{"total":610,"rows":[{"id":"2406.16860","title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","created":"2024-06-24","cited_by_count":838,"area":"mllm"},{"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":"2409.02813","title":"MMMU-Pro: A More Robust Multi-discipline Multimodal Understanding Benchmark","created":"2024-09-04","cited_by_count":512,"area":null},{"id":"2404.01291","title":"Evaluating Text-to-Visual Generation with Image-to-Text Generation","created":"2024-04-01","cited_by_count":474,"area":null},{"id":"2404.18930","title":"Hallucination of Multimodal Large Language Models: A Survey","created":"2024-04-29","cited_by_count":388,"area":"mllm"},{"id":"2306.16527","title":"OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents","created":"2023-06-21","cited_by_count":316,"area":"mllm"},{"id":"2409.01652","title":"ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation","created":"2024-09-03","cited_by_count":315,"area":"lr"},{"id":"2305.16934","title":"On Evaluating Adversarial Robustness of Large Vision-Language Models","created":"2023-05-26","cited_by_count":284,"area":"mllm"},{"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,"area":"lr"},{"id":"2306.14610","title":"SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality","created":"2023-06-26","cited_by_count":243,"area":"mllm"},{"id":"2412.14164","title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","created":"2024-12-18","cited_by_count":206,"area":null},{"id":"2503.07265","title":"WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation","created":"2025-03-10","cited_by_count":204,"area":null},{"id":"2305.00976","title":"TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis","created":"2023-05-02","cited_by_count":198,"area":null},{"id":"2306.00984","title":"StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners","created":"2023-06-01","cited_by_count":177,"area":null},{"id":"2306.08877","title":"Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment","created":"2023-06-15","cited_by_count":171,"area":"diffusion"},{"id":"2311.17076","title":"Compositional Chain-of-Thought Prompting for Large Multimodal Models","created":"2023-11-27","cited_by_count":164,"area":"lr"},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135,"area":"agents"},{"id":"2406.13743","title":"GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation","created":"2024-06-19","cited_by_count":135,"area":null},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130,"area":null},{"id":"2312.12856","title":"SkyScript: A Large and Semantically Diverse Vision-Language Dataset for Remote Sensing","created":"2023-12-20","cited_by_count":125,"area":"mllm"},{"id":"2302.13996","title":"Aligning Bag of Regions for Open-Vocabulary Object Detection","created":"2023-02-27","cited_by_count":119,"area":"mllm"},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119,"area":null},{"id":"2406.04312","title":"ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization","created":"2024-06-06","cited_by_count":119,"area":"alignment"},{"id":"2309.14859","title":"Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation","created":"2023-09-26","cited_by_count":109,"area":"diffusion"},{"id":"2305.10400","title":"What You See is What You Read? Improving Text-Image Alignment Evaluation","created":"2023-05-17","cited_by_count":108,"area":"mllm"},{"id":"2312.08578","title":"A Picture is Worth More Than 77 Text Tokens: Evaluating CLIP-Style Models on Dense Captions","created":"2023-12-14","cited_by_count":108,"area":null},{"id":"2212.10537","title":"Does CLIP Bind Concepts? Probing Compositionality in Large Image Models","created":"2022-12-20","cited_by_count":102,"area":null},{"id":"2306.07282","title":"Waffling around for Performance: Visual Classification with Random Words and Broad Concepts","created":"2023-06-12","cited_by_count":101,"area":"mllm"},{"id":"2311.17049","title":"MobileCLIP: Fast Image-Text Models through Multi-Modal Reinforced Training","created":"2023-11-28","cited_by_count":96,"area":null},{"id":"2304.05390","title":"HRS-Bench: Holistic, Reliable and Scalable Benchmark for Text-to-Image Models","created":"2023-04-11","cited_by_count":95,"area":"diffusion"},{"id":"2403.17804","title":"Improving Text-to-Image Consistency via Automatic Prompt Optimization","created":"2024-03-26","cited_by_count":90,"area":null},{"id":"2305.11116","title":"LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation","created":"2023-05-18","cited_by_count":87,"area":null},{"id":"2406.08478","title":"What If We Recaption Billions of Web Images with LLaMA-3?","created":"2024-06-12","cited_by_count":87,"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":"2305.07017","title":"An Inverse Scaling Law for CLIP Training","created":"2023-05-11","cited_by_count":77,"area":null},{"id":"2304.06708","title":"Verbs in Action: Improving verb understanding in video-language models","created":"2023-04-13","cited_by_count":76,"area":null},{"id":"2403.15941","title":"Explore until Confident: Efficient Exploration for Embodied Question Answering","created":"2024-03-23","cited_by_count":74,"area":null},{"id":"2410.06912","title":"Compositional Entailment Learning for Hyperbolic Vision-Language Models","created":"2024-10-09","cited_by_count":74,"area":"mllm"},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"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":"2305.19595","title":"Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models","created":"2023-05-31","cited_by_count":72,"area":null},{"id":"2403.17007","title":"DreamLIP: Language-Image Pre-training with Long Captions","created":"2024-03-25","cited_by_count":72,"area":null},{"id":"2501.09425","title":"Vision-Language Models Do Not Understand Negation","created":"2025-01-16","cited_by_count":72,"area":"mllm"},{"id":"2504.02821","title":"Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models","created":"2025-04-03","cited_by_count":71,"area":"mllm"},{"id":"2307.09220","title":"A Survey on Open-Vocabulary Detection and Segmentation: Past, Present, and Future","created":"2023-07-18","cited_by_count":61,"area":null},{"id":"2404.03653","title":"CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching","created":"2024-04-04","cited_by_count":61,"area":"diffusion"},{"id":"2506.17267","title":"CF-VLM:CounterFactual Vision-Language Fine-tuning","created":"2025-06-10","cited_by_count":59,"area":"lr"},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"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":"2404.07983","title":"Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models","created":"2024-04-11","cited_by_count":57,"area":"mllm"},{"id":"2405.02793","title":"ImageInWords: Unlocking Hyper-Detailed Image Descriptions","created":"2024-05-05","cited_by_count":57,"area":null},{"id":"2305.03689","title":"COLA: A Benchmark for Compositional Text-to-image Retrieval","created":"2023-05-05","cited_by_count":53,"area":"mllm"},{"id":"2501.04931","title":"Jailbreaking Multimodal Large Language Models via Shuffle Inconsistency","created":"2025-01-09","cited_by_count":51,"area":"mllm"},{"id":"2403.20312","title":"Learn \"No\" to Say \"Yes\" Better: Improving Vision-Language Models via Negations","created":"2024-03-29","cited_by_count":46,"area":"mllm"},{"id":"2408.15769","title":"A Survey on Evaluation of Multimodal Large Language Models","created":"2024-08-28","cited_by_count":46,"area":"lr"},{"id":"2404.16820","title":"Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings","created":"2024-04-25","cited_by_count":44,"area":null},{"id":"2303.08914","title":"MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledge","created":"2023-03-15","cited_by_count":43,"area":null},{"id":"2310.08753","title":"CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models","created":"2023-10-12","cited_by_count":43,"area":"lr"},{"id":"2305.10683","title":"Paxion: Patching Action Knowledge in Video-Language Foundation Models","created":"2023-05-18","cited_by_count":42,"area":null},{"id":"2406.11171","title":"SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations","created":"2024-06-17","cited_by_count":42,"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":"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,"area":"mllm"},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"id":"2407.00143","title":"InfoNCE: Identifying the Gap Between Theory and Practice","created":"2024-06-28","cited_by_count":40,"area":null},{"id":"2305.06343","title":"Incorporating Structured Representations into Pretrained Vision & Language Models Using Scene Graphs","created":"2023-05-10","cited_by_count":39,"area":null},{"id":"2309.14289","title":"CLIP-DIY: CLIP Dense Inference Yields Open-Vocabulary Semantic Segmentation For-Free","created":"2023-09-25","cited_by_count":39,"area":null},{"id":"2410.10855","title":"Core Knowledge Deficits in Multi-Modal Language Models","created":"2024-10-06","cited_by_count":38,"area":"mllm"},{"id":"2511.00405","title":"UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddings","created":"2025-11-01","cited_by_count":38,"area":"lr"},{"id":"2305.06152","title":"Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations","created":"2023-05-06","cited_by_count":37,"area":"mllm"},{"id":"2404.16038","title":"A Survey on Generative AI and LLM for Video Generation, Understanding, and Streaming","created":"2024-01-30","cited_by_count":37,"area":null},{"id":"2503.17349","title":"Beyond Semantics: Rediscovering Spatial Awareness in Vision-Language Models","created":"2025-03-21","cited_by_count":37,"area":"lr"},{"id":"2306.12105","title":"Mass-Producing Failures of Multimodal Systems with Language Models","created":"2023-06-21","cited_by_count":36,"area":null},{"id":"2402.13254","title":"CounterCurate: Enhancing Physical and Semantic Visio-Linguistic Compositional Reasoning via Counterfactual Examples","created":"2024-02-20","cited_by_count":35,"area":"lr"},{"id":"2403.10997","title":"N2F2: Hierarchical Scene Understanding with Nested Neural Feature Fields","created":"2024-03-16","cited_by_count":34,"area":null},{"id":"2303.17590","title":"Going Beyond Nouns With Vision & Language Models Using Synthetic Data","created":"2023-03-30","cited_by_count":33,"area":null},{"id":"2406.13246","title":"GSR-BENCH: A Benchmark for Grounded Spatial Reasoning Evaluation via Multimodal LLMs","created":"2024-06-19","cited_by_count":33,"area":"lr"},{"id":"2411.02537","title":"INQUIRE: A Natural World Text-to-Image Retrieval Benchmark","created":"2024-11-04","cited_by_count":33,"area":"mllm"},{"id":"2407.03471","title":"Learning Action and Reasoning-Centric Image Editing from Videos and Simulations","created":"2024-07-03","cited_by_count":32,"area":null},{"id":"2308.03977","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","created":"2023-08-08","cited_by_count":31,"area":null},{"id":"2310.16640","title":"EmoCLIP: A Vision-Language Method for Zero-Shot Video Facial Expression Recognition","created":"2023-10-25","cited_by_count":31,"area":null},{"id":"2408.04810","title":"UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling","created":"2024-08-09","cited_by_count":31,"area":"lr"},{"id":"2410.09733","title":"MMCOMPOSITION: Revisiting the Compositionality of Pre-trained Vision-Language Models","created":"2024-10-13","cited_by_count":31,"area":"mllm"},{"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,"area":null},{"id":"2311.10111","title":"VideoCon: Robust Video-Language Alignment via Contrast Captions","created":"2023-11-15","cited_by_count":30,"area":null},{"id":"2406.10424","title":"What is the Visual Cognition Gap between Humans and Multimodal LLMs?","created":"2024-06-14","cited_by_count":30,"area":"mllm"},{"id":"2406.16320","title":"What Do VLMs NOTICE? A Mechanistic Interpretability Pipeline for Gaussian-Noise-free Text-Image Corruption and Evaluation","created":"2024-06-24","cited_by_count":30,"area":"mllm"},{"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":"2506.09987","title":"A Shortcut-aware Video-QA Benchmark for Physical Understanding via Minimal Video Pairs","created":"2025-06-11","cited_by_count":30,"area":"lr"},{"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,"area":null},{"id":"2508.17298","title":"Explain Before You Answer: A Survey on Compositional Visual Reasoning","created":"2025-08-24","cited_by_count":28,"area":"lr"},{"id":"2503.18325","title":"Towards Training-free Anomaly Detection with Vision and Language Foundation Models","created":"2025-03-24","cited_by_count":26,"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":"2308.13142","title":"A Survey of Diffusion Based Image Generation Models: Issues and Their Solutions","created":"2023-08-25","cited_by_count":25,"area":"diffusion"},{"id":"2305.14428","title":"Prompting Language-Informed Distribution for Compositional Zero-Shot Learning","created":"2023-05-23","cited_by_count":24,"area":null},{"id":"2401.17221","title":"MouSi: Poly-Visual-Expert Vision-Language Models","created":"2024-01-30","cited_by_count":24,"area":"mllm"},{"id":"2404.18624","title":"Do Vision & Language Decoders use Images and Text equally? How Self-consistent are their Explanations?","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2405.02951","title":"iSEARLE: Improving Textual Inversion for Zero-Shot Composed Image Retrieval","created":"2024-05-05","cited_by_count":24,"area":null},{"id":"2406.13807","title":"AlanaVLM: A Multimodal Embodied AI Foundation Model for Egocentric Video Understanding","created":"2024-06-19","cited_by_count":23,"area":null},{"id":"2407.16772","title":"VisMin: Visual Minimal-Change Understanding","created":"2024-07-23","cited_by_count":23,"area":"mllm"},{"id":"2409.15477","title":"MediConfusion: Can you trust your AI radiologist? Probing the reliability of multimodal medical foundation models","created":"2024-09-23","cited_by_count":23,"area":"mllm"}],"next_cursor":"100"}