMs","created":"2025-12-11","cited_by_count":6,"area":"inference"},{"id":"2505.12053","title":"VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption","created":"2025-05-17","cited_by_count":5,"area":"diffusion"},{"id":"2512.08374","title":"The Unseen Bias: How Norm Discrepancy in Pre-Norm MLLMs Leads to Visual Information Loss","created":"2025-12-09","cited_by_count":5,"area":"mllm"},{"id":"2602.16455","title":"Visual Self-Refine: A Pixel-Guided Paradigm for Accurate Chart Parsing","created":"2026-02-18","cited_by_count":5,"area":"mllm"},{"id":"2505.20444","title":"HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models","created":"2025-05-26","cited_by_count":4,"area":"mllm"},{"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":"2512.11438","title":"Flowception: Temporally Expansive Flow Matching for Video Generation","created":"2025-12-12","cited_by_count":2,"area":"diffusion"},{"id":"2602.10551","title":"C^2ROPE: Causal Continuous Rotary Positional Encoding for 3D Large Multimodal-Models Reasoning","created":"2026-02-11","cited_by_count":2,"area":"lr"},{"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":"2605.08560","title":"ZAYA1-VL-8B Technical Report","created":"2026-05-08","cited_by_count":2,"area":"mllm"},{"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":"2506.21184","title":"Task-Aware KV Compression For Cost-Effective Long Video Understanding","created":"2025-06-26","cited_by_count":1,"area":"mllm"},{"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":"2603.10863","title":"Beyond Sequential Distance: Inter-Modal Distance Invariant Position Encoding","created":"2026-03-11","cited_by_count":1,"area":"mllm"},{"id":"2603.24721","title":"Scalable Object Relation Encoding for Better 3D Spatial Reasoning in Large Language Models","created":"2026-03-25","cited_by_count":1,"area":"lr"},{"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":"2512.11399","title":"Minimal Clips, Maximum Salience: Long Video Summarization via Key Moment Extraction","created":"2025-12-12","cited_by_count":0,"area":"mllm"},{"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":"2605.14530","title":"Mitigating Mask Prior Drift and Positional Attention Collapse in Large Diffusion Vision-Language Models","created":"2026-05-14","cited_by_count":0,"area":"mllm"},{"id":"2605.16457","title":"Identifiable Token Correspondence for World Models","created":"2026-05-15","cited_by_count":0,"area":"wm"},{"id":"2606.09250","title":"LiteVSR: Lightweight Adaptation of Frozen Diffusion Transformers for Video Super-Resolution","created":"2026-06-08","cited_by_count":0,"area":"diffusion"},{"id":"2606.19338","title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","created":"2026-06-17","cited_by_count":0,"area":"mllm"},{"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":"2607.19547","title":"ChronoStitch: Training-Free Composition of Visual KV Memories for Long-Horizon Temporal Reasoning","created":"2026-07-21","cited_by_count":0,"area":"lr"},{"id":"2607.20628","title":"RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring","created":"2026-07-22","cited_by_count":0,"area":"diffusion"},{"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":"2608.12780","title":"SCOPE: Subspace Clustering with Online Per-Head Top-K Estimation for Sparse Video Attention","created":"2026-08-13","cited_by_count":0,"area":"diffusion"},{"id":"2609.33804","title":"MinkowskiPE: Minkowski Positional Encoding for Spatiotemporal Perception","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.36781","title":"Aperture: Merge-Consistent Rotary States for Compressed Tokens","created":"2026-09-29","cited_by_count":0,"area":"inference"},{"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}