{"list":"other","total":53,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1907.11692","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","created":"2019-07-26","cited_by_count":13372},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"1409.0575","title":"ImageNet Large Scale Visual Recognition Challenge","created":"2014-09-01","cited_by_count":8498},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1904.09675","title":"BERTScore: Evaluating Text Generation with BERT","created":"2019-04-21","cited_by_count":5512},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"1412.2306","title":"Deep Visual-Semantic Alignments for Generating Image Descriptions","created":"2014-12-07","cited_by_count":968},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2304.14108","title":"DataComp: In search of the next generation of multimodal datasets","created":"2023-04-27","cited_by_count":644},{"id":"2010.04592","title":"Contrastive Learning with Hard Negative Samples","created":"2020-10-09","cited_by_count":628},{"id":"2204.03162","title":"Winoground: Probing Vision and Language Models for Visio-Linguistic Compositionality","created":"2022-04-07","cited_by_count":529},{"id":"1910.04867","title":"A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmark","created":"2019-10-01","cited_by_count":425},{"id":"2504.13181","title":"Perception Encoder: The best visual embeddings are not at the output of the network","created":"2025-04-17","cited_by_count":326},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2309.16671","title":"Demystifying CLIP Data","created":"2023-09-28","cited_by_count":270},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2305.20088","title":"Improving CLIP Training with Language Rewrites","created":"2023-05-31","cited_by_count":217},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198},{"id":"2110.06848","title":"Decoupled Contrastive Learning","created":"2021-10-13","cited_by_count":143},{"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},{"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":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72},{"id":"2412.03735","title":"VidHalluc: Evaluating Temporal Hallucinations in Multimodal Large Language Models for Video Understanding","created":"2024-12-04","cited_by_count":68},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58},{"id":"2010.06682","title":"Are all negatives created equal in contrastive instance discrimination?","created":"2020-10-13","cited_by_count":50},{"id":"2202.12387","title":"Provable Stochastic Optimization for Global Contrastive Learning: Small Batch Does Not Harm Performance","created":"2022-02-24","cited_by_count":43},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42},{"id":"2502.08636","title":"Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Multimodal Models","created":"2025-02-12","cited_by_count":38},{"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":"2403.04547","title":"CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?","created":"2024-03-07","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":"2501.10913","title":"Know \"No\" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP","created":"2025-01-19","cited_by_count":28},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19},{"id":"1804.06786","title":"Quantifying the visual concreteness of words and topics in multimodal datasets","created":"2018-04-18","cited_by_count":17},{"id":"2304.08480","title":"DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training","created":"2023-04-17","cited_by_count":15},{"id":"2410.02740","title":"Revisit Large-Scale Image-Caption Data in Pre-training Multimodal Foundation Models","created":"2024-10-03","cited_by_count":14},{"id":"2403.03662","title":"Harnessing Meta-Learning for Improving Full-Frame Video Stabilization","created":"2024-03-06","cited_by_count":5},{"id":"2412.03745","title":"Deep Variational Bayesian Modeling of Haze Degradation Process","created":"2024-12-04","cited_by_count":5},{"id":"2507.12998","title":"Differential-informed Sample Selection Accelerates Multimodal Contrastive Learning","created":"2025-07-17","cited_by_count":3},{"id":"2411.17794","title":"NEMO: Can Multimodal LLMs Identify Attribute-Modified Objects?","created":"2024-11-26","cited_by_count":2},{"id":"2508.18859","title":"Harnessing Meta-Learning for Controllable Full-Frame Video Stabilization","created":"2025-08-26","cited_by_count":2},{"id":"2510.18083","title":"Chimera: Compositional Image Generation using Part-based Concepting","created":"2025-10-20","cited_by_count":2},{"id":"2501.11469","title":"MASS: Overcoming Language Bias in Image-Text Matching","created":"2025-01-20","cited_by_count":1}],"next_cursor":null}