{"total":65,"rows":[{"id":"2310.05914","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","created":"2023-10-09","cited_by_count":100,"area":null},{"id":"2411.17040","title":"Multimodal Alignment and Fusion: A Survey","created":"2024-11-26","cited_by_count":74,"area":null},{"id":"2307.15220","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","created":"2023-07-27","cited_by_count":68,"area":null},{"id":"2303.16899","title":"AutoAD: Movie Description in Context","created":"2023-03-29","cited_by_count":50,"area":null},{"id":"2311.17435","title":"MM-Narrator: Narrating Long-form Videos with Multimodal In-Context Learning","created":"2023-11-29","cited_by_count":46,"area":null},{"id":"2403.03715","title":"MeaCap: Memory-Augmented Zero-shot Image Captioning","created":"2024-03-06","cited_by_count":35,"area":null},{"id":"2307.16525","title":"Transferable Decoding with Visual Entities for Zero-Shot Image Captioning","created":"2023-07-31","cited_by_count":34,"area":null},{"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":"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":"2302.03675","title":"Auditing Gender Presentation Differences in Text-to-Image Models","created":"2023-02-07","cited_by_count":22,"area":null},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2403.10153","title":"Improving Medical Multi-modal Contrastive Learning with Expert Annotations","created":"2024-03-15","cited_by_count":16,"area":null},{"id":"2407.21757","title":"Learning Video Context as Interleaved Multimodal Sequences","created":"2024-07-31","cited_by_count":16,"area":null},{"id":"2312.08865","title":"Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning","created":"2023-12-14","cited_by_count":14,"area":null},{"id":"2308.13218","title":"MultiCapCLIP: Auto-Encoding Prompts for Zero-Shot Multilingual Visual Captioning","created":"2023-08-25","cited_by_count":13,"area":null},{"id":"2504.01020","title":"Shot-by-Shot: Film-Grammar-Aware Training-Free Audio Description Generation","created":"2025-04-01","cited_by_count":13,"area":null},{"id":"2310.16492","title":"On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection","created":"2023-10-25","cited_by_count":12,"area":null},{"id":"2401.02347","title":"Mining Fine-Grained Image-Text Alignment for Zero-Shot Captioning via Text-Only Training","created":"2024-01-04","cited_by_count":12,"area":null},{"id":"2411.18180","title":"DistinctAD: Distinctive Audio Description Generation in Contexts","created":"2024-11-27","cited_by_count":12,"area":null},{"id":"2403.12693","title":"As Firm As Their Foundations: Can open-sourced foundation models be used to create adversarial examples for downstream tasks?","created":"2024-03-19","cited_by_count":11,"area":null},{"id":"2409.18046","title":"IFCap: Image-like Retrieval and Frequency-based Entity Filtering for Zero-shot Captioning","created":"2024-09-26","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":"2405.13911","title":"TOPA: Extending Large Language Models for Video Understanding via Text-Only Pre-Alignment","created":"2024-05-22","cited_by_count":10,"area":null},{"id":"2309.17175","title":"TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8,"area":null},{"id":"2503.13385","title":"Scale Efficient Training for Large Datasets","created":"2025-03-17","cited_by_count":7,"area":null},{"id":"2404.17498","title":"Learning text-to-video retrieval from image captioning","created":"2024-04-26","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":"2410.01529","title":"Robo-MUTUAL: Robotic Multimodal Task Specification via Unimodal Learning","created":"2024-10-02","cited_by_count":6,"area":null},{"id":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2303.06458","title":"ZeroNLG: Aligning and Autoencoding Domains for Zero-Shot Multimodal and Multilingual Natural Language Generation","created":"2023-03-11","cited_by_count":4,"area":null},{"id":"2307.16399","title":"Visual Captioning at Will: Describing Images and Videos Guided by a Few Stylized Sentences","created":"2023-07-31","cited_by_count":4,"area":null},{"id":"2312.01523","title":"SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise","created":"2023-12-03","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":"2403.18969","title":"A Survey on Large Language Models from Concept to Implementation","created":"2024-03-27","cited_by_count":4,"area":null},{"id":"2405.18258","title":"Text-only Synthesis for Image Captioning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2505.19614","title":"Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning","created":"2025-05-26","cited_by_count":4,"area":null},{"id":"2308.08881","title":"Text-Only Training for Visual Storytelling","created":"2023-08-17","cited_by_count":3,"area":null},{"id":"2310.10543","title":"ViPE: Visualise Pretty-much Everything","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2501.09555","title":"Text-driven Adaptation of Foundation Models for Few-shot Surgical Workflow Analysis","created":"2025-01-16","cited_by_count":3,"area":null},{"id":"2507.18616","title":"SynC: Synthetic Image Caption Dataset Refinement with One-to-many Mapping for Zero-shot Image Captioning","created":"2025-07-24","cited_by_count":3,"area":null},{"id":"2304.13742","title":"TR0N: Translator Networks for 0-Shot Plug-and-Play Conditional Generation","created":"2023-04-26","cited_by_count":2,"area":null},{"id":"2307.01969","title":"Multimodal Prompt Learning for Product Title Generation with Extremely Limited Labels","created":"2023-07-05","cited_by_count":2,"area":null},{"id":"2307.03798","title":"Fooling Contrastive Language-Image Pre-trained Models with CLIPMasterPrints","created":"2023-07-07","cited_by_count":2,"area":null},{"id":"2510.02898","title":"One Patch to Caption Them All: A Unified Zero-Shot Captioning Framework","created":"2025-10-03","cited_by_count":2,"area":null},{"id":"2312.05588","title":"Language-assisted Vision Model Debugger: A Sample-Free Approach to Finding and Fixing Bugs","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2403.19193","title":"Text Data-Centric Image Captioning with Interactive Prompts","created":"2024-03-28","cited_by_count":1,"area":null},{"id":"2407.08934","title":"Compositional Structures in Neural Embedding and Interaction Decompositions","created":"2024-07-12","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2512.04309","title":"Text-Only Training for Image Captioning with Retrieval Augmentation and Modality Gap Correction","created":"2025-12-03","cited_by_count":1,"area":null},{"id":"2406.05075","title":"Diving Deep into the Motion Representation of Video-Text Models","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2409.19960","title":"TROPE: TRaining-Free Object-Part Enhancement for Seamlessly Improving Fine-Grained Zero-Shot Image Captioning","created":"2024-09-30","cited_by_count":0,"area":null},{"id":"2411.15611","title":"If you can describe it, they can see it: Cross-Modal Learning of Visual Concepts from Textual Descriptions","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2503.23679","title":"The Devil is in the Distributions: Explicit Modeling of Scene Content is Key in Zero-Shot Video Captioning","created":"2025-03-31","cited_by_count":0,"area":null},{"id":"2508.01270","title":"SGCap: Decoding Semantic Group for Zero-shot Video Captioning","created":"2025-08-02","cited_by_count":0,"area":null},{"id":"2510.05411","title":"Personalizing Retrieval using Joint Embeddings or \"the Return of Fluffy\"","created":"2025-10-06","cited_by_count":0,"area":null},{"id":"2602.23588","title":"Hyperdimensional Cross-Modal Alignment of Frozen Language and Image Models for Efficient Image Captioning","created":"2026-02-27","cited_by_count":0,"area":null},{"id":"2605.23171","title":"Understanding and Improving Noisy Embedding Techniques in Instruction Finetuning","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.29628","title":"COMET: Concept Space Dissection of the Modality Gap in Audio-Text Multimodal Contrastive Embeddings","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2607.28986","title":"Adjudicated Captioning: Multi-Agent Alignment Scoring and Consensus-Distilled Beam Arbitration for Strict Zero-Shot Image Captioning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2608.00994","title":"Entity-Faithful Repair of Synthetic Supervision for Zero-Shot Image Captioning","created":"2026-08-02","cited_by_count":0,"area":null},{"id":"2608.06972","title":"Generative Embedding Benchmark: How Much Information Survives in a Dense Embedding?","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.11013","title":"Watching Synthetic Videos: Aligning Cross-modal Representations with Visual Synthesis for Zero-shot Video Captioning","created":"2026-08-11","cited_by_count":0,"area":null},{"id":"2609.10292","title":"Isotropic Embedding Perturbations for Robust Vision Language Encoders","created":"2026-09-09","cited_by_count":0,"area":null}],"next_cursor":null}