{"total":73,"rows":[{"id":"2212.07143","title":"Reproducible scaling laws for contrastive language-image learning","created":"2022-12-14","cited_by_count":1173,"area":null},{"id":"2302.10035","title":"Large-scale Multi-Modal Pre-trained Models: A Comprehensive Survey","created":"2023-02-20","cited_by_count":153,"area":null},{"id":"2212.08013","title":"FlexiViT: One Model for All Patch Sizes","created":"2022-12-15","cited_by_count":152,"area":null},{"id":"2309.12314","title":"TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance","created":"2023-09-21","cited_by_count":90,"area":null},{"id":"2401.08092","title":"A Survey of Resource-efficient LLM and Multimodal Foundation Models","created":"2024-01-16","cited_by_count":86,"area":null},{"id":"2209.00099","title":"Efficient Methods for Natural Language Processing: A Survey","created":"2022-08-31","cited_by_count":78,"area":null},{"id":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2504.07951","title":"Scaling Laws for Native Multimodal Models","created":"2025-04-10","cited_by_count":50,"area":null},{"id":"2404.08763","title":"CATS: Contextually-Aware Thresholding for Sparsity in Large Language Models","created":"2024-04-12","cited_by_count":41,"area":null},{"id":"2212.09811","title":"Memory-efficient NLLB-200: Language-specific Expert Pruning of a Massively Multilingual Machine Translation Model","created":"2022-12-19","cited_by_count":36,"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":"2310.20071","title":"FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space","created":"2023-10-30","cited_by_count":33,"area":null},{"id":"2209.15466","title":"Sparsity-Constrained Optimal Transport","created":"2022-09-30","cited_by_count":32,"area":null},{"id":"2307.11471","title":"Robust Visual Question Answering: Datasets, Methods, and Future Challenges","created":"2023-07-21","cited_by_count":23,"area":null},{"id":"2211.11153","title":"Unifying Vision-Language Representation Space with Single-tower Transformer","created":"2022-11-21","cited_by_count":22,"area":null},{"id":"2404.16030","title":"MoDE: CLIP Data Experts via Clustering","created":"2024-04-24","cited_by_count":22,"area":null},{"id":"2409.02877","title":"Configurable Foundation Models: Building LLMs from a Modular Perspective","created":"2024-09-04","cited_by_count":22,"area":null},{"id":"2405.17773","title":"XTrack: Multimodal Training Boosts RGB-X Video Object Trackers","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2211.10411","title":"CITADEL: Conditional Token Interaction via Dynamic Lexical Routing for Efficient and Effective Multi-Vector Retrieval","created":"2022-11-18","cited_by_count":19,"area":null},{"id":"2211.03959","title":"Pretraining in Deep Reinforcement Learning: A Survey","created":"2022-11-08","cited_by_count":18,"area":null},{"id":"2310.10908","title":"Unlocking Emergent Modularity in Large Language Models","created":"2023-10-17","cited_by_count":17,"area":null},{"id":"2502.11986","title":"Selective Task Group Updates for Multi-Task Optimization","created":"2025-02-17","cited_by_count":17,"area":null},{"id":"2403.19638","title":"Siamese Vision Transformers are Scalable Audio-visual Learners","created":"2024-03-28","cited_by_count":14,"area":null},{"id":"2306.09008","title":"Exploring the Application of Large-scale Pre-trained Models on Adverse Weather Removal","created":"2023-06-15","cited_by_count":12,"area":null},{"id":"2309.14580","title":"CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss","created":"2023-09-26","cited_by_count":12,"area":null},{"id":"2402.19119","title":"VIXEN: Visual Text Comparison Network for Image Difference Captioning","created":"2024-02-29","cited_by_count":12,"area":null},{"id":"2301.12860","title":"Massively Scaling Heteroscedastic Classifiers","created":"2023-01-30","cited_by_count":11,"area":null},{"id":"2312.02520","title":"Towards More Unified In-context Visual Understanding","created":"2023-12-05","cited_by_count":10,"area":null},{"id":"2407.15617","title":"Norface: Improving Facial Expression Analysis by Identity Normalization","created":"2024-07-22","cited_by_count":10,"area":null},{"id":"2508.15281","title":"MMQ: Multimodal Mixture-of-Quantization Tokenization for Semantic ID Generation and User Behavioral Adaptation","created":"2025-08-21","cited_by_count":10,"area":null},{"id":"2309.06612","title":"Harmonic-NAS: Hardware-Aware Multimodal Neural Architecture Search on Resource-constrained Devices","created":"2023-09-12","cited_by_count":8,"area":null},{"id":"2305.12544","title":"Has It All Been Solved? Open NLP Research Questions Not Solved by Large Language Models","created":"2023-05-21","cited_by_count":7,"area":null},{"id":"2403.08281","title":"Mastering Text, Code and Math Simultaneously via Fusing Highly Specialized Language Models","created":"2024-03-13","cited_by_count":7,"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":"2512.03125","title":"Mitigating Intra- and Inter-modal Forgetting in Continual Learning of Unified Multimodal Models","created":"2025-12-02","cited_by_count":6,"area":null},{"id":"2403.10568","title":"MoPE: Mixture of Prompt Experts for Parameter-Efficient and Scalable Multimodal Fusion","created":"2024-03-14","cited_by_count":5,"area":null},{"id":"2410.10589","title":"MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer","created":"2024-10-14","cited_by_count":5,"area":null},{"id":"2503.23536","title":"A Survey on Unlearnable Data","created":"2025-03-30","cited_by_count":5,"area":null},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2507.07778","title":"Synchronizing Task Behavior: Aligning Multiple Tasks during Test-Time Training","created":"2025-07-10","cited_by_count":5,"area":null},{"id":"2507.20498","title":"Mixture of Length and Pruning Experts for Knowledge Graphs Reasoning","created":"2025-07-28","cited_by_count":5,"area":null},{"id":"2404.03179","title":"UniAV: Unified Audio-Visual Perception for Multi-Task Video Event Localization","created":"2024-04-04","cited_by_count":4,"area":null},{"id":"2507.07485","title":"Resolving Token-Space Gradient Conflicts: Token Space Manipulation for Transformer-Based Multi-Task Learning","created":"2025-07-10","cited_by_count":4,"area":null},{"id":"2403.08477","title":"Unleashing the Power of Meta-tuning for Few-shot Generalization Through Sparse Interpolated Experts","created":"2024-03-13","cited_by_count":3,"area":null},{"id":"2408.14153","title":"Explaining Caption-Image Interactions in CLIP Models with Second-Order Attributions","created":"2024-08-26","cited_by_count":3,"area":null},{"id":"2509.19230","title":"DevFD: Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces","created":"2025-09-23","cited_by_count":3,"area":null},{"id":"2510.12140","title":"Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration","created":"2025-10-14","cited_by_count":3,"area":null},{"id":"2306.05001","title":"COURIER: Contrastive User Intention Reconstruction for Large-Scale Visual Recommendation","created":"2023-06-08","cited_by_count":2,"area":null},{"id":"2405.19950","title":"Multimodal Lego: Model Merging and Fine-Tuning Across Topologies and Modalities in Biomedicine","created":"2024-05-30","cited_by_count":2,"area":null},{"id":"2512.00450","title":"RecruitView: A Multimodal Dataset for Predicting Personality and Interview Performance for Human Resources Applications","created":"2025-11-29","cited_by_count":2,"area":null},{"id":"2303.02484","title":"Multi-Symmetry Ensembles: Improving Diversity and Generalization via Opposing Symmetries","created":"2023-03-04","cited_by_count":1,"area":null},{"id":"2408.00365","title":"Multimodal Fusion and Coherence Modeling for Video Topic Segmentation","created":"2024-08-01","cited_by_count":1,"area":null},{"id":"2512.05515","title":"DashFusion: Dual-stream Alignment with Hierarchical Bottleneck Fusion for Multimodal Sentiment Analysis","created":"2025-12-05","cited_by_count":1,"area":null},{"id":"2602.08331","title":"PACC: Protocol-Aware Cross-Layer Compression for Compact Network Traffic Representation","created":"2026-02-09","cited_by_count":1,"area":null},{"id":"2603.02695","title":"Addressing Missing and Noisy Modalities in One Solution: Unified Modality-Quality Framework for Low-quality Multimodal Data","created":"2026-03-03","cited_by_count":1,"area":null},{"id":"2605.18192","title":"View-Aware Semantic Alignment for Aerial-Ground Person Re-Identification","created":"2026-05-18","cited_by_count":1,"area":null},{"id":"2606.18105","title":"OmniPlan: An Adaptive Framework for Timely and Near-Optimal Network Planning Optimization","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2210.07453","title":"Using Graph Algorithms to Pretrain Graph Completion Transformers","created":"2022-10-14","cited_by_count":0,"area":null},{"id":"2305.07167","title":"OneCAD: One Classifier for All image Datasets using multimodal learning","created":"2023-05-11","cited_by_count":0,"area":null},{"id":"2311.12077","title":"Balancing Efficiency and Quality: MoEISR for Arbitrary-Scale Image Super-Resolution","created":"2023-11-20","cited_by_count":0,"area":null},{"id":"2312.03734","title":"Conditional Prompt Tuning for Multimodal Fusion","created":"2023-11-28","cited_by_count":0,"area":null},{"id":"2408.09752","title":"A Unified Framework for Iris Anti-Spoofing: Introducing Iris Anti-Spoofing Cross-Domain-Testing Protocol and Masked-MoE Method","created":"2024-08-19","cited_by_count":0,"area":null},{"id":"2501.07304","title":"Code and Pixels: Multi-Modal Contrastive Pre-training for Enhanced Tabular Data Analysis","created":"2025-01-13","cited_by_count":0,"area":null},{"id":"2502.19677","title":"Towards Differential Handling of Various Blur Regions for Accurate Image Deblurring","created":"2025-02-27","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":"2505.04850","title":"ORXE: Orchestrating Experts for Dynamically Configurable Efficiency","created":"2025-05-07","cited_by_count":0,"area":null},{"id":"2508.04427","title":"Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2601.22573","title":"DELNet: Continuous All-in-One Weather Removal via Dynamic Expert Library","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2602.08309","title":"CAE-AV: Improving Audio-Visual Learning via Cross-modal Interactive Enrichment","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2602.20723","title":"Modality-Guided Mixture of Structured Experts with Entropy-Triggered Routing for Multimodal Recommendation","created":"2026-02-24","cited_by_count":0,"area":null},{"id":"2603.29211","title":"Xuanwu: Evolving General Multimodal Models into an Industrial-Grade Foundation for Content Ecosystems","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2605.19595","title":"A novel YOLO26-MoE optimized by an LLM agent for insulator fault detection considering UAV images","created":"2026-05-19","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}],"next_cursor":null}