{"total":89,"rows":[{"id":"2401.06209","title":"Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs","created":"2024-01-11","cited_by_count":735,"area":"mllm"},{"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,"area":null},{"id":"2309.10020","title":"Multimodal Foundation Models: From Specialists to General-Purpose Assistants","created":"2023-09-18","cited_by_count":247,"area":null},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2403.06963","title":"The pitfalls of next-token prediction","created":"2024-03-11","cited_by_count":160,"area":null},{"id":"2401.10815","title":"Exploring scalable medical image encoders beyond text supervision","created":"2024-01-19","cited_by_count":132,"area":null},{"id":"2310.09199","title":"PaLI-3 Vision Language Models: Smaller, Faster, Stronger","created":"2023-10-13","cited_by_count":126,"area":"mllm"},{"id":"2307.13721","title":"Foundational Models Defining a New Era in Vision: A Survey and Outlook","created":"2023-07-25","cited_by_count":110,"area":null},{"id":"2411.14402","title":"Multimodal Autoregressive Pre-training of Large Vision Encoders","created":"2024-11-21","cited_by_count":109,"area":null},{"id":"2410.14669","title":"NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples","created":"2024-10-18","cited_by_count":97,"area":"mllm"},{"id":"2312.02116","title":"GIVT: Generative Infinite-Vocabulary Transformers","created":"2023-12-04","cited_by_count":80,"area":null},{"id":"2402.12259","title":"Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships","created":"2024-02-19","cited_by_count":80,"area":null},{"id":"2310.18689","title":"Foundational Models in Medical Imaging: A Comprehensive Survey and Future Vision","created":"2023-10-28","cited_by_count":76,"area":null},{"id":"2504.17432","title":"Breaking the Modality Barrier: Universal Embedding Learning with Multimodal LLMs","created":"2025-04-24","cited_by_count":73,"area":"mllm"},{"id":"2310.13355","title":"SILC: Improving Vision Language Pretraining with Self-Distillation","created":"2023-10-20","cited_by_count":66,"area":"mllm"},{"id":"2504.01017","title":"Scaling Language-Free Visual Representation Learning","created":"2025-04-01","cited_by_count":66,"area":null},{"id":"2309.16779","title":"Intriguing properties of generative classifiers","created":"2023-09-28","cited_by_count":52,"area":null},{"id":"2312.00648","title":"SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers","created":"2023-12-01","cited_by_count":49,"area":null},{"id":"2506.09108","title":"SensorLM: Learning the Language of Wearable Sensors","created":"2025-06-10","cited_by_count":49,"area":null},{"id":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2510.13515","title":"UniME-V2: MLLM-as-a-Judge for Universal Multimodal Embedding Learning","created":"2025-10-15","cited_by_count":42,"area":null},{"id":"2503.10635","title":"A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1","created":"2025-03-13","cited_by_count":37,"area":"mllm"},{"id":"2603.03276","title":"Beyond Language Modeling: An Exploration of Multimodal Pretraining","created":"2026-03-03","cited_by_count":37,"area":"moe"},{"id":"2403.19596","title":"LocCa: Visual Pretraining with Location-aware Captioners","created":"2024-03-28","cited_by_count":35,"area":null},{"id":"2312.07395","title":"A Simple Recipe for Contrastively Pre-training Video-First Encoders Beyond 16 Frames","created":"2023-12-12","cited_by_count":34,"area":null},{"id":"2512.02014","title":"TUNA: Taming Unified Visual Representations for Native Unified Multimodal Models","created":"2025-12-01","cited_by_count":34,"area":null},{"id":"2504.10462","title":"The Scalability of Simplicity: Empirical Analysis of Vision-Language Learning with a Single Transformer","created":"2025-04-14","cited_by_count":30,"area":"mllm"},{"id":"2504.15266","title":"Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction","created":"2025-04-21","cited_by_count":29,"area":null},{"id":"2504.12880","title":"Can Masked Autoencoders Also Listen to Birds?","created":"2025-04-17","cited_by_count":26,"area":null},{"id":"2506.10128","title":"ViCrit: A Verifiable Reinforcement Learning Proxy Task for Visual Perception in VLMs","created":"2025-06-11","cited_by_count":25,"area":"lr"},{"id":"2409.17958","title":"The Hard Positive Truth about Vision-Language Compositionality","created":"2024-09-26","cited_by_count":22,"area":"mllm"},{"id":"2510.15042","title":"Comprehensive language-image pre-training for 3D medical image understanding","created":"2025-10-16","cited_by_count":22,"area":"mllm"},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2406.08164","title":"ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs","created":"2024-06-12","cited_by_count":21,"area":"lr"},{"id":"2406.18587","title":"Nomic Embed Vision: Expanding the Latent Space","created":"2024-06-06","cited_by_count":19,"area":null},{"id":"2502.07617","title":"Scaling Pre-training to One Hundred Billion Data for Vision Language Models","created":"2025-02-11","cited_by_count":19,"area":"mllm"},{"id":"2404.01911","title":"VLRM: Vision-Language Models act as Reward Models for Image Captioning","created":"2024-04-02","cited_by_count":18,"area":"mllm"},{"id":"2405.03207","title":"A Philosophical Introduction to Language Models - Part II: The Way Forward","created":"2024-05-06","cited_by_count":18,"area":null},{"id":"2405.13777","title":"No Filter: Cultural and Socioeconomic Diversity in Contrastive Vision-Language Models","created":"2024-05-22","cited_by_count":16,"area":"mllm"},{"id":"2510.14751","title":"Beyond Multi-Token Prediction: Pretraining LLMs with Future Summaries","created":"2025-10-16","cited_by_count":15,"area":null},{"id":"2401.01974","title":"Towards Truly Zero-shot Compositional Visual Reasoning with LLMs as Programmers","created":"2024-01-03","cited_by_count":14,"area":"lr"},{"id":"2402.17510","title":"Demonstrating and Reducing Shortcuts in Vision-Language Representation Learning","created":"2024-02-27","cited_by_count":14,"area":"mllm"},{"id":"2410.11087","title":"Locality Alignment Improves Vision-Language Models","created":"2024-10-14","cited_by_count":13,"area":"lr"},{"id":"2512.19687","title":"Pushing the Frontier of Audiovisual Perception with Large-Scale Multimodal Correspondence Learning","created":"2025-12-22","cited_by_count":13,"area":null},{"id":"2604.12012","title":"TIPSv2: Advancing Vision-Language Pretraining with Enhanced Patch-Text Alignment","created":"2026-04-13","cited_by_count":13,"area":"mllm"},{"id":"2402.15021","title":"CLoVe: Encoding Compositional Language in Contrastive Vision-Language Models","created":"2024-02-22","cited_by_count":12,"area":"mllm"},{"id":"2404.05016","title":"Hyperbolic Learning with Synthetic Captions for Open-World Detection","created":"2024-04-07","cited_by_count":12,"area":null},{"id":"2602.23605","title":"SleepLM: Natural-Language Intelligence for Human Sleep","created":"2026-02-27","cited_by_count":12,"area":null},{"id":"2411.05195","title":"Exploring How Generative MLLMs Perceive More Than CLIP with the Same Vision Encoder","created":"2024-11-07","cited_by_count":11,"area":"lr"},{"id":"2411.03313","title":"Classification Done Right for Vision-Language Pre-Training","created":"2024-11-05","cited_by_count":10,"area":"mllm"},{"id":"2412.13364","title":"Bringing Multimodality to Amazon Visual Search System","created":"2024-12-17","cited_by_count":10,"area":null},{"id":"2511.20223","title":"V-Attack: Targeting Disentangled Value Features for Controllable Adversarial Attacks on LVLMs","created":"2025-11-25","cited_by_count":9,"area":"mllm"},{"id":"2506.04598","title":"Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets","created":"2025-06-05","cited_by_count":8,"area":null},{"id":"2509.01644","title":"OpenVision 2: A Family of Generative Pretrained Visual Encoders for Multimodal Learning","created":"2025-09-01","cited_by_count":7,"area":null},{"id":"2406.09952","title":"BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval","created":"2024-06-14","cited_by_count":6,"area":null},{"id":"2410.23261","title":"$100K or 100 Days: Trade-offs when Pre-Training with Academic Resources","created":"2024-10-30","cited_by_count":6,"area":null},{"id":"2411.08753","title":"Which Viewpoint Shows it Best? Language for Weakly Supervising View Selection in Multi-view Instructional Videos","created":"2024-11-13","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":"2602.17645","title":"Pushing the Frontier of Black-Box LVLM Attacks via Fine-Grained Detail Targeting","created":"2026-02-19","cited_by_count":6,"area":"mllm"},{"id":"2402.01399","title":"A Probabilistic Model Behind Self-Supervised Learning","created":"2024-02-02","cited_by_count":5,"area":null},{"id":"2403.02506","title":"Differentially Private Representation Learning via Image Captioning","created":"2024-03-04","cited_by_count":5,"area":null},{"id":"2506.08227","title":"A Good CREPE needs more than just Sugar: Investigating Biases in Compositional Vision-Language Benchmarks","created":"2025-06-09","cited_by_count":5,"area":null},{"id":"2511.16757","title":"Revisiting Audio-language Pretraining for Learning General-purpose Audio Representation","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2309.07917","title":"Looking at words and points with attention: a benchmark for text-to-shape coherence","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2406.16085","title":"A Simple Framework for Open-Vocabulary Zero-Shot Segmentation","created":"2024-06-23","cited_by_count":3,"area":null},{"id":"2412.15396","title":"Learning Visual Composition through Improved Semantic Guidance","created":"2024-12-19","cited_by_count":3,"area":null},{"id":"2504.13219","title":"Scaling Laws for Data-Efficient Visual Transfer Learning","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2510.10487","title":"Towards Self-Refinement of Vision-Language Models with Triangular Consistency","created":"2025-10-12","cited_by_count":3,"area":"mllm"},{"id":"2511.22294","title":"Structure is Supervision: Multiview Masked Autoencoders for Radiology","created":"2025-11-27","cited_by_count":2,"area":null},{"id":"2605.00809","title":"Let ViT Speak: Generative Language-Image Pre-training","created":"2026-05-01","cited_by_count":2,"area":"mllm"},{"id":"2608.29335","title":"GenFirst: Generation Before Reconstruction for Stable End-to-End Latent Generative Modeling","created":"2026-08-29","cited_by_count":2,"area":null},{"id":"2406.18249","title":"Foundational Models for Pathology and Endoscopy Images: Application for Gastric Inflammation","created":"2024-06-26","cited_by_count":1,"area":null},{"id":"2501.11469","title":"MASS: Overcoming Language Bias in Image-Text Matching","created":"2025-01-20","cited_by_count":1,"area":"mllm"},{"id":"2505.19990","title":"Progressive Scaling Visual Object Tracking","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2508.21451","title":"MM-SeR: Multimodal Self-Refinement for Lightweight Image Captioning","created":"2025-08-29","cited_by_count":1,"area":null},{"id":"2510.26799","title":"Masked Diffusion Captioning for Visual Feature Learning","created":"2025-10-30","cited_by_count":1,"area":"diffusion"},{"id":"2602.09934","title":"VersaViT: Enhancing MLLM Vision Backbones via Task-Guided Optimization","created":"2026-02-10","cited_by_count":1,"area":"mllm"},{"id":"2603.04950","title":"Location-Aware Pretraining for Medical Difference Visual Question Answering","created":"2026-03-05","cited_by_count":1,"area":null},{"id":"2603.25767","title":"Unlocking Strong Supervision: A Data-Centric Study of General-Purpose Audio Pre-Training Methods","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2603.26475","title":"Foundation Model for Cardiac Time Series via Masked Latent Attention","created":"2026-03-27","cited_by_count":1,"area":null},{"id":"2606.19584","title":"Language-Instructed Vision Embeddings for Controllable and Generalizable Perception","created":"2026-06-17","cited_by_count":1,"area":null},{"id":"2409.16024","title":"From Goal-Conditioned to Language-Conditioned Agents via Vision-Language Models","created":"2024-09-24","cited_by_count":0,"area":"mllm"},{"id":"2510.17405","title":"AFRICAPTION: Establishing a New Paradigm for Image Captioning in African Languages","created":"2025-10-20","cited_by_count":0,"area":null},{"id":"2602.16918","title":"Xray-Visual Models: Scaling Vision models on Industry Scale Data","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2607.23373","title":"UltraViT: Latency-Optimized On-device Vision Encoder for Large Vision-Language Models","created":"2026-07-25","cited_by_count":0,"area":"mllm"},{"id":"2608.18132","title":"Alignment Is All You Need: Instruction-Free Training for General Audio-Language Models","created":"2026-07-28","cited_by_count":0,"area":"mllm"},{"id":"2609.12035","title":"Reading the Whole Heart: Latent-Attention Masked Autoencoders for Multimodal Cardiac Representation Learning","created":"2026-09-10","cited_by_count":0,"area":null},{"id":"2609.26617","title":"MMAP: Multimodal Missing-Aware Pretraining for Longitudinal Alzheimer's Prediction","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.31985","title":"Does Vision-Language Pretraining Granularity Matter? A Controlled Evaluation of Vision-Language Objectives Across Chest X-Ray Interpretation Tasks","created":"2026-09-25","cited_by_count":0,"area":"mllm"}],"next_cursor":null}