{"total":54,"rows":[{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"area":null},{"id":"2408.12637","title":"Building and better understanding vision-language models: insights and future directions","created":"2024-08-22","cited_by_count":173,"area":"mllm"},{"id":"2411.07975","title":"JanusFlow: Harmonizing Autoregression and Rectified Flow for Unified Multimodal Understanding and Generation","created":"2024-11-12","cited_by_count":163,"area":"diffusion"},{"id":"2505.02567","title":"Unified Multimodal Understanding and Generation Models: Advances, Challenges, and Opportunities","created":"2025-05-05","cited_by_count":85,"area":null},{"id":"2503.21979","title":"Harmonizing Visual Representations for Unified Multimodal Understanding and Generation","created":"2025-03-27","cited_by_count":74,"area":null},{"id":"2503.20853","title":"Unified Multimodal Discrete Diffusion","created":"2025-03-26","cited_by_count":49,"area":"diffusion"},{"id":"2412.03561","title":"FLAIR: VLM with Fine-grained Language-informed Image Representations","created":"2024-12-04","cited_by_count":48,"area":"mllm"},{"id":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","cited_by_count":41,"area":"diffusion"},{"id":"2509.09680","title":"FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark","created":"2025-09-11","cited_by_count":38,"area":"lr"},{"id":"2503.11579","title":"Vamba: Understanding Hour-Long Videos with Hybrid Mamba-Transformers","created":"2025-03-14","cited_by_count":36,"area":"mllm"},{"id":"2509.04394","title":"Transition Models: Rethinking the Generative Learning Objective","created":"2025-09-04","cited_by_count":34,"area":"diffusion"},{"id":"2511.12609","title":"Uni-MoE-2.0-Omni: Scaling Language-Centric Omnimodal Large Model with Advanced MoE, Training and Data","created":"2025-11-16","cited_by_count":21,"area":"moe"},{"id":"2506.23115","title":"MoCa: Modality-aware Continual Pre-training Makes Better Bidirectional Multimodal Embeddings","created":"2025-06-29","cited_by_count":20,"area":"mllm"},{"id":"2410.14072","title":"Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers","created":"2024-10-17","cited_by_count":19,"area":"mllm"},{"id":"2503.21193","title":"UGen: Unified Autoregressive Multimodal Model with Progressive Vocabulary Learning","created":"2025-03-27","cited_by_count":16,"area":null},{"id":"2410.13925","title":"FiTv2: Scalable and Improved Flexible Vision Transformer for Diffusion Model","created":"2024-10-17","cited_by_count":15,"area":"diffusion"},{"id":"2412.01814","title":"COSMOS: Cross-Modality Self-Distillation for Vision Language Pre-training","created":"2024-12-02","cited_by_count":15,"area":"mllm"},{"id":"2506.20100","title":"MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations","created":"2025-06-25","cited_by_count":13,"area":"lr"},{"id":"2502.02589","title":"COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation","created":"2025-02-04","cited_by_count":12,"area":null},{"id":"2603.09160","title":"RubiCap: Rubric-Guided Reinforcement Learning for Dense Image Captioning","created":"2026-03-10","cited_by_count":9,"area":"mllm"},{"id":"2505.03420","title":"Mitigating Image Captioning Hallucinations in Vision-Language Models","created":"2025-05-06","cited_by_count":7,"area":"mllm"},{"id":"2407.20756","title":"SynthVLM: Towards High-Quality and Efficient Synthesis of Image-Caption Datasets for Vision-Language Models","created":"2024-07-30","cited_by_count":6,"area":"mllm"},{"id":"2503.17482","title":"What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models","created":"2025-03-21","cited_by_count":6,"area":null},{"id":"2506.06727","title":"VisioMath: Benchmarking Figure-based Mathematical Reasoning in LMMs","created":"2025-06-07","cited_by_count":6,"area":"lr"},{"id":"2607.13125","title":"Boogu-Image-0.1: Boosting Open Agentic Multimodal Generation via Understanding under a Minimal Budget","created":"2026-07-14","cited_by_count":6,"area":"agents"},{"id":"2409.03025","title":"No Detail Left Behind: Revisiting Self-Retrieval for Fine-Grained Image Captioning","created":"2024-09-04","cited_by_count":5,"area":null},{"id":"2411.09018","title":"Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions","created":"2024-11-13","cited_by_count":5,"area":"mllm"},{"id":"2505.24424","title":"Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning","created":"2025-05-30","cited_by_count":5,"area":"mllm"},{"id":"2409.15125","title":"Detect, Describe, Discriminate: Moving Beyond VQA for MLLM Evaluation","created":"2024-09-23","cited_by_count":4,"area":"mllm"},{"id":"2502.11753","title":"HintsOfTruth: A Multimodal Checkworthiness Detection Dataset with Real and Synthetic Claims","created":"2025-02-17","cited_by_count":4,"area":null},{"id":"2503.15633","title":"Vision-Speech Models: Teaching Speech Models to Converse about Images","created":"2025-03-19","cited_by_count":4,"area":"mllm"},{"id":"2511.16595","title":"TimeViper: A Hybrid Mamba-Transformer Vision-Language Model for Efficient Long Video Understanding","created":"2025-11-20","cited_by_count":4,"area":"mllm"},{"id":"2510.05532","title":"Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation","created":"2025-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2507.06654","title":"MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2609.36893","title":"Momentum-Coupled Rubric Adaptation for Detailed Image Captioning","created":"2026-09-29","cited_by_count":2,"area":null},{"id":"2504.12316","title":"Data Metabolism: An Efficient Data Design Schema For Vision Language Model","created":"2025-04-10","cited_by_count":1,"area":"mllm"},{"id":"2505.06356","title":"Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2505.22627","title":"Chain-of-Talkers (CoTalk): Fast Human Annotation of Dense Image Captions","created":"2025-05-28","cited_by_count":1,"area":null},{"id":"2507.20077","title":"The Devil is in the EOS: Sequence Training for Detailed Image Captioning","created":"2025-07-26","cited_by_count":1,"area":"mllm"},{"id":"2510.26799","title":"Masked Diffusion Captioning for Visual Feature Learning","created":"2025-10-30","cited_by_count":1,"area":"diffusion"},{"id":"2605.18115","title":"WinTok: A Win-Win Hybrid Tokenizer via Decomposing Visual Understanding and Generation with Transferable Tokens","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2605.28023","title":"VCap: Hypergeometric Rewards for Weak-to-Strong Visual Captioning","created":"2026-05-27","cited_by_count":1,"area":null},{"id":"2606.30124","title":"SciIR: A Large-scale Training Dataset and Benchmark for Scientific Image Reasoning Generation","created":"2026-06-29","cited_by_count":1,"area":"lr"},{"id":"2608.13783","title":"Doomed to Re-Annotate, Forever: The ImageNet Story","created":"2026-08-13","cited_by_count":1,"area":null},{"id":"2505.23078","title":"Document-Level Text Generation with Minimum Bayes Risk Decoding using Optimal Transport","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2508.01008","title":"ROVI: A VLM-LLM Re-Captioned Dataset for Open-Vocabulary Instance-Grounded Text-to-Image Generation","created":"2025-08-01","cited_by_count":0,"area":null},{"id":"2602.23588","title":"Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2603.16944","title":"Omni IIE Bench: Benchmarking the Practical Capabilities of Image Editing Models","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.21728","title":"BEiTScore: Reference-free Image Captioning Evaluation with an Efficient Cross-Encoder Model","created":"2026-05-20","cited_by_count":0,"area":"mllm"},{"id":"2608.00868","title":"MIDAL: A Dataset of Math Image Descriptions for Accessible Learning","created":"2026-08-01","cited_by_count":0,"area":null},{"id":"2608.12532","title":"MASCOT: Model-Aware Submodular Coverage for Composite-Attribute Text-to-Image Retrieval","created":"2026-08-12","cited_by_count":0,"area":"mllm"},{"id":"2609.26375","title":"KwaiMind Technical Report","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.32734","title":"REALIS: A Curated Dataset for Studying the Challenges of AI Image Detection","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2610.16552","title":"Making Language the Low-Rate Code of Vision: Successive Refinement from Words to Pixels","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}