{"total":34,"rows":[{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2601.08584","title":"Ministral 3","created":"2026-01-13","cited_by_count":114,"area":null},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2502.04328","title":"Ola: Pushing the Frontiers of Omni-Modal Language Model","created":"2025-02-06","cited_by_count":83,"area":null},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2411.03292","title":"Interaction2Code: Benchmarking MLLM-based Interactive Webpage Code Generation from Interactive Prototyping","created":"2024-11-05","cited_by_count":51,"area":null},{"id":"2506.06251","title":"DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation","created":"2025-06-06","cited_by_count":45,"area":null},{"id":"2503.20680","title":"Vision as LoRA","created":"2025-03-26","cited_by_count":37,"area":null},{"id":"2411.02829","title":"CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaboration","created":"2024-11-05","cited_by_count":25,"area":null},{"id":"2503.08507","title":"Referring to Any Person","created":"2025-03-11","cited_by_count":21,"area":null},{"id":"2410.10783","title":"LiveXiv -- A Multi-Modal Live Benchmark Based on Arxiv Papers Content","created":"2024-10-14","cited_by_count":17,"area":null},{"id":"2504.01001","title":"Zero-shot Benchmarking: A Framework for Flexible and Scalable Automatic Evaluation of Language Models","created":"2025-04-01","cited_by_count":14,"area":null},{"id":"2411.17837","title":"OracleSage: Towards Unified Visual-Linguistic Understanding of Oracle Bone Scripts through Cross-Modal Knowledge Fusion","created":"2024-11-26","cited_by_count":10,"area":null},{"id":"2602.08071","title":"ViT-5: Vision Transformers for The Mid-2020s","created":"2026-02-08","cited_by_count":9,"area":null},{"id":"2602.13013","title":"Towards Universal Video MLLMs with Attribute-Structured and Quality-Verified Instructions","created":"2026-02-13","cited_by_count":9,"area":null},{"id":"2502.15462","title":"Game State and Spatio-temporal Action Detection in Soccer using Graph Neural Networks and 3D Convolutional Networks","created":"2025-02-21","cited_by_count":6,"area":null},{"id":"2503.04506","title":"Multi-modal Summarization in Model-Based Engineering: Automotive Software Development Case Study","created":"2025-03-06","cited_by_count":6,"area":null},{"id":"2508.19650","title":"Video-LevelGauge: Investigating Contextual Positional Bias in Large Video Language Models","created":"2025-08-27","cited_by_count":6,"area":null},{"id":"2606.14502","title":"From Chatbot to Digital Colleague: The Paradigm Shift Toward Persistent Autonomous AI","created":"2026-06-12","cited_by_count":6,"area":null},{"id":"2503.16096","title":"MarkushGrapher: Joint Visual and Textual Recognition of Markush Structures","created":"2025-03-20","cited_by_count":5,"area":null},{"id":"2503.18931","title":"Enhancing Vision Foundation Models via Multimodal Continual Pre-Training","created":"2025-03-24","cited_by_count":5,"area":null},{"id":"2505.02867","title":"RESAnything: Attribute Prompting for Arbitrary Referring Segmentation","created":"2025-05-03","cited_by_count":4,"area":null},{"id":"2603.18373","title":"To See or To Please: Uncovering Visual Sycophancy and Split Beliefs in VLMs","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2605.08146","title":"VT-Bench: A Unified Benchmark for Visual-Tabular Multi-Modal Learning","created":"2026-05-03","cited_by_count":3,"area":null},{"id":"2605.31145","title":"FOCUS: Forcing In-Context Object Localization through Visual Support Constraints and Policy Optimization","created":"2026-05-29","cited_by_count":3,"area":null},{"id":"2503.13060","title":"Historic Scripts to Modern Vision: A Novel Dataset and A VLM Framework for Transliteration of Modi Script to Devanagari","created":"2025-03-17","cited_by_count":1,"area":null},{"id":"2607.25857","title":"Shieldstral","created":"2026-07-28","cited_by_count":1,"area":null},{"id":"2503.12206","title":"TLAC: Two-stage LMM Augmented CLIP for Zero-Shot Classification","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2602.13345","title":"BLUEPRINT Rebuilding a Legacy: Multimodal Retrieval for Complex Engineering Drawings and Documents","created":"2026-02-12","cited_by_count":0,"area":null},{"id":"2604.16993","title":"Rule-VLN: Bridging Perception and Compliance via Semantic Reasoning and Geometric Rectification","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2605.10391","title":"Phoenix-VL 1.5 Medium Technical Report","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.21140","title":"A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.16591","title":"FLAT: Resampling Image and Text into 1D Flexible-Length Aligned Transmodal Tokens for Retrieval and Generation","created":"2026-09-15","cited_by_count":0,"area":null},{"id":"2610.08560","title":"Have I Seen Enough? Frozen Video-Language Models Encode Evidence Readiness","created":"2026-10-06","cited_by_count":0,"area":null}],"next_cursor":null}