{"total":120,"rows":[{"id":"2412.04431","title":"Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis","created":"2024-12-05","cited_by_count":304,"area":null},{"id":"2504.06256","title":"Transfer between Modalities with MetaQueries","created":"2025-04-08","cited_by_count":236,"area":null},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163,"area":null},{"id":"2505.17412","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention","created":"2025-05-23","cited_by_count":110,"area":null},{"id":"2503.21758","title":"Lumina-Image 2.0: A Unified and Efficient Image Generative Framework","created":"2025-03-27","cited_by_count":96,"area":null},{"id":"2506.09350","title":"Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation","created":"2025-06-11","cited_by_count":90,"area":null},{"id":"2506.02161","title":"TIIF-Bench: How Does Your T2I Model Follow Your Instructions?","created":"2025-06-02","cited_by_count":69,"area":null},{"id":"2505.23661","title":"OpenUni: A Simple Baseline for Unified Multimodal Understanding and Generation","created":"2025-05-29","cited_by_count":46,"area":null},{"id":"2503.10270","title":"EEdit: Rethinking the Spatial and Temporal Redundancy for Efficient Image Editing","created":"2025-03-13","cited_by_count":45,"area":null},{"id":"2511.04675","title":"InfinityStar: Unified Spacetime AutoRegressive Modeling for Visual Generation","created":"2025-11-06","cited_by_count":45,"area":null},{"id":"2507.23278","title":"UniLiP: Adapting CLIP for Unified Multimodal Understanding, Generation and Editing","created":"2025-07-31","cited_by_count":44,"area":null},{"id":"2509.16630","title":"Follow-Your-Emoji-Faster: Towards Efficient, Fine-Controllable, and Expressive Freestyle Portrait Animation","created":"2025-09-20","cited_by_count":43,"area":null},{"id":"2509.04548","title":"Skywork UniPic 2.0: Building Kontext Model with Online RL for Unified Multimodal Model","created":"2025-09-04","cited_by_count":41,"area":null},{"id":"2411.06558","title":"Region-Aware Text-to-Image Generation via Hard Binding and Soft Refinement","created":"2024-11-10","cited_by_count":37,"area":null},{"id":"2507.17801","title":"Lumina-mGPT 2.0: Stand-Alone AutoRegressive Image Modeling","created":"2025-07-23","cited_by_count":37,"area":null},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"id":"2506.01799","title":"WorldExplorer: Towards Generating Fully Navigable 3D Scenes","created":"2025-06-02","cited_by_count":26,"area":null},{"id":"2601.02358","title":"VINO: A Unified Visual Generator with Interleaved OmniModal Context","created":"2026-01-05","cited_by_count":26,"area":null},{"id":"2510.10575","title":"UniFlow: A Unified Pixel Flow Tokenizer for Visual Understanding and Generation","created":"2025-10-12","cited_by_count":23,"area":null},{"id":"2506.09995","title":"PlayerOne: Egocentric World Simulator","created":"2025-06-11","cited_by_count":20,"area":null},{"id":"2601.21406","title":"Generation Enhances Understanding in Unified Multimodal Models via Multi-Representation Generation","created":"2026-01-29","cited_by_count":20,"area":null},{"id":"2504.01008","title":"IntrinsiX: High-Quality PBR Generation using Image Priors","created":"2025-04-01","cited_by_count":19,"area":null},{"id":"2504.17789","title":"Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models","created":"2025-04-24","cited_by_count":18,"area":null},{"id":"2510.20661","title":"UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset","created":"2025-10-23","cited_by_count":18,"area":null},{"id":"2512.05150","title":"TwinFlow: Realizing One-step Generation on Large Models with Self-adversarial Flows","created":"2025-12-03","cited_by_count":17,"area":null},{"id":"2410.23144","title":"Public Domain 12M: A Highly Aesthetic Image-Text Dataset with Novel Governance Mechanisms","created":"2024-10-30","cited_by_count":15,"area":null},{"id":"2506.03131","title":"Native-Resolution Image Synthesis","created":"2025-06-03","cited_by_count":15,"area":null},{"id":"2411.13552","title":"REDUCIO! Generating 1K Video within 16 Seconds using Extremely Compressed Motion Latents","created":"2024-11-20","cited_by_count":14,"area":null},{"id":"2504.04903","title":"Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision","created":"2025-04-07","cited_by_count":14,"area":null},{"id":"2509.17609","title":"Audio Super-Resolution with Latent Bridge Models","created":"2025-09-22","cited_by_count":14,"area":null},{"id":"2504.14470","title":"Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2505.02471","title":"Ming-Lite-Uni: Advancements in Unified Architecture for Natural Multimodal Interaction","created":"2025-05-05","cited_by_count":13,"area":null},{"id":"2505.18142","title":"TokBench: Evaluating Your Visual Tokenizer before Visual Generation","created":"2025-05-23","cited_by_count":13,"area":null},{"id":"2507.04947","title":"DC-AR: Efficient Masked Autoregressive Image Generation with Deep Compression Hybrid Tokenizer","created":"2025-07-07","cited_by_count":13,"area":null},{"id":"2411.13842","title":"Detecting Human Artifacts from Text-to-Image Models","created":"2024-11-21","cited_by_count":12,"area":null},{"id":"2506.01955","title":"Dual-Process Image Generation","created":"2025-06-02","cited_by_count":12,"area":null},{"id":"2509.21318","title":"SD3.5-Flash: Distribution-Guided Distillation of Generative Flows","created":"2025-09-25","cited_by_count":11,"area":null},{"id":"2502.21318","title":"How far can we go with ImageNet for Text-to-Image generation?","created":"2025-02-28","cited_by_count":10,"area":null},{"id":"2506.08210","title":"A Comprehensive Study of Decoder-Only LLMs for Text-to-Image Generation","created":"2025-06-09","cited_by_count":10,"area":null},{"id":"2601.22076","title":"Where Do the Joules Go? Diagnosing Inference Energy Consumption","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2504.19595","title":"WILD: a new in-the-Wild Image Linkage Dataset for synthetic image attribution","created":"2025-04-28","cited_by_count":9,"area":null},{"id":"2506.18729","title":"MuseControlLite: Multifunctional Music Generation with Lightweight Conditioners","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2504.15159","title":"Acquire and then Adapt: Squeezing out Text-to-Image Model for Image Restoration","created":"2025-04-21","cited_by_count":8,"area":null},{"id":"2509.05441","title":"Decoupling High and Low Frequencies for Faithful Image Generation with Fine Details","created":"2025-09-05","cited_by_count":7,"area":null},{"id":"2601.07832","title":"MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head","created":"2026-01-12","cited_by_count":7,"area":null},{"id":"2411.08127","title":"TIPO: Text to Image with Text Presampling for Prompt Optimization","created":"2024-11-12","cited_by_count":6,"area":null},{"id":"2505.16915","title":"DetailMaster: Can Your Text-to-Image Model Handle Long Prompts?","created":"2025-05-22","cited_by_count":6,"area":null},{"id":"2505.19297","title":"Alchemist: Turning Public Text-to-Image Data into Generative Gold","created":"2025-05-25","cited_by_count":5,"area":null},{"id":"2602.15031","title":"EditCtrl: Disentangled Local and Global Control for Real-Time Generative Video Editing","created":"2026-02-16","cited_by_count":5,"area":null},{"id":"2606.31451","title":"UniTac: A Unified Multimodal Model for Cross-Sensor Tactile Understanding and Generation","created":"2026-06-30","cited_by_count":5,"area":null},{"id":"2504.01137","title":"Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models","created":"2025-04-01","cited_by_count":4,"area":null},{"id":"2506.03988","title":"RAID: A Dataset for Testing the Adversarial Robustness of AI-Generated Image Detectors","created":"2025-06-04","cited_by_count":4,"area":null},{"id":"2511.18271","title":"Beyond Words and Pixels: A Benchmark for Implicit World Knowledge Reasoning in Generative Models","created":"2025-11-23","cited_by_count":4,"area":null},{"id":"2603.25319","title":"MACRO: Advancing Multi-Reference Image Generation with Structured Long-Context Data","created":"2026-03-26","cited_by_count":4,"area":null},{"id":"2506.06962","title":"AR-RAG: Autoregressive Retrieval Augmentation for Image Generation","created":"2025-06-08","cited_by_count":3,"area":null},{"id":"2507.22100","title":"Trade-offs in Image Generation: How Do Different Dimensions Interact?","created":"2025-07-29","cited_by_count":3,"area":null},{"id":"2509.12817","title":"SAGA: Selective Adaptive Gating for Efficient and Expressive Linear Attention","created":"2025-09-16","cited_by_count":3,"area":null},{"id":"2510.20586","title":"GenColorBench: A Color Evaluation Benchmark for Text-to-Image Generation Models","created":"2025-10-23","cited_by_count":3,"area":null},{"id":"2605.05646","title":"MUSE: Resolving Manifold Misalignment in Visual Tokenization via Topological Orthogonality","created":"2026-05-07","cited_by_count":3,"area":null},{"id":"2606.01911","title":"Residual Decoder Adapter: ID-Preserving Tokenizer Adaption for Autoregressive Text Rendering","created":"2026-06-01","cited_by_count":3,"area":null},{"id":"2510.14823","title":"FraQAT: Quantization Aware Training with Fractional bits","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.15015","title":"DeLeaker: Dynamic Inference-Time Reweighting For Semantic Leakage Mitigation in Text-to-Image Models","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2510.25279","title":"Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2511.09139","title":"MACEval: A Multi-Agent Continual Evaluation Network for Large Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2512.13672","title":"Directional Textual Inversion for Personalized Text-to-Image Generation","created":"2025-12-15","cited_by_count":2,"area":null},{"id":"2601.02242","title":"VIBE: Visual Instruction Based Editor","created":"2026-01-05","cited_by_count":2,"area":null},{"id":"2601.04946","title":"Prototypicality Bias Reveals Blindspots in Multimodal Evaluation Metrics","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2603.15433","title":"Real-Time Human Frontal View Synthesis from a Single Image","created":"2026-03-16","cited_by_count":2,"area":null},{"id":"2603.16139","title":"Rethinking UMM Visual Generation: Masked Modeling for Efficient Image-Only Pre-training","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.23463","title":"InverFill: One-Step Inversion for Enhanced Few-Step Diffusion Inpainting","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.27666","title":"Gated Condition Injection without Multimodal Attention: Towards Controllable Linear-Attention Transformers","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2604.12322","title":"Self-Adversarial One Step Generation via Condition Shifting","created":"2026-04-14","cited_by_count":2,"area":null},{"id":"2604.18168","title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","created":"2026-04-20","cited_by_count":2,"area":null},{"id":"2606.14700","title":"RepFusion: Leveraging Multimodal Priors for Denoising in Representation Space","created":"2026-06-12","cited_by_count":2,"area":null},{"id":"2505.14341","title":"Replace in Translation: Boost Concept Alignment in Counterfactual Text-to-Image","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2505.17695","title":"SynRES: Towards Referring Expression Segmentation in the Wild via Synthetic Data","created":"2025-05-23","cited_by_count":1,"area":null},{"id":"2507.21518","title":"ST-GDance: Long-Term and Collision-Free Group Choreography from Music","created":"2025-07-29","cited_by_count":1,"area":null},{"id":"2511.20624","title":"ShapeGen: Towards High-Quality 3D Shape Synthesis","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2512.10669","title":"Learning by Analogy: A Causal Framework for Composition Generalization","created":"2025-12-11","cited_by_count":1,"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":"2602.09843","title":"Kelix Technical Report","created":"2026-02-10","cited_by_count":1,"area":null},{"id":"2602.12128","title":"HLA: Hadamard Linear Attention","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2604.02482","title":"SEDGE: Structural Extrapolated Data Generation","created":"2026-04-02","cited_by_count":1,"area":null},{"id":"2604.06061","title":"PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space","created":"2026-04-03","cited_by_count":1,"area":null},{"id":"2604.22865","title":"MeshLAM: Feed-Forward One-Shot Animatable Textured Mesh Avatar Reconstruction","created":"2026-04-23","cited_by_count":1,"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":"2605.14569","title":"Bridging Brain and Semantics: A Hierarchical Framework for Semantically Enhanced fMRI-to-Video Reconstruction","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2605.20147","title":"PixVerve: Advancing Native UHR Image Generation to 100MP with a Large-Scale High-Quality Dataset","created":"2026-05-19","cited_by_count":1,"area":null},{"id":"2605.24762","title":"4KLSDB: A Large-Scale Dataset for 4K Image Restoration and Generation","created":"2026-05-23","cited_by_count":1,"area":null},{"id":"2607.11199","title":"DynEval: Holistic Evaluations of T2I Generative Models in the Wild","created":"2026-07-13","cited_by_count":1,"area":null},{"id":"2607.19575","title":"VQ-Transplant: Efficient VQ-Module Integration for Pre-trained Visual Tokenizers","created":"2026-07-21","cited_by_count":1,"area":null},{"id":"2608.30129","title":"Efficient and High-Quality Depth Estimation via Pixel-Space Diffusion with Linear Attention","created":"2026-08-31","cited_by_count":1,"area":null},{"id":"2504.09441","title":"Structure-Accurate Medical Image Translation via Dynamic Frequency Balance and Knowledge Guidance","created":"2025-04-13","cited_by_count":0,"area":null},{"id":"2505.20498","title":"ControlTac: Scaling Tactile Data with Physically Controlled Tactile Image Generation","created":"2025-05-26","cited_by_count":0,"area":null},{"id":"2510.08771","title":"LinearSR: Unlocking Linear Attention for Stable and Efficient Image Super-Resolution","created":"2025-10-09","cited_by_count":0,"area":null},{"id":"2511.04260","title":"Proto-LeakNet: Towards Signal-Leak Aware Attribution in Synthetic Human Face Imagery","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2601.06525","title":"Toward Generalizable Deblurring: Leveraging Massive Blur Priors with Linear Attention for Real-World Scenarios","created":"2026-01-10","cited_by_count":0,"area":null},{"id":"2601.22630","title":"LINA: Linear Autoregressive Image Generative Models with Continuous Tokens","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2603.00166","title":"Exploring the AI Obedience: Why is Generating a Pure Color Image Harder than CyberPunk?","created":"2026-02-26","cited_by_count":0,"area":null},{"id":"2603.12126","title":"Hoi3DGen: Generating High-Quality Human-Object-Interactions in 3D","created":"2026-03-12","cited_by_count":0,"area":null}],"next_cursor":"100"}