{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2102.05918","title":"Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervision","created":"2021-02-11","cited_by_count":3864},{"id":"2403.05530","title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","created":"2024-03-08","cited_by_count":3224},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2305.06500","title":"InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning","created":"2023-05-11","cited_by_count":2876},{"id":"1505.04870","title":"Flickr30k Entities: Collecting Region-to-Phrase Correspondences for Richer Image-to-Sentence Models","created":"2015-05-19","cited_by_count":1362},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2408.01800","title":"MiniCPM-V: A GPT-4V Level MLLM on Your Phone","created":"2024-08-03","cited_by_count":1079},{"id":"2303.15389","title":"EVA-CLIP: Improved Training Techniques for CLIP at Scale","created":"2023-03-27","cited_by_count":798},{"id":"2209.06794","title":"PaLI: A Jointly-Scaled Multilingual Language-Image Model","created":"2022-09-14","cited_by_count":766},{"id":"2003.07082","title":"Stanza: A Python Natural Language Processing Toolkit for Many Human Languages","created":"2020-03-16","cited_by_count":723},{"id":"2407.07726","title":"PaliGemma: A versatile 3B VLM for transfer","created":"2024-07-10","cited_by_count":696},{"id":"2010.00747","title":"Contrastive Learning of Medical Visual Representations from Paired Images and Text","created":"2020-10-02","cited_by_count":641},{"id":"2111.07783","title":"FILIP: Fine-grained Interactive Language-Image Pre-Training","created":"2021-11-09","cited_by_count":627},{"id":"2112.09106","title":"RegionCLIP: Region-based Language-Image Pretraining","created":"2021-12-16","cited_by_count":616},{"id":"2210.01936","title":"When and why vision-language models behave like bags-of-words, and what to do about it?","created":"2022-10-04","cited_by_count":610},{"id":"2111.07991","title":"LiT: Zero-Shot Transfer with Locked-image text Tuning","created":"2021-11-15","cited_by_count":577},{"id":"2111.09734","title":"ClipCap: CLIP Prefix for Image Captioning","created":"2021-11-18","cited_by_count":559},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"2112.12750","title":"SLIP: Self-supervision meets Language-Image Pre-training","created":"2021-12-23","cited_by_count":436},{"id":"2010.01028","title":"Hard Negative Mixing for Contrastive Learning","created":"2020-10-02","cited_by_count":402},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2311.06607","title":"Monkey: Image Resolution and Text Label Are Important Things for Large Multi-modal Models","created":"2023-11-11","cited_by_count":357},{"id":"2403.15378","title":"Long-CLIP: Unlocking the Long-Text Capability of CLIP","created":"2024-03-22","cited_by_count":300},{"id":"2111.08276","title":"Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts","created":"2021-11-16","cited_by_count":256},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243},{"id":"2312.00784","title":"ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts","created":"2023-12-01","cited_by_count":161},{"id":"2312.03818","title":"Alpha-CLIP: A CLIP Model Focusing on Wherever You Want","created":"2023-12-06","cited_by_count":151},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"2207.00221","title":"VL-CheckList: Evaluating Pre-trained Vision-Language Models with Objects, Attributes and Relations","created":"2022-07-01","cited_by_count":114},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102},{"id":"2402.04252","title":"EVA-CLIP-18B: Scaling CLIP to 18 Billion Parameters","created":"2024-02-06","cited_by_count":99},{"id":"2505.05071","title":"FG-CLIP: Fine-Grained Visual and Textual Alignment","created":"2025-05-08","cited_by_count":81},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58},{"id":"2304.06061","title":"CLIP-Guided Vision-Language Pre-training for Question Answering in 3D Scenes","created":"2023-04-12","cited_by_count":55},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48},{"id":"2306.08832","title":"Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Compositional Understanding","created":"2023-06-15","cited_by_count":41},{"id":"2305.06152","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","created":"2023-05-06","cited_by_count":37},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35},{"id":"2502.03566","title":"CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally","created":"2025-02-05","cited_by_count":31},{"id":"2211.13854","title":"ComCLIP: Training-Free Compositional Image and Text Matching","created":"2022-11-25","cited_by_count":26},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23},{"id":"2409.19967","title":"Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function","created":"2024-09-30","cited_by_count":19},{"id":"2502.14113","title":"Object-centric Binding in Contrastive Language-Image Pretraining","created":"2025-02-19","cited_by_count":12},{"id":"2408.12902","title":"IAA: Inner-Adaptor Architecture Empowers Frozen Large Language Model with Multimodal Capabilities","created":"2024-08-23","cited_by_count":8},{"id":"2503.17142","title":"Not Only Text: Exploring Compositionality of Visual Representations in Vision-Language Models","created":"2025-03-21","cited_by_count":8}],"next_cursor":null}