{"total":561,"rows":[{"id":"2301.13826","title":"Attend-and-Excite: Attention-Based Semantic Guidance for Text-to-Image Diffusion Models","created":"2023-01-31","cited_by_count":702,"area":"diffusion"},{"id":"2401.15947","title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","created":"2024-01-29","cited_by_count":300,"area":"mllm"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2307.14539","title":"Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models","created":"2023-07-26","cited_by_count":273,"area":"mllm"},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2309.00236","title":"Image Hijacks: Adversarial Images can Control Generative Models at Runtime","created":"2023-09-01","cited_by_count":172,"area":null},{"id":"2411.04996","title":"Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Models","created":"2024-11-07","cited_by_count":163,"area":null},{"id":"2305.18274","title":"Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors","created":"2023-05-29","cited_by_count":160,"area":"diffusion"},{"id":"2406.01506","title":"The Geometry of Categorical and Hierarchical Concepts in Large Language Models","created":"2024-06-03","cited_by_count":159,"area":null},{"id":"2302.00402","title":"mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video","created":"2023-02-01","cited_by_count":154,"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":"2407.12580","title":"E5-V: Universal Embeddings with Multimodal Large Language Models","created":"2024-07-17","cited_by_count":126,"area":"mllm"},{"id":"2307.10490","title":"Abusing Images and Sounds for Indirect Instruction Injection in Multi-Modal LLMs","created":"2023-07-19","cited_by_count":124,"area":"mllm"},{"id":"2211.16198","title":"SuS-X: Training-Free Name-Only Transfer of Vision-Language Models","created":"2022-11-28","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":"2209.03430","title":"Foundations and Trends in Multimodal Machine Learning: Principles, Challenges, and Open Questions","created":"2022-09-07","cited_by_count":116,"area":null},{"id":"2403.11207","title":"MindEye2: Shared-Subject Models Enable fMRI-To-Image With 1 Hour of Data","created":"2024-03-17","cited_by_count":109,"area":null},{"id":"2403.18406","title":"An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM","created":"2024-03-27","cited_by_count":97,"area":"lr"},{"id":"2204.01694","title":"\"This is my unicorn, Fluffy\": Personalizing frozen vision-language representations","created":"2022-04-04","cited_by_count":95,"area":null},{"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":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84,"area":null},{"id":"2305.19270","title":"Learning without Forgetting for Vision-Language Models","created":"2023-05-30","cited_by_count":79,"area":"mllm"},{"id":"2403.03867","title":"On the Origins of Linear Representations in Large Language Models","created":"2024-03-06","cited_by_count":79,"area":null},{"id":"2506.18902","title":"jina-embeddings-v4: Universal Embeddings for Multimodal Multilingual Retrieval","created":"2025-06-23","cited_by_count":76,"area":null},{"id":"2311.10707","title":"Multimodal Representation Learning by Alternating Unimodal Adaptation","created":"2023-11-17","cited_by_count":75,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2308.09300","title":"V2A-Mapper: A Lightweight Solution for Vision-to-Audio Generation by Connecting Foundation Models","created":"2023-08-18","cited_by_count":65,"area":null},{"id":"2408.01432","title":"VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance","created":"2024-07-18","cited_by_count":65,"area":null},{"id":"2307.15199","title":"PromptStyler: Prompt-driven Style Generation for Source-free Domain Generalization","created":"2023-07-27","cited_by_count":59,"area":null},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58,"area":null},{"id":"2304.01008","title":"Self-Supervised Multimodal Learning: A Survey","created":"2023-03-31","cited_by_count":58,"area":null},{"id":"2211.11427","title":"Expectation-Maximization Contrastive Learning for Compact Video-and-Language Representations","created":"2022-11-21","cited_by_count":57,"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":"2212.08045","title":"CLIPPO: Image-and-Language Understanding from Pixels Only","created":"2022-12-15","cited_by_count":55,"area":null},{"id":"2505.12540","title":"Harnessing the Universal Geometry of Embeddings","created":"2025-05-18","cited_by_count":55,"area":null},{"id":"2412.11959","title":"Gramian Multimodal Representation Learning and Alignment","created":"2024-12-16","cited_by_count":54,"area":null},{"id":"2303.05952","title":"Understanding and Constructing Latent Modality Structures in Multi-modal Representation Learning","created":"2023-03-10","cited_by_count":53,"area":null},{"id":"2402.10962","title":"Measuring and Controlling Instruction (In)Stability in Language Model Dialogs","created":"2024-02-13","cited_by_count":53,"area":null},{"id":"2308.11485","title":"Composed Image Retrieval using Contrastive Learning and Task-oriented CLIP-based Features","created":"2023-08-22","cited_by_count":52,"area":null},{"id":"2310.02071","title":"Towards End-to-End Embodied Decision Making via Multi-modal Large Language Model: Explorations with GPT4-Vision and Beyond","created":"2023-10-03","cited_by_count":51,"area":"mllm"},{"id":"2302.14383","title":"Linear Spaces of Meanings: Compositional Structures in Vision-Language Models","created":"2023-02-28","cited_by_count":48,"area":"mllm"},{"id":"2310.19795","title":"SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization","created":"2023-10-30","cited_by_count":48,"area":null},{"id":"2211.01427","title":"CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language","created":"2022-11-02","cited_by_count":46,"area":null},{"id":"2311.05709","title":"OmniVec: Learning robust representations with cross modal sharing","created":"2023-11-07","cited_by_count":44,"area":null},{"id":"2405.00571","title":"Spherical Linear Interpolation and Text-Anchoring for Zero-shot Composed Image Retrieval","created":"2024-05-01","cited_by_count":44,"area":null},{"id":"2504.14348","title":"Manipulating Multimodal Agents via Cross-Modal Prompt Injection","created":"2025-04-19","cited_by_count":44,"area":"mllm"},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43,"area":null},{"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":"2411.14517","title":"The Double-Ellipsoid Geometry of CLIP","created":"2024-11-21","cited_by_count":42,"area":null},{"id":"2312.07330","title":"Learned representation-guided diffusion models for large-image generation","created":"2023-12-12","cited_by_count":40,"area":"diffusion"},{"id":"2304.01752","title":"Black Box Few-Shot Adaptation for Vision-Language models","created":"2023-04-04","cited_by_count":39,"area":"mllm"},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2410.00263","title":"Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation","created":"2024-09-30","cited_by_count":39,"area":null},{"id":"2306.04507","title":"Improving neural network representations using human similarity judgments","created":"2023-06-07","cited_by_count":38,"area":null},{"id":"2211.15388","title":"Shifted Diffusion for Text-to-image Generation","created":"2022-11-24","cited_by_count":37,"area":"diffusion"},{"id":"2412.08802","title":"jina-clip-v2: Multilingual Multimodal Embeddings for Text and Images","created":"2024-12-11","cited_by_count":37,"area":null},{"id":"2210.17020","title":"A Law of Data Separation in Deep Learning","created":"2022-10-31","cited_by_count":36,"area":null},{"id":"2305.14381","title":"Connecting Multi-modal Contrastive Representations","created":"2023-05-22","cited_by_count":36,"area":null},{"id":"2406.14479","title":"Tracing Representation Progression: Analyzing and Enhancing Layer-Wise Similarity","created":"2024-06-20","cited_by_count":36,"area":null},{"id":"2504.16109","title":"Representation Learning for Tabular Data: A Comprehensive Survey","created":"2025-04-17","cited_by_count":36,"area":null},{"id":"2212.04473","title":"Diffusion Guided Domain Adaptation of Image Generators","created":"2022-12-08","cited_by_count":35,"area":"diffusion"},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35,"area":"mllm"},{"id":"2308.03793","title":"ReCLIP: Refine Contrastive Language Image Pre-Training with Source Free Domain Adaptation","created":"2023-08-04","cited_by_count":35,"area":"mllm"},{"id":"2506.09047","title":"Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs","created":"2025-06-10","cited_by_count":35,"area":"mllm"},{"id":"2309.06236","title":"The first step is the hardest: Pitfalls of Representing and Tokenizing Temporal Data for Large Language Models","created":"2023-09-12","cited_by_count":34,"area":null},{"id":"2207.01887","title":"Open-Vocabulary Multi-Label Classification via Multi-Modal Knowledge Transfer","created":"2022-07-05","cited_by_count":33,"area":null},{"id":"2311.08089","title":"Improving In-context Learning of Multilingual Generative Language Models with Cross-lingual Alignment","created":"2023-11-14","cited_by_count":33,"area":null},{"id":"2306.00738","title":"ReFACT: Updating Text-to-Image Models by Editing the Text Encoder","created":"2023-06-01","cited_by_count":32,"area":null},{"id":"2403.02899","title":"Domain-Agnostic Mutual Prompting for Unsupervised Domain Adaptation","created":"2024-03-05","cited_by_count":32,"area":null},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2403.11650","title":"Prioritized Semantic Learning for Zero-shot Instance Navigation","created":"2024-03-18","cited_by_count":31,"area":null},{"id":"2406.18043","title":"GenRL: Multimodal-foundation world models for generalization in embodied agents","created":"2024-06-26","cited_by_count":31,"area":"wm"},{"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":"2503.19900","title":"CAFe: Unifying Representation and Generation with Contrastive-Autoregressive Finetuning","created":"2025-03-25","cited_by_count":31,"area":"mllm"},{"id":"2405.01926","title":"Auto-Encoding Morph-Tokens for Multimodal LLM","created":"2024-05-03","cited_by_count":30,"area":"mllm"},{"id":"2203.03897","title":"Geodesic Multi-Modal Mixup for Robust Fine-Tuning","created":"2022-03-08","cited_by_count":29,"area":null},{"id":"2308.11804","title":"Adversarial Illusions in Multi-Modal Embeddings","created":"2023-08-22","cited_by_count":29,"area":null},{"id":"2503.04207","title":"Bridging the Vision-Brain Gap with an Uncertainty-Aware Blur Prior","created":"2025-03-06","cited_by_count":29,"area":null},{"id":"2303.13273","title":"TAPS3D: Text-Guided 3D Textured Shape Generation from Pseudo Supervision","created":"2023-03-23","cited_by_count":28,"area":null},{"id":"2404.04072","title":"Label Propagation for Zero-shot Classification with Vision-Language Models","created":"2024-04-05","cited_by_count":28,"area":"mllm"},{"id":"2501.01346","title":"Large Vision-Language Model Alignment and Misalignment: A Survey Through the Lens of Explainability","created":"2025-01-02","cited_by_count":28,"area":"mllm"},{"id":"2209.04145","title":"ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation","created":"2022-09-09","cited_by_count":27,"area":null},{"id":"2303.06285","title":"DeltaEdit: Exploring Text-free Training for Text-Driven Image Manipulation","created":"2023-03-11","cited_by_count":27,"area":null},{"id":"2310.19752","title":"Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP","created":"2023-10-30","cited_by_count":27,"area":"mllm"},{"id":"2312.01998","title":"Language-only Efficient Training of Zero-shot Composed Image Retrieval","created":"2023-12-04","cited_by_count":27,"area":null},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2507.19024","title":"A Survey of Multimodal Hallucination Evaluation and Detection","created":"2025-07-25","cited_by_count":27,"area":"mllm"},{"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":"2405.18570","title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap","created":"2024-05-28","cited_by_count":26,"area":null},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26,"area":null},{"id":"2305.11965","title":"Not All Semantics are Created Equal: Contrastive Self-supervised Learning with Automatic Temperature Individualization","created":"2023-05-19","cited_by_count":25,"area":null},{"id":"2403.17924","title":"AID: Attention Interpolation of Text-to-Image Diffusion","created":"2024-03-26","cited_by_count":25,"area":"diffusion"},{"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":"2405.16700","title":"Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs","created":"2024-05-26","cited_by_count":23,"area":null},{"id":"2406.03496","title":"Wings: Learning Multimodal LLMs without Text-only Forgetting","created":"2024-06-05","cited_by_count":23,"area":"mllm"},{"id":"2406.17639","title":"Mitigate the Gap: Investigating Approaches for Improving Cross-Modal Alignment in CLIP","created":"2024-06-25","cited_by_count":23,"area":null},{"id":"2408.14471","title":"A Practitioner's Guide to Continual Multimodal Pretraining","created":"2024-08-26","cited_by_count":23,"area":null},{"id":"2507.19264","title":"SimMLM: A Simple Framework for Multi-modal Learning with Missing Modality","created":"2025-07-25","cited_by_count":23,"area":null},{"id":"2509.16645","title":"ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents","created":"2025-09-20","cited_by_count":23,"area":"lr"},{"id":"2205.11501","title":"VQA-GNN: Reasoning with Multimodal Knowledge via Graph Neural Networks for Visual Question Answering","created":"2022-05-23","cited_by_count":22,"area":null}],"next_cursor":"100"}