{"total":53,"rows":[{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296,"area":null},{"id":"2412.15188","title":"LMFusion: Adapting Pretrained Language Models for Multimodal Generation","created":"2024-12-19","cited_by_count":120,"area":null},{"id":"2409.00088","title":"On-Device Language Models: A Comprehensive Review","created":"2024-08-26","cited_by_count":104,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"area":null},{"id":"2506.03147","title":"UniWorld-V1: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation","created":"2025-06-03","cited_by_count":66,"area":null},{"id":"2406.10729","title":"A Comprehensive Survey of Foundation Models in Medicine","created":"2024-06-15","cited_by_count":56,"area":null},{"id":"2402.05391","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","created":"2024-02-08","cited_by_count":53,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2407.19584","title":"SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain","created":"2024-07-28","cited_by_count":39,"area":null},{"id":"2403.07508","title":"MoAI: Mixture of All Intelligence for Large Language and Vision Models","created":"2024-03-12","cited_by_count":36,"area":null},{"id":"2410.11163","title":"Model Swarms: Collaborative Search to Adapt LLM Experts via Swarm Intelligence","created":"2024-10-15","cited_by_count":27,"area":null},{"id":"2412.15321","title":"Next Patch Prediction for Autoregressive Visual Generation","created":"2024-12-19","cited_by_count":26,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2408.04203","title":"MMRole: A Comprehensive Framework for Developing and Evaluating Multimodal Role-Playing Agents","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2409.04267","title":"An overview of domain-specific foundation model: key technologies, applications and challenges","created":"2024-09-06","cited_by_count":19,"area":null},{"id":"2409.14713","title":"Phantom of Latent for Large Language and Vision Models","created":"2024-09-23","cited_by_count":17,"area":null},{"id":"2506.03320","title":"The Future of Continual Learning in the Era of Foundation Models: Three Key Directions","created":"2025-06-03","cited_by_count":17,"area":null},{"id":"2503.14021","title":"MP-GUI: Modality Perception with MLLMs for GUI Understanding","created":"2025-03-18","cited_by_count":12,"area":null},{"id":"2408.09856","title":"TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition","created":"2024-08-19","cited_by_count":10,"area":null},{"id":"2508.06350","title":"Aligning Effective Tokens with Video Anomaly in Large Language Models","created":"2025-08-08","cited_by_count":8,"area":null},{"id":"2409.01990","title":"Designing Large Foundation Models for Efficient Training and Inference: A Survey","created":"2024-09-03","cited_by_count":7,"area":null},{"id":"2404.06212","title":"OmniFusion Technical Report","created":"2024-04-09","cited_by_count":6,"area":null},{"id":"2503.08120","title":"UniF$^2$ace: A Unified Fine-grained Face Understanding and Generation Model","created":"2025-03-11","cited_by_count":5,"area":null},{"id":"2607.09084","title":"A Survey on the Green Development of Large Models: From Resource-Efficient Architectures to Hardware-Software Co-Design","created":"2026-07-10","cited_by_count":5,"area":null},{"id":"2410.03553","title":"Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs","created":"2024-10-04","cited_by_count":4,"area":null},{"id":"2501.08982","title":"CityLoc: 6DoF Pose Distributional Localization for Text Descriptions in Large-Scale Scenes with Gaussian Representation","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2504.10804","title":"Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability","created":"2025-04-15","cited_by_count":4,"area":null},{"id":"2509.25187","title":"FlashI2V: Fourier-Guided Latent Shifting Prevents Conditional Image Leakage in Image-to-Video Generation","created":"2025-09-29","cited_by_count":4,"area":null},{"id":"2505.15772","title":"MIKU-PAL: An Automated and Standardized Multi-Modal Method for Speech Paralinguistic and Affect Labeling","created":"2025-05-21","cited_by_count":3,"area":null},{"id":"2510.07961","title":"Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement","created":"2025-10-09","cited_by_count":3,"area":null},{"id":"2512.18804","title":"Tempo as the Stable Cue: Hierarchical Mixture of Tempo and Beat Experts for Music to 3D Dance Generation","created":"2025-12-21","cited_by_count":3,"area":null},{"id":"2410.17779","title":"ADEM-VL: Adaptive and Embedded Fusion for Efficient Vision-Language Tuning","created":"2024-10-23","cited_by_count":2,"area":null},{"id":"2506.02882","title":"GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation","created":"2025-06-03","cited_by_count":1,"area":null},{"id":"2603.03564","title":"Modeling Cross-vision Synergy for Unified Large Vision Model","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2603.19296","title":"TTQ: Activation-Aware Test-Time Quantization to Accelerate LLM Inference On The Fly","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2604.18476","title":"SemLT3D: Semantic-Guided Expert Distillation for Camera-only Long-Tailed 3D Object Detection","created":"2026-04-20","cited_by_count":1,"area":null},{"id":"2605.08329","title":"An Efficient Token Compression Framework for Visual Object Tracking","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2405.18669","title":"Zipper: A Multi-Tower Decoder Architecture for Fusing Modalities","created":"2024-05-29","cited_by_count":0,"area":null},{"id":"2501.02527","title":"Vision-Driven Prompt Optimization for Large Language Models in Multimodal Generative Tasks","created":"2025-01-05","cited_by_count":0,"area":null},{"id":"2503.02063","title":"V$^2$Dial: Unification of Video and Visual Dialog via Multimodal Experts","created":"2025-03-03","cited_by_count":0,"area":null},{"id":"2503.09154","title":"SwapAnyone: Consistent and Realistic Video Synthesis for Swapping Any Person into Any Video","created":"2025-03-12","cited_by_count":0,"area":null},{"id":"2505.00275","title":"AdCare-VLM: Towards a Unified and Pre-aligned Latent Representation for Healthcare Video Understanding","created":"2025-05-01","cited_by_count":0,"area":null},{"id":"2508.17364","title":"Condition Weaving Meets Expert Modulation: Towards Universal and Controllable Image Generation","created":"2025-08-24","cited_by_count":0,"area":null},{"id":"2508.19498","title":"UNIFORM: Unifying Knowledge from Large-scale and Diverse Pre-trained Models","created":"2025-08-27","cited_by_count":0,"area":null},{"id":"2510.01004","title":"TextCAM: Explaining Class Activation Map with Text","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2602.10585","title":"Neural Additive Experts: Context-Gated Experts for Controllable Model Additivity","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2603.16936","title":"TDMM-LM: Bridging Facial Understanding and Animation via Language Models","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.16974","title":"Are a Thousand Words Better Than a Single Picture? Beyond Images -- A Framework for Multi-Modal Knowledge Graph Dataset Enrichment","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2605.17907","title":"One Model to Translate Them All: Universal Any-to-Any Translation for Heterogeneous Collaborative Perception","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.20077","title":"The Hidden Evolution of Disguised Visual Context inside the VLM","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.20970","title":"CogniRoute: Learning to Route Social Evidence in Omni-Modal Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2608.30510","title":"Lot Machine: Multimodal Lot Extraction from Auction Catalogs","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.33492","title":"FedMHAR: Federated Multimodal Human Activity Recognition using Multi-Agent Reinforcement Learning","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}