{"list":"other","total":55,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"2306.05685","title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena","created":"2023-06-09","cited_by_count":8626},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"1411.5726","title":"CIDEr: Consensus-based Image Description Evaluation","created":"2014-11-20","cited_by_count":2046},{"id":"2005.10242","title":"Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hypersphere","created":"2020-05-20","cited_by_count":1405},{"id":"1711.11279","title":"Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)","created":"2017-11-30","cited_by_count":1319},{"id":"2007.04612","title":"Concept Bottleneck Models","created":"2020-07-09","cited_by_count":1032},{"id":"1607.08822","title":"SPICE: Semantic Propositional Image Caption Evaluation","created":"2016-07-29","cited_by_count":824},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"2301.12503","title":"AudioLDM: Text-to-Audio Generation with Latent Diffusion Models","created":"2023-01-29","cited_by_count":599},{"id":"2203.02053","title":"Mind the Gap: Understanding the Modality Gap in Multi-modal Contrastive Representation Learning","created":"2022-03-03","cited_by_count":561},{"id":"1910.09387","title":"Clotho: An Audio Captioning Dataset","created":"2019-10-21","cited_by_count":358},{"id":"2308.05734","title":"AudioLDM 2: Learning Holistic Audio Generation with Self-supervised Pretraining","created":"2023-08-10","cited_by_count":344},{"id":"2205.15480","title":"Post-hoc Concept Bottleneck Models","created":"2022-05-31","cited_by_count":293},{"id":"2304.06129","title":"Label-Free Concept Bottleneck Models","created":"2023-04-12","cited_by_count":285},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"2305.11834","title":"Pengi: An Audio Language Model for Audio Tasks","created":"2023-05-19","cited_by_count":220},{"id":"2211.10154","title":"CRAFT: Concept Recursive Activation FacTorization for Explainability","created":"2022-11-17","cited_by_count":178},{"id":"2202.00874","title":"HTS-AT: A Hierarchical Token-Semantic Audio Transformer for Sound Classification and Detection","created":"2022-02-02","cited_by_count":176},{"id":"2402.10376","title":"Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)","created":"2024-02-16","cited_by_count":119},{"id":"1612.00370","title":"Improved Image Captioning via Policy Gradient optimization of SPIDEr","created":"2016-12-01","cited_by_count":113},{"id":"2306.07304","title":"A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation","created":"2023-06-11","cited_by_count":109},{"id":"2211.00575","title":"Text-Only Training for Image Captioning using Noise-Injected CLIP","created":"2022-11-01","cited_by_count":91},{"id":"2303.03032","title":"DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training","created":"2023-03-06","cited_by_count":84},{"id":"2309.05767","title":"Natural Language Supervision for General-Purpose Audio Representations","created":"2023-09-11","cited_by_count":61},{"id":"2302.04269","title":"Diagnosing and Rectifying Vision Models using Language","created":"2023-02-08","cited_by_count":58},{"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},{"id":"2301.11911","title":"Multi-dimensional concept discovery (MCD): A unifying framework with completeness guarantees","created":"2023-01-27","cited_by_count":50},{"id":"2309.11500","title":"Auto-ACD: A Large-scale Dataset for Audio-Language Representation Learning","created":"2023-09-20","cited_by_count":33},{"id":"2309.09836","title":"RECAP: Retrieval-Augmented Audio Captioning","created":"2023-09-18","cited_by_count":27},{"id":"2401.08567","title":"Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data","created":"2024-01-16","cited_by_count":27},{"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},{"id":"2405.18570","title":"It's Not a Modality Gap: Characterizing and Addressing the Contrastive Gap","created":"2024-05-28","cited_by_count":26},{"id":"2412.07909","title":"Explaining and Mitigating the Modality Gap in Contrastive Multimodal Learning","created":"2024-12-10","cited_by_count":26},{"id":"2411.18953","title":"AudioSetCaps: An Enriched Audio-Caption Dataset using Automated Generation Pipeline with Large Audio and Language Models","created":"2024-11-28","cited_by_count":21},{"id":"2404.12652","title":"Pre-trained Vision-Language Models Learn Discoverable Visual Concepts","created":"2024-04-19","cited_by_count":16},{"id":"2407.04416","title":"Sound-VECaps: Improving Audio Generation with Visual Enhanced Captions","created":"2024-07-05","cited_by_count":15},{"id":"2309.07372","title":"Training Audio Captioning Models without Audio","created":"2023-09-14","cited_by_count":12},{"id":"2507.19054","title":"Closing the Modality Gap for Mixed Modality Search","created":"2025-07-25","cited_by_count":12},{"id":"2311.08396","title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","created":"2023-11-14","cited_by_count":11},{"id":"2410.09472","title":"DRCap: Decoding CLAP Latents with Retrieval-Augmented Generation for Zero-shot Audio Captioning","created":"2024-10-12","cited_by_count":11},{"id":"2510.03268","title":"Decipher the Modality Gap in Multimodal Contrastive Learning: From Convergent Representations to Pairwise Alignment","created":"2025-09-27","cited_by_count":10},{"id":"2309.12242","title":"Weakly-supervised Automated Audio Captioning via text only training","created":"2023-09-21","cited_by_count":8},{"id":"2412.14384","title":"I0T: Embedding Standardization Method Towards Zero Modality Gap","created":"2024-12-18","cited_by_count":8},{"id":"2406.06295","title":"Zero-Shot Audio Captioning Using Soft and Hard Prompts","created":"2024-06-10","cited_by_count":7},{"id":"2503.12131","title":"DiffGAP: A Lightweight Diffusion Module in Contrastive Space for Bridging Cross-Model Gap","created":"2025-03-15","cited_by_count":7},{"id":"2506.13831","title":"Quantifying Structure in CLIP Embeddings: A Statistical Framework for Concept Interpretation","created":"2025-06-16","cited_by_count":6},{"id":"2504.14076","title":"Transformation of audio embeddings into interpretable, concept-based representations","created":"2025-04-18","cited_by_count":5},{"id":"2309.03884","title":"Zero-Shot Audio Captioning via Audibility Guidance","created":"2023-09-07","cited_by_count":3},{"id":"2509.14003","title":"RFM-Editing: Rectified Flow Matching for Text-guided Audio Editing","created":"2025-09-17","cited_by_count":3},{"id":"2510.11330","title":"Diffusion-Link: Diffusion Probabilistic Model for Bridging the Audio-Text Modality Gap","created":"2025-10-13","cited_by_count":3},{"id":"2509.16649","title":"AISTAT lab system for DCASE2025 Task6: Language-based audio retrieval","created":"2025-09-20","cited_by_count":1},{"id":"2603.13884","title":"SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis","created":"2026-03-14","cited_by_count":1}],"next_cursor":null}