{"total":113,"rows":[{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2411.10440","title":"LLaVA-CoT: Let Vision Language Models Reason Step-by-Step","created":"2024-11-15","cited_by_count":454,"area":"lr"},{"id":"2207.04429","title":"LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action","created":"2022-07-10","cited_by_count":439,"area":null},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2302.03084","title":"Pic2Word: Mapping Pictures to Words for Zero-shot Composed Image Retrieval","created":"2023-02-06","cited_by_count":156,"area":null},{"id":"2305.14093","title":"Weakly Supervised 3D Open-vocabulary Segmentation","created":"2023-05-23","cited_by_count":135,"area":null},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91,"area":null},{"id":"2301.06267","title":"Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models","created":"2023-01-16","cited_by_count":91,"area":null},{"id":"2304.00788","title":"Open-Vocabulary Point-Cloud Object Detection without 3D Annotation","created":"2023-04-03","cited_by_count":81,"area":"mllm"},{"id":"2209.15517","title":"Medical Image Understanding with Pretrained Vision Language Models: A Comprehensive Study","created":"2022-09-30","cited_by_count":66,"area":"mllm"},{"id":"2310.05473","title":"Sentence-level Prompts Benefit Composed Image Retrieval","created":"2023-10-09","cited_by_count":59,"area":null},{"id":"2411.02545","title":"TripletCLIP: Improving Compositional Reasoning of CLIP via Synthetic Vision-Language Negatives","created":"2024-11-04","cited_by_count":58,"area":null},{"id":"2306.16410","title":"Towards Language Models That Can See: Computer Vision Through the LENS of Natural Language","created":"2023-06-28","cited_by_count":53,"area":null},{"id":"2410.07112","title":"VHELM: A Holistic Evaluation of Vision Language Models","created":"2024-10-09","cited_by_count":53,"area":"mllm"},{"id":"2309.16137","title":"Context-I2W: Mapping Images to Context-dependent Words for Accurate Zero-Shot Composed Image Retrieval","created":"2023-09-28","cited_by_count":52,"area":null},{"id":"2412.13736","title":"MedCoT: Medical Chain of Thought via Hierarchical Expert","created":"2024-12-18","cited_by_count":46,"area":"lr"},{"id":"2502.04263","title":"Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion","created":"2025-02-06","cited_by_count":43,"area":"mllm"},{"id":"2406.05491","title":"One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models","created":"2024-06-08","cited_by_count":40,"area":"mllm"},{"id":"2206.01127","title":"VL-BEiT: Generative Vision-Language Pretraining","created":"2022-06-02","cited_by_count":39,"area":"mllm"},{"id":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2412.11077","title":"Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval","created":"2024-12-15","cited_by_count":32,"area":"lr"},{"id":"2305.14014","title":"CLIP4STR: A Simple Baseline for Scene Text Recognition with Pre-trained Vision-Language Model","created":"2023-05-23","cited_by_count":30,"area":"mllm"},{"id":"2310.19301","title":"ROME: Evaluating Pre-trained Vision-Language Models on Reasoning beyond Visual Common Sense","created":"2023-10-30","cited_by_count":27,"area":"lr"},{"id":"2211.09778","title":"I Can't Believe There's No Images! Learning Visual Tasks Using only Language Supervision","created":"2022-11-17","cited_by_count":26,"area":null},{"id":"2311.00308","title":"From Image to Language: A Critical Analysis of Visual Question Answering (VQA) Approaches, Challenges, and Opportunities","created":"2023-11-01","cited_by_count":25,"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":"2410.20327","title":"R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest","created":"2024-10-27","cited_by_count":21,"area":null},{"id":"2205.12191","title":"Reassessing Evaluation Practices in Visual Question Answering: A Case Study on Out-of-Distribution Generalization","created":"2022-05-24","cited_by_count":20,"area":null},{"id":"2302.14794","title":"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning","created":"2023-02-28","cited_by_count":20,"area":null},{"id":"2410.22456","title":"Image2Struct: Benchmarking Structure Extraction for Vision-Language Models","created":"2024-10-29","cited_by_count":19,"area":"mllm"},{"id":"2210.10362","title":"CPL: Counterfactual Prompt Learning for Vision and Language Models","created":"2022-10-19","cited_by_count":18,"area":null},{"id":"2407.03056","title":"Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation","created":"2024-07-03","cited_by_count":18,"area":"mllm"},{"id":"2210.05593","title":"Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection","created":"2022-10-11","cited_by_count":14,"area":null},{"id":"2302.06891","title":"UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training","created":"2023-02-14","cited_by_count":14,"area":"mllm"},{"id":"2303.06580","title":"Towards General Purpose Medical AI: Continual Learning Medical Foundation Model","created":"2023-03-12","cited_by_count":14,"area":null},{"id":"2310.04999","title":"Symmetrical Linguistic Feature Distillation with CLIP for Scene Text Recognition","created":"2023-10-08","cited_by_count":14,"area":"distill"},{"id":"2409.16718","title":"Vision-Language Model Fine-Tuning via Simple Parameter-Efficient Modification","created":"2024-09-25","cited_by_count":14,"area":"mllm"},{"id":"2407.11717","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Large Models","created":"2024-07-16","cited_by_count":13,"area":null},{"id":"2412.00440","title":"Advancing Myopia To Holism: Fully Contrastive Language-Image Pre-training","created":"2024-11-30","cited_by_count":13,"area":"mllm"},{"id":"2302.06658","title":"In Search for a Generalizable Method for Source Free Domain Adaptation","created":"2023-02-13","cited_by_count":12,"area":null},{"id":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2304.14204","title":"Towards Medical Artificial General Intelligence via Knowledge-Enhanced Multimodal Pretraining","created":"2023-04-26","cited_by_count":11,"area":null},{"id":"2312.07408","title":"Turbo: Informativity-Driven Acceleration Plug-In for Vision-Language Models","created":"2023-12-12","cited_by_count":11,"area":"mllm"},{"id":"2504.12104","title":"Logits DeConfusion with CLIP for Few-Shot Learning","created":"2025-04-16","cited_by_count":11,"area":null},{"id":"2308.12045","title":"CgT-GAN: CLIP-guided Text GAN for Image Captioning","created":"2023-08-23","cited_by_count":10,"area":null},{"id":"2404.19065","title":"HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models","created":"2024-04-29","cited_by_count":8,"area":"agents"},{"id":"2210.13838","title":"Multilingual Relation Classification via Efficient and Effective Prompting","created":"2022-10-25","cited_by_count":7,"area":null},{"id":"2303.04497","title":"Exploiting the Textual Potential from Vision-Language Pre-training for Text-based Person Search","created":"2023-03-08","cited_by_count":7,"area":"mllm"},{"id":"2305.18373","title":"KAFA: Rethinking Image Ad Understanding with Knowledge-Augmented Feature Adaptation of Vision-Language Models","created":"2023-05-28","cited_by_count":7,"area":"lr"},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2403.10492","title":"Mitigating Dialogue Hallucination for Large Vision Language Models via Adversarial Instruction Tuning","created":"2024-03-15","cited_by_count":7,"area":"mllm"},{"id":"2406.01906","title":"ProGEO: Generating Prompts through Image-Text Contrastive Learning for Visual Geo-localization","created":"2024-06-04","cited_by_count":6,"area":null},{"id":"2407.11211","title":"Unconstrained Open Vocabulary Image Classification: Zero-Shot Transfer from Text to Image via CLIP Inversion","created":"2024-07-15","cited_by_count":6,"area":null},{"id":"2408.00331","title":"DECIDER: Leveraging Foundation Model Priors for Improved Model Failure Detection and Explanation","created":"2024-08-01","cited_by_count":6,"area":null},{"id":"2412.09353","title":"Causal Graphical Models for Vision-Language Compositional Understanding","created":"2024-12-12","cited_by_count":6,"area":"mllm"},{"id":"2409.19210","title":"Learning to Obstruct Few-Shot Image Classification over Restricted Classes","created":"2024-09-28","cited_by_count":5,"area":null},{"id":"2502.06600","title":"Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?","created":"2025-02-10","cited_by_count":5,"area":null},{"id":"2302.06072","title":"Actional Atomic-Concept Learning for Demystifying Vision-Language Navigation","created":"2023-02-13","cited_by_count":4,"area":null},{"id":"2307.07742","title":"SINC: Self-Supervised In-Context Learning for Vision-Language Tasks","created":"2023-07-15","cited_by_count":4,"area":null},{"id":"2402.17298","title":"ArcSin: Adaptive ranged cosine Similarity injected noise for Language-Driven Visual Tasks","created":"2024-02-27","cited_by_count":4,"area":null},{"id":"2410.11639","title":"Efficient and Effective Universal Adversarial Attack against Vision-Language Pre-training Models","created":"2024-10-15","cited_by_count":4,"area":"mllm"},{"id":"2412.00526","title":"Human Action CLIPs: Detecting AI-generated Human Motion","created":"2024-11-30","cited_by_count":4,"area":null},{"id":"2412.07119","title":"DiffCLIP: Few-shot Language-driven Multimodal Classifier","created":"2024-12-10","cited_by_count":4,"area":"mllm"},{"id":"2502.07830","title":"Captured by Captions: On Memorization and its Mitigation in CLIP Models","created":"2025-02-11","cited_by_count":4,"area":null},{"id":"2503.22208","title":"DeepSound-V1: Start to Think Step-by-Step in the Audio Generation from Videos","created":"2025-03-28","cited_by_count":4,"area":"lr"},{"id":"2208.10758","title":"Learning More May Not Be Better: Knowledge Transferability in Vision and Language Tasks","created":"2022-08-23","cited_by_count":3,"area":null},{"id":"2210.05836","title":"CLIP also Understands Text: Prompting CLIP for Phrase Understanding","created":"2022-10-11","cited_by_count":3,"area":null},{"id":"2305.17369","title":"Modularized Zero-shot VQA with Pre-trained Models","created":"2023-05-27","cited_by_count":3,"area":null},{"id":"2307.00862","title":"UniFine: A Unified and Fine-grained Approach for Zero-shot Vision-Language Understanding","created":"2023-07-03","cited_by_count":3,"area":"lr"},{"id":"2410.17393","title":"Denoise-I2W: Mapping Images to Denoising Words for Accurate Zero-Shot Composed Image Retrieval","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2411.15099","title":"Context-Aware Multimodal Pretraining","created":"2024-11-22","cited_by_count":3,"area":null},{"id":"2502.11969","title":"Learning Generalizable Prompt for CLIP with Class Similarity Knowledge","created":"2025-02-17","cited_by_count":3,"area":"mllm"},{"id":"2507.06210","title":"CultureCLIP: Empowering CLIP with Cultural Awareness through Synthetic Images and Contextualized Captions","created":"2025-07-08","cited_by_count":3,"area":"mllm"},{"id":"2508.16707","title":"Sparse and Dense Retrievers Learn Better Together: Joint Sparse-Dense Optimization for Text-Image Retrieval","created":"2025-08-22","cited_by_count":3,"area":"mllm"},{"id":"2508.17290","title":"MEENA (PersianMMMU): Multimodal-Multilingual Educational Exams for N-level Assessment","created":"2025-08-24","cited_by_count":3,"area":"mllm"},{"id":"2509.06233","title":"O$^3$Afford: One-Shot 3D Object-to-Object Affordance Grounding for Generalizable Robotic Manipulation","created":"2025-09-07","cited_by_count":3,"area":null},{"id":"2603.19862","title":"IsoCLIP: Decomposing CLIP Projectors for Efficient Intra-modal Alignment","created":"2026-03-20","cited_by_count":3,"area":"mllm"},{"id":"2308.10240","title":"Generic Attention-model Explainability by Weighted Relevance Accumulation","created":"2023-08-20","cited_by_count":2,"area":null},{"id":"2311.01580","title":"MetaReVision: Meta-Learning with Retrieval for Visually Grounded Compositional Concept Acquisition","created":"2023-11-02","cited_by_count":2,"area":null},{"id":"2406.12638","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","created":"2024-06-18","cited_by_count":2,"area":"mllm"},{"id":"2502.05924","title":"Multi-Branch Collaborative Learning Network for Video Quality Assessment in Industrial Video Search","created":"2025-02-09","cited_by_count":2,"area":null},{"id":"2508.16932","title":"Align 3D Representation and Text Embedding for 3D Content Personalization","created":"2025-08-23","cited_by_count":2,"area":null},{"id":"2509.15695","title":"ORIC: Benchmarking Object Recognition under Contextual Incongruity in Large Vision-Language Models","created":"2025-09-19","cited_by_count":2,"area":"mllm"},{"id":"2210.12905","title":"Visualizing the Obvious: A Concreteness-based Ensemble Model for Noun Property Prediction","created":"2022-10-24","cited_by_count":1,"area":null},{"id":"2306.06077","title":"Semantically-Prompted Language Models Improve Visual Descriptions","created":"2023-06-05","cited_by_count":1,"area":null},{"id":"2306.11400","title":"MuDPT: Multi-modal Deep-symphysis Prompt Tuning for Large Pre-trained Vision-Language Models","created":"2023-06-20","cited_by_count":1,"area":"mllm"},{"id":"2312.10613","title":"p-Laplacian Adaptation for Generative Pre-trained Vision-Language Models","created":"2023-12-17","cited_by_count":1,"area":"mllm"},{"id":"2403.15152","title":"Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval","created":"2024-03-22","cited_by_count":1,"area":null},{"id":"2405.19773","title":"VQA Training Sets are Self-play Environments for Generating Few-shot Pools","created":"2024-05-30","cited_by_count":1,"area":"synth"},{"id":"2506.17967","title":"Adapting Vision-Language Models for Evaluating World Models","created":"2025-06-22","cited_by_count":1,"area":"wm"},{"id":"2510.03727","title":"Bridging the Gap Between Multimodal Foundation Models and World Models","created":"2025-10-04","cited_by_count":1,"area":"wm"},{"id":"2606.06938","title":"When CLIP Sees More, It Fights Back Harder: Multi-View Guided Adaptive Counterattacks for Test-Time Adversarial Robustness","created":"2026-06-05","cited_by_count":1,"area":"mllm"},{"id":"2206.05281","title":"Less Is More: Linear Layers on CLIP Features as Powerful VizWiz Model","created":"2022-06-10","cited_by_count":0,"area":null},{"id":"2307.15983","title":"Instance-Wise Adaptive Tuning and Caching for Vision-Language Models","created":"2023-07-29","cited_by_count":0,"area":"mllm"},{"id":"2401.16347","title":"Cross-Modal Coordination Across a Diverse Set of Input Modalities","created":"2024-01-29","cited_by_count":0,"area":null},{"id":"2405.00479","title":"Enhanced Textual Feature Extraction for Visual Question Answering: A Simple Convolutional Approach","created":"2024-05-01","cited_by_count":0,"area":null},{"id":"2405.03852","title":"VSA4VQA: Scaling a Vector Symbolic Architecture to Visual Question Answering on Natural Images","created":"2024-05-06","cited_by_count":0,"area":null},{"id":"2405.09125","title":"HAAP: Vision-context Hierarchical Attention Autoregressive with Adaptive Permutation for Scene Text Recognition","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2405.10954","title":"Multimodal CLIP Inference for Meta-Few-Shot Image Classification","created":"2024-03-26","cited_by_count":0,"area":null}],"next_cursor":"100"}