{"total":73,"rows":[{"id":"2509.22622","title":"LongLive: Real-time Interactive Long Video Generation","created":"2025-09-26","cited_by_count":265,"area":null},{"id":"2410.10781","title":"When Attention Sink Emerges in Language Models: An Empirical View","created":"2024-10-14","cited_by_count":208,"area":"inference"},{"id":"2501.04001","title":"Sa2VA: Marrying SAM2 with MLLM for Dense Grounded Understanding of Images and Videos","created":"2025-01-07","cited_by_count":159,"area":"mllm"},{"id":"2410.23775","title":"In-Context LoRA for Diffusion Transformers","created":"2024-10-31","cited_by_count":158,"area":"diffusion"},{"id":"2411.14794","title":"VideoEspresso: A Large-Scale Chain-of-Thought Dataset for Fine-Grained Video Reasoning via Core Frame Selection","created":"2024-11-22","cited_by_count":65,"area":"lr"},{"id":"2507.18634","title":"Captain Cinema: Towards Short Movie Generation","created":"2025-07-24","cited_by_count":48,"area":null},{"id":"2412.00127","title":"Orthus: Autoregressive Interleaved Image-Text Generation with Modality-Specific Heads","created":"2024-11-28","cited_by_count":44,"area":null},{"id":"2503.23512","title":"SCORE: Story Coherence and Retrieval Enhancement for AI Narratives","created":"2025-03-30","cited_by_count":42,"area":null},{"id":"2512.19539","title":"StoryMem: Multi-shot Long Video Storytelling with Memory","created":"2025-12-22","cited_by_count":40,"area":"diffusion"},{"id":"2411.05902","title":"Autoregressive Models in Vision: A Survey","created":"2024-11-08","cited_by_count":39,"area":null},{"id":"2411.18499","title":"OpenING: A Comprehensive Benchmark for Judging Open-ended Interleaved Image-Text Generation","created":"2024-11-27","cited_by_count":31,"area":"mllm"},{"id":"2409.18142","title":"A Survey on Multimodal Benchmarks: In the Era of Large AI Models","created":"2024-09-21","cited_by_count":27,"area":"mllm"},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19,"area":"diffusion"},{"id":"2412.07589","title":"DiffSensei: Bridging Multi-Modal LLMs and Diffusion Models for Customized Manga Generation","created":"2024-12-10","cited_by_count":18,"area":"mllm"},{"id":"2501.06173","title":"VideoAuteur: Towards Long Narrative Video Generation","created":"2025-01-10","cited_by_count":18,"area":null},{"id":"2501.06250","title":"Generative AI for Cel-Animation: A Survey","created":"2025-01-08","cited_by_count":17,"area":null},{"id":"2508.09983","title":"Story2Board: A Training-Free Approach for Expressive Storyboard Generation","created":"2025-08-13","cited_by_count":17,"area":null},{"id":"2504.05782","title":"MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models","created":"2025-04-08","cited_by_count":15,"area":"lr"},{"id":"2410.06244","title":"Story-Iter: A Training-free Iterative Paradigm for Long Story Visualization","created":"2024-10-08","cited_by_count":13,"area":null},{"id":"2503.09344","title":"Unified Dense Prediction of Video Diffusion","created":"2025-03-12","cited_by_count":13,"area":"diffusion"},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12,"area":"mllm"},{"id":"2411.11496","title":"Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models","created":"2024-11-18","cited_by_count":10,"area":"lr"},{"id":"2412.04432","title":"Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation","created":"2024-12-05","cited_by_count":9,"area":"diffusion"},{"id":"2506.03126","title":"AnimeShooter: A Multi-Shot Animation Dataset for Reference-Guided Video Generation","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2601.17737","title":"The Script is All You Need: An Agentic Framework for Long-Horizon Dialogue-to-Cinematic Video Generation","created":"2026-01-25","cited_by_count":8,"area":"agents"},{"id":"2412.11767","title":"IDEA-Bench: How Far are Generative Models from Professional Designing?","created":"2024-12-16","cited_by_count":7,"area":null},{"id":"2504.01014","title":"AnimeGamer: Infinite Anime Life Simulation with Next Game State Prediction","created":"2025-04-01","cited_by_count":7,"area":null},{"id":"2510.22994","title":"SceneDecorator: Towards Scene-Oriented Story Generation with Scene Planning and Scene Consistency","created":"2025-10-27","cited_by_count":7,"area":null},{"id":"2505.18605","title":"Rethinking Causal Mask Attention for Vision-Language Inference","created":"2025-05-24","cited_by_count":6,"area":"lr"},{"id":"2508.08949","title":"Lay2Story: Extending Diffusion Transformers for Layout-Togglable Story Generation","created":"2025-08-12","cited_by_count":6,"area":"diffusion"},{"id":"2408.09333","title":"SkyScript-100M: 1,000,000,000 Pairs of Scripts and Shooting Scripts for Short Drama","created":"2024-08-18","cited_by_count":5,"area":null},{"id":"2505.24862","title":"ViStoryBench: Comprehensive Benchmark Suite for Story Visualization","created":"2025-05-30","cited_by_count":5,"area":null},{"id":"2412.09612","title":"Olympus: A Universal Task Router for Computer Vision Tasks","created":"2024-12-12","cited_by_count":4,"area":"mllm"},{"id":"2412.12571","title":"ChatDiT: A Training-Free Baseline for Task-Agnostic Free-Form Chatting with Diffusion Transformers","created":"2024-12-17","cited_by_count":4,"area":"diffusion"},{"id":"2502.06474","title":"UniMoD: Efficient Unified Multimodal Transformers with Mixture-of-Depths","created":"2025-02-10","cited_by_count":4,"area":"inference"},{"id":"2503.02399","title":"VisAgent: Narrative-Preserving Story Visualization Framework","created":"2025-03-04","cited_by_count":4,"area":null},{"id":"2504.05800","title":"Storybooth: Training-free Multi-Subject Consistency for Improved Visual Storytelling","created":"2025-04-08","cited_by_count":4,"area":null},{"id":"2504.19894","title":"CineVerse: Consistent Keyframe Synthesis for Cinematic Scene Composition","created":"2025-04-28","cited_by_count":4,"area":null},{"id":"2508.18159","title":"SpotEdit: Evaluating Visually-Guided Image Editing Methods","created":"2025-08-25","cited_by_count":4,"area":null},{"id":"2511.07427","title":"DynaKV: Enabling Accurate and Efficient Long-Sequence LLM Decoding on Smartphones","created":"2025-10-20","cited_by_count":4,"area":"inference"},{"id":"2410.04721","title":"ACDC: Autoregressive Coherent Multimodal Generation using Diffusion Correction","created":"2024-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2506.09427","title":"A High-Quality Dataset and Reliable Evaluation for Interleaved Image-Text Generation","created":"2025-06-11","cited_by_count":3,"area":"mllm"},{"id":"2506.12198","title":"ViSTA: Visual Storytelling using Multi-modal Adapters for Text-to-Image Diffusion Models","created":"2025-06-13","cited_by_count":3,"area":"diffusion"},{"id":"2603.18017","title":"Frayed RoPE and Long Inputs: A Geometric Perspective","created":"2026-02-24","cited_by_count":3,"area":null},{"id":"2604.13452","title":"CANVAS: Continuity-Aware Narratives via Visual Agentic Storyboarding","created":"2026-04-15","cited_by_count":3,"area":"agents"},{"id":"2505.16819","title":"Character-Centered Dialogue Generation from Scene-Level Prompts","created":"2025-05-22","cited_by_count":2,"area":null},{"id":"2508.03735","title":"StorySync: Training-Free Subject Consistency in Text-to-Image Generation via Region Harmonization","created":"2025-07-31","cited_by_count":2,"area":"diffusion"},{"id":"2512.23222","title":"Bridging Your Imagination with Audio-Video Generation via a Unified Director","created":"2025-12-29","cited_by_count":2,"area":null},{"id":"2603.06248","title":"Gradient Flow Polarizes Softmax Outputs towards Low-Entropy Solutions","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2603.14790","title":"Mind-of-Director: Multi-modal Agent-Driven Film Previsualization via Collaborative Decision-Making","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.28082","title":"LogiStory: A Logic-Aware Framework for Multi-Image Story Visualization","created":"2026-03-30","cited_by_count":2,"area":null},{"id":"2606.25079","title":"FreeStory: Training-Free Character Consistency for Free-Form Visual Storytelling","created":"2026-06-23","cited_by_count":2,"area":null},{"id":"2507.08396","title":"CoDi: Subject-Consistent and Pose-Diverse Text-to-Image Generation","created":"2025-07-11","cited_by_count":1,"area":null},{"id":"2507.21893","title":"Aether Weaver: Multimodal Affective Narrative Co-Generation with Dynamic Scene Graphs","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2508.16230","title":"FlexMUSE: Multimodal Unification and Semantics Enhancement Framework with Flexible interaction for Creative Writing","created":"2025-08-22","cited_by_count":1,"area":null},{"id":"2509.04446","title":"Plot'n Polish: Zero-shot Story Visualization and Disentangled Editing with Text-to-Image Diffusion Models","created":"2025-09-04","cited_by_count":1,"area":"diffusion"},{"id":"2512.07198","title":"Generating Storytelling Images with Rich Chains-of-Reasoning","created":"2025-12-08","cited_by_count":1,"area":"lr"},{"id":"2602.01303","title":"ReDiStory: Region-Disentangled Diffusion for Consistent Visual Story Generation","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2604.16958","title":"Self-Reasoning Agentic Framework for Narrative Product Grid-Collage Generation","created":"2026-04-18","cited_by_count":1,"area":"agents"},{"id":"2604.17195","title":"DreamShot: Personalized Storyboard Synthesis with Video Diffusion Prior","created":"2026-04-19","cited_by_count":1,"area":"diffusion"},{"id":"2605.08503","title":"NARRA-Gym for Evaluating Interactive Narrative Agents","created":"2026-05-08","cited_by_count":1,"area":"agents"},{"id":"2606.30054","title":"Illuminating Unified Multimodal Model for Free-form Interleaved Text-Image Generation","created":"2026-06-29","cited_by_count":1,"area":null},{"id":"2607.19947","title":"ETPDesigner: Multi-Agent Orchestration for Interactive Multimodal Electronic Theater Program","created":"2026-07-22","cited_by_count":1,"area":"agents"},{"id":"2608.29621","title":"CineForge: Self-Improving Agents for Long-Horizon Video Generation","created":"2026-08-30","cited_by_count":1,"area":"agents"},{"id":"2408.07467","title":"Domain-invariant Representation Learning via Segment Anything Model for Blood Cell Classification","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2506.18900","title":"Audit & Repair: An Agentic Framework for Consistent Story Visualization in Text-to-Image Diffusion Models","created":"2025-06-23","cited_by_count":0,"area":"diffusion"},{"id":"2512.05557","title":"2K-Characters-10K-Stories: A Quality-Gated Stylized Narrative Dataset with Disentangled Control and Sequence Consistency","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2602.02197","title":"Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models","created":"2026-02-02","cited_by_count":0,"area":"mllm"},{"id":"2602.21273","title":"StoryTailor:A Zero-Shot Pipeline for Action-Rich Multi-Subject Visual Narratives","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2604.10557","title":"LLMs Should Incorporate Explicit Mechanisms for Human Empathy","created":"2026-04-12","cited_by_count":0,"area":null},{"id":"2609.37317","title":"What Comes Next? Omni-StoryBench for Evaluating Story-Grounded Omnimodal Generation","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.15555","title":"ELECT: Settling Identity Before Rendering for Scalable Story Visualization","created":"2026-10-11","cited_by_count":0,"area":null},{"id":"2610.17080","title":"Scaling Unified Multimodal Models to Long-Horizon Interleaved Generation","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}