{"total":250,"rows":[{"id":"2107.07651","title":"Align before Fuse: Vision and Language Representation Learning with Momentum Distillation","created":"2021-07-16","cited_by_count":1619,"area":null},{"id":"2205.01917","title":"CoCa: Contrastive Captioners are Image-Text Foundation Models","created":"2022-05-04","cited_by_count":1274,"area":null},{"id":"2102.03334","title":"ViLT: Vision-and-Language Transformer Without Convolution or Region Supervision","created":"2021-02-05","cited_by_count":1230,"area":null},{"id":"2102.08981","title":"Conceptual 12M: Pushing Web-Scale Image-Text Pre-Training To Recognize Long-Tail Visual Concepts","created":"2021-02-17","cited_by_count":1216,"area":null},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2402.09353","title":"DoRA: Weight-Decomposed Low-Rank Adaptation","created":"2024-02-14","cited_by_count":758,"area":null},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743,"area":null},{"id":"2208.10442","title":"Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks","created":"2022-08-22","cited_by_count":511,"area":null},{"id":"2102.02779","title":"Unifying Vision-and-Language Tasks via Text Generation","created":"2021-02-04","cited_by_count":412,"area":null},{"id":"2112.06825","title":"VL-Adapter: Parameter-Efficient Transfer Learning for Vision-and-Language Tasks","created":"2021-12-13","cited_by_count":320,"area":null},{"id":"2312.17172","title":"Unified-IO 2: Scaling Autoregressive Multimodal Models with Vision, Language, Audio, and Action","created":"2023-12-28","cited_by_count":302,"area":null},{"id":"2111.02387","title":"An Empirical Study of Training End-to-End Vision-and-Language Transformers","created":"2021-11-03","cited_by_count":271,"area":null},{"id":"2108.04024","title":"Image Retrieval on Real-life Images with Pre-trained Vision-and-Language Models","created":"2021-08-09","cited_by_count":251,"area":null},{"id":"2206.06522","title":"LST: Ladder Side-Tuning for Parameter and Memory Efficient Transfer Learning","created":"2022-06-13","cited_by_count":230,"area":null},{"id":"2109.13238","title":"Visually Grounded Reasoning across Languages and Cultures","created":"2021-09-28","cited_by_count":189,"area":null},{"id":"2205.12005","title":"mPLUG: Effective and Efficient Vision-Language Learning by Cross-modal Skip-connections","created":"2022-05-24","cited_by_count":187,"area":null},{"id":"2111.11431","title":"RedCaps: web-curated image-text data created by the people, for the people","created":"2021-11-22","cited_by_count":180,"area":null},{"id":"2104.08768","title":"Constrained Language Models Yield Few-Shot Semantic Parsers","created":"2021-04-18","cited_by_count":163,"area":null},{"id":"2112.07566","title":"VALSE: A Task-Independent Benchmark for Vision and Language Models Centered on Linguistic Phenomena","created":"2021-12-14","cited_by_count":135,"area":null},{"id":"2403.19651","title":"MagicLens: Self-Supervised Image Retrieval with Open-Ended Instructions","created":"2024-03-28","cited_by_count":119,"area":null},{"id":"2305.11172","title":"ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities","created":"2023-05-18","cited_by_count":118,"area":null},{"id":"2405.17461","title":"EMR-Merging: Tuning-Free High-Performance Model Merging","created":"2024-05-23","cited_by_count":110,"area":null},{"id":"2109.00590","title":"WebQA: Multihop and Multimodal QA","created":"2021-09-01","cited_by_count":109,"area":null},{"id":"2211.09699","title":"PromptCap: Prompt-Guided Task-Aware Image Captioning","created":"2022-11-15","cited_by_count":104,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"area":null},{"id":"2107.12708","title":"QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension","created":"2021-07-27","cited_by_count":91,"area":null},{"id":"2104.05832","title":"SpartQA: : A Textual Question Answering Benchmark for Spatial Reasoning","created":"2021-04-12","cited_by_count":77,"area":null},{"id":"2109.06082","title":"xGQA: Cross-Lingual Visual Question Answering","created":"2021-09-13","cited_by_count":72,"area":null},{"id":"2206.09059","title":"CLiMB: A Continual Learning Benchmark for Vision-and-Language Tasks","created":"2022-06-18","cited_by_count":68,"area":null},{"id":"2308.00675","title":"Tool Documentation Enables Zero-Shot Tool-Usage with Large Language Models","created":"2023-08-01","cited_by_count":68,"area":null},{"id":"2310.04655","title":"VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models","created":"2023-10-07","cited_by_count":68,"area":null},{"id":"2208.02131","title":"Masked Vision and Language Modeling for Multi-modal Representation Learning","created":"2022-08-03","cited_by_count":67,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2107.02331","title":"Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering","created":"2021-07-06","cited_by_count":62,"area":null},{"id":"2206.08358","title":"MixGen: A New Multi-Modal Data Augmentation","created":"2022-06-16","cited_by_count":61,"area":null},{"id":"2308.12305","title":"FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated Learning","created":"2023-08-21","cited_by_count":60,"area":null},{"id":"2109.06860","title":"Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning","created":"2021-09-14","cited_by_count":59,"area":null},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59,"area":null},{"id":"2206.08657","title":"BridgeTower: Building Bridges Between Encoders in Vision-Language Representation Learning","created":"2022-06-17","cited_by_count":56,"area":null},{"id":"2209.09019","title":"LAVIS: A Library for Language-Vision Intelligence","created":"2022-09-15","cited_by_count":55,"area":null},{"id":"2201.11732","title":"IGLUE: A Benchmark for Transfer Learning across Modalities, Tasks, and Languages","created":"2022-01-27","cited_by_count":54,"area":null},{"id":"2301.13741","title":"UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers","created":"2023-01-31","cited_by_count":54,"area":null},{"id":"2403.15452","title":"What Are Tools Anyway? A Survey from the Language Model Perspective","created":"2024-03-18","cited_by_count":54,"area":null},{"id":"2303.05952","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","created":"2023-03-10","cited_by_count":53,"area":null},{"id":"2304.14933","title":"An Empirical Study of Multimodal Model Merging","created":"2023-04-28","cited_by_count":52,"area":null},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2308.14746","title":"CoVR-2: Automatic Data Construction for Composed Video Retrieval","created":"2023-08-28","cited_by_count":52,"area":null},{"id":"2503.13436","title":"Unified Autoregressive Visual Generation and Understanding with Continuous Tokens","created":"2025-03-17","cited_by_count":51,"area":null},{"id":"2306.05392","title":"Modular Visual Question Answering via Code Generation","created":"2023-06-08","cited_by_count":48,"area":null},{"id":"2111.10023","title":"UFO: A UniFied TransfOrmer for Vision-Language Representation Learning","created":"2021-11-19","cited_by_count":46,"area":null},{"id":"2303.09429","title":"Data Roaming and Quality Assessment for Composed Image Retrieval","created":"2023-03-16","cited_by_count":46,"area":null},{"id":"2104.11832","title":"Playing Lottery Tickets with Vision and Language","created":"2021-04-23","cited_by_count":45,"area":null},{"id":"2106.02192","title":"Grounding 'Grounding' in NLP","created":"2021-06-04","cited_by_count":44,"area":null},{"id":"2405.00571","title":"Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval","created":"2024-05-01","cited_by_count":44,"area":null},{"id":"2303.16604","title":"Bi-directional Training for Composed Image Retrieval via Text Prompt Learning","created":"2023-03-29","cited_by_count":43,"area":null},{"id":"2312.10908","title":"CLOVA: A Closed-Loop Visual Assistant with Tool Usage and Update","created":"2023-12-18","cited_by_count":43,"area":null},{"id":"2210.07179","title":"MAPL: Parameter-Efficient Adaptation of Unimodal Pre-Trained Models for Vision-Language Few-Shot Prompting","created":"2022-10-13","cited_by_count":41,"area":null},{"id":"2604.17898","title":"ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval","created":"2026-04-20","cited_by_count":41,"area":null},{"id":"2410.05352","title":"Recent Advances of Multimodal Continual Learning: A Comprehensive Survey","created":"2024-10-07","cited_by_count":39,"area":null},{"id":"2305.16304","title":"Candidate Set Re-ranking for Composed Image Retrieval with Dual Multi-modal Encoder","created":"2023-05-25","cited_by_count":35,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2109.02401","title":"Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization","created":"2021-09-06","cited_by_count":32,"area":null},{"id":"2302.12248","title":"Learning Visual Representations via Language-Guided Sampling","created":"2023-02-23","cited_by_count":32,"area":null},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32,"area":null},{"id":"2512.02792","title":"HUD: Hierarchical Uncertainty-Aware Disambiguation Network for Composed Video Retrieval","created":"2025-12-02","cited_by_count":32,"area":null},{"id":"2203.01922","title":"Vision-Language Intelligence: Tasks, Representation Learning, and Large Models","created":"2022-03-03","cited_by_count":28,"area":null},{"id":"2308.16463","title":"Sparkles: Unlocking Chats Across Multiple Images for Multimodal Instruction-Following Models","created":"2023-08-31","cited_by_count":28,"area":null},{"id":"2109.04988","title":"Panoptic Narrative Grounding","created":"2021-09-10","cited_by_count":27,"area":null},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27,"area":null},{"id":"2109.04275","title":"M5Product: Self-harmonized Contrastive Learning for E-commercial Multi-modal Pretraining","created":"2021-09-09","cited_by_count":26,"area":null},{"id":"2203.15867","title":"Image Retrieval from Contextual Descriptions","created":"2022-03-29","cited_by_count":26,"area":null},{"id":"2212.01612","title":"Named Entity and Relation Extraction with Multi-Modal Retrieval","created":"2022-12-03","cited_by_count":26,"area":null},{"id":"2308.14316","title":"UniPT: Universal Parallel Tuning for Transfer Learning with Efficient Parameter and Memory","created":"2023-08-28","cited_by_count":26,"area":null},{"id":"2311.07022","title":"ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models","created":"2023-11-13","cited_by_count":26,"area":null},{"id":"2109.10613","title":"COVR: A test-bed for Visually Grounded Compositional Generalization with real images","created":"2021-09-22","cited_by_count":25,"area":null},{"id":"2305.07558","title":"Measuring Progress in Fine-grained Vision-and-Language Understanding","created":"2023-05-12","cited_by_count":25,"area":null},{"id":"2101.06013","title":"Reasoning over Vision and Language: Exploring the Benefits of Supplemental Knowledge","created":"2021-01-15","cited_by_count":24,"area":null},{"id":"2112.06482","title":"ITA: Image-Text Alignments for Multi-Modal Named Entity Recognition","created":"2021-12-13","cited_by_count":24,"area":null},{"id":"2206.00621","title":"Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training","created":"2022-06-01","cited_by_count":24,"area":null},{"id":"2212.09993","title":"Are Deep Neural Networks SMARTer than Second Graders?","created":"2022-12-20","cited_by_count":24,"area":null},{"id":"2305.17388","title":"MPCHAT: Towards Multimodal Persona-Grounded Conversation","created":"2023-05-27","cited_by_count":24,"area":null},{"id":"2604.18037","title":"HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval","created":"2026-04-20","cited_by_count":24,"area":null},{"id":"2203.00242","title":"Unsupervised Vision-and-Language Pre-training via Retrieval-based Multi-Granular Alignment","created":"2022-03-01","cited_by_count":23,"area":null},{"id":"2312.08924","title":"Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking","created":"2023-12-14","cited_by_count":23,"area":null},{"id":"2112.08723","title":"Distilled Dual-Encoder Model for Vision-Language Understanding","created":"2021-12-16","cited_by_count":22,"area":null},{"id":"2203.00758","title":"There is a Time and Place for Reasoning Beyond the Image","created":"2022-03-01","cited_by_count":22,"area":null},{"id":"2308.09804","title":"VL-PET: Vision-and-Language Parameter-Efficient Tuning via Granularity Control","created":"2023-08-18","cited_by_count":21,"area":null},{"id":"2311.18765","title":"MLLMs-Augmented Visual-Language Representation Learning","created":"2023-11-30","cited_by_count":21,"area":null},{"id":"2405.17927","title":"The Evolution of Multimodal Model Architectures","created":"2024-05-28","cited_by_count":21,"area":null},{"id":"2407.03418","title":"HEMM: Holistic Evaluation of Multimodal Foundation Models","created":"2024-07-03","cited_by_count":21,"area":null},{"id":"2503.19910","title":"CoLLM: A Large Language Model for Composed Image Retrieval","created":"2025-03-25","cited_by_count":21,"area":null},{"id":"2409.14750","title":"FineCops-Ref: A new Dataset and Task for Fine-Grained Compositional Referring Expression Comprehension","created":"2024-09-23","cited_by_count":20,"area":null},{"id":"2112.10728","title":"MuMuQA: Multimedia Multi-Hop News Question Answering via Cross-Media Knowledge Extraction and Grounding","created":"2021-12-20","cited_by_count":19,"area":null},{"id":"2210.06423","title":"Foundation Transformers","created":"2022-10-12","cited_by_count":19,"area":null},{"id":"2104.08066","title":"Effect of Visual Extensions on Natural Language Understanding in Vision-and-Language Models","created":"2021-04-16","cited_by_count":18,"area":null},{"id":"2107.12270","title":"Adaptive Hierarchical Graph Reasoning with Semantic Coherence for Video-and-Language Inference","created":"2021-07-26","cited_by_count":18,"area":null},{"id":"2109.11321","title":"Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?","created":"2021-09-23","cited_by_count":18,"area":null},{"id":"2305.04474","title":"TRIPS: Efficient Vision-and-Language Pre-training with Text-Relevant Image Patch Selection","created":"2023-05-08","cited_by_count":18,"area":null},{"id":"2411.16752","title":"Imagine and Seek: Improving Composed Image Retrieval with an Imagined Proxy","created":"2024-11-24","cited_by_count":18,"area":null},{"id":"2211.07912","title":"YORO -- Lightweight End to End Visual Grounding","created":"2022-11-15","cited_by_count":17,"area":null}],"next_cursor":"100"}