{"total":150,"rows":[{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611,"area":"diffusion"},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543,"area":"wm"},{"id":"2204.00598","title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","created":"2022-04-01","cited_by_count":513,"area":"lr"},{"id":"2306.11029","title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing","created":"2023-06-19","cited_by_count":363,"area":"mllm"},{"id":"2303.14814","title":"WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation","created":"2023-03-26","cited_by_count":315,"area":null},{"id":"2302.12066","title":"Teaching CLIP to Count to Ten","created":"2023-02-23","cited_by_count":198,"area":"mllm"},{"id":"2212.07796","title":"CREPE: Can Vision-Language Foundation Models Reason Compositionally?","created":"2022-12-13","cited_by_count":181,"area":"mllm"},{"id":"2410.03051","title":"AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark","created":"2024-10-04","cited_by_count":140,"area":null},{"id":"2206.06336","title":"Language Models are General-Purpose Interfaces","created":"2022-06-13","cited_by_count":97,"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":"2407.14499","title":"Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery","created":"2024-07-19","cited_by_count":91,"area":"mechinterp"},{"id":"2205.02655","title":"Language Models Can See: Plugging Visual Controls in Text Generation","created":"2022-05-05","cited_by_count":90,"area":null},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90,"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":"2405.10825","title":"Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities","created":"2024-05-17","cited_by_count":83,"area":"lr"},{"id":"2302.02551","title":"CHiLS: Zero-Shot Image Classification with Hierarchical Label Sets","created":"2023-02-06","cited_by_count":79,"area":null},{"id":"2306.06370","title":"AutoSAM: Adapting SAM to Medical Images by Overloading the Prompt Encoder","created":"2023-06-10","cited_by_count":70,"area":null},{"id":"2303.00855","title":"Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents","created":"2023-03-01","cited_by_count":67,"area":"agents"},{"id":"2305.06386","title":"Text-To-Concept (and Back) via Cross-Model Alignment","created":"2023-05-10","cited_by_count":64,"area":null},{"id":"2303.15786","title":"HOICLIP: Efficient Knowledge Transfer for HOI Detection with Vision-Language Models","created":"2023-03-28","cited_by_count":61,"area":"mllm"},{"id":"2401.07103","title":"Leveraging Large Language Models for NLG Evaluation: Advances and Challenges","created":"2024-01-13","cited_by_count":37,"area":null},{"id":"2302.12971","title":"BrainCLIP: Bridging Brain and Visual-Linguistic Representation Via CLIP for Generic Natural Visual Stimulus Decoding","created":"2023-02-25","cited_by_count":36,"area":null},{"id":"2401.01862","title":"A Vision Check-up for Language Models","created":"2024-01-03","cited_by_count":36,"area":null},{"id":"2205.12390","title":"Toxicity Detection with Generative Prompt-based Inference","created":"2022-05-24","cited_by_count":35,"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":"2303.02437","title":"ConZIC: Controllable Zero-shot Image Captioning by Sampling-Based Polishing","created":"2023-03-04","cited_by_count":33,"area":null},{"id":"2406.14595","title":"Adversaries Can Misuse Combinations of Safe Models","created":"2024-06-20","cited_by_count":32,"area":null},{"id":"2205.12630","title":"Multimodal Knowledge Alignment with Reinforcement Learning","created":"2022-05-25","cited_by_count":30,"area":null},{"id":"2210.11522","title":"Composing Ensembles of Pre-trained Models via Iterative Consensus","created":"2022-10-20","cited_by_count":28,"area":null},{"id":"2303.02506","title":"Prismer: A Vision-Language Model with Multi-Task Experts","created":"2023-03-04","cited_by_count":28,"area":"mllm"},{"id":"2308.09383","title":"Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events","created":"2023-08-18","cited_by_count":28,"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":"2204.04908","title":"No Token Left Behind: Explainability-Aided Image Classification and Generation","created":"2022-04-11","cited_by_count":25,"area":null},{"id":"2207.11100","title":"Zero-Shot Video Captioning with Evolving Pseudo-Tokens","created":"2022-07-22","cited_by_count":25,"area":null},{"id":"2212.13563","title":"Noise-aware Learning from Web-crawled Image-Text Data for Image Captioning","created":"2022-12-27","cited_by_count":22,"area":null},{"id":"2305.13050","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","created":"2023-05-22","cited_by_count":22,"area":"diffusion"},{"id":"2307.05151","title":"ExFaceGAN: Exploring Identity Directions in GAN's Learned Latent Space for Synthetic Identity Generation","created":"2023-07-11","cited_by_count":22,"area":null},{"id":"2302.14794","title":"Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning","created":"2023-02-28","cited_by_count":20,"area":null},{"id":"2307.06526","title":"AvatarFusion: Zero-shot Generation of Clothing-Decoupled 3D Avatars Using 2D Diffusion","created":"2023-07-13","cited_by_count":20,"area":null},{"id":"2310.04420","title":"BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity","created":"2023-10-06","cited_by_count":19,"area":null},{"id":"2407.08521","title":"Emergent Visual-Semantic Hierarchies in Image-Text Representations","created":"2024-07-11","cited_by_count":19,"area":null},{"id":"2408.10202","title":"SANER: Annotation-free Societal Attribute Neutralizer for Debiasing CLIP","created":"2024-08-19","cited_by_count":19,"area":"mllm"},{"id":"2303.13396","title":"Zero-guidance Segmentation Using Zero Segment Labels","created":"2023-03-23","cited_by_count":18,"area":null},{"id":"2404.17806","title":"T-CLAP: Temporal-Enhanced Contrastive Language-Audio Pretraining","created":"2024-04-27","cited_by_count":18,"area":null},{"id":"2305.19821","title":"LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting","created":"2023-05-31","cited_by_count":17,"area":"rag"},{"id":"2307.16686","title":"Guiding Image Captioning Models Toward More Specific Captions","created":"2023-07-31","cited_by_count":17,"area":null},{"id":"2210.02506","title":"Large Language Models are Pretty Good Zero-Shot Video Game Bug Detectors","created":"2022-10-05","cited_by_count":14,"area":null},{"id":"2303.12208","title":"MAGVLT: Masked Generative Vision-and-Language Transformer","created":"2023-03-21","cited_by_count":14,"area":null},{"id":"2310.16781","title":"Kiki or Bouba? Sound Symbolism in Vision-and-Language Models","created":"2023-10-25","cited_by_count":14,"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":"2405.15587","title":"Composed Image Retrieval for Remote Sensing","created":"2024-05-24","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":"2404.02157","title":"Segment Any 3D Object with Language","created":"2024-04-02","cited_by_count":13,"area":null},{"id":"2407.20341","title":"BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues","created":"2024-07-29","cited_by_count":13,"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":"2410.13016","title":"Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge","created":"2024-10-16","cited_by_count":12,"area":null},{"id":"2206.09358","title":"What is Where by Looking: Weakly-Supervised Open-World Phrase-Grounding without Text Inputs","created":"2022-06-19","cited_by_count":11,"area":null},{"id":"2303.13455","title":"CoBIT: A Contrastive Bi-directional Image-Text Generation Model","created":"2023-03-23","cited_by_count":11,"area":null},{"id":"2304.13273","title":"From Association to Generation: Text-only Captioning by Unsupervised Cross-modal Mapping","created":"2023-04-26","cited_by_count":11,"area":"mllm"},{"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,"area":null},{"id":"2404.09632","title":"Bridging Vision and Language Spaces with Assignment Prediction","created":"2024-04-15","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":"2309.01617","title":"DeViL: Decoding Vision features into Language","created":"2023-09-04","cited_by_count":10,"area":null},{"id":"2310.03957","title":"Understanding prompt engineering may not require rethinking generalization","created":"2023-10-06","cited_by_count":10,"area":"lr"},{"id":"2503.20308","title":"Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics","created":"2025-03-26","cited_by_count":10,"area":null},{"id":"2602.07026","title":"Modality Gap-Driven Subspace Alignment Training Paradigm For Multimodal Large Language Models","created":"2026-02-02","cited_by_count":10,"area":"mllm"},{"id":"2312.08648","title":"CLIP-guided Federated Learning on Heterogeneous and Long-Tailed Data","created":"2023-12-14","cited_by_count":9,"area":null},{"id":"2211.07275","title":"Zero-shot Image Captioning by Anchor-augmented Vision-Language Space Alignment","created":"2022-11-14","cited_by_count":8,"area":null},{"id":"2305.19108","title":"DisCLIP: Open-Vocabulary Referring Expression Generation","created":"2023-05-30","cited_by_count":8,"area":null},{"id":"2403.01139","title":"ParallelPARC: A Scalable Pipeline for Generating Natural-Language Analogies","created":"2024-03-02","cited_by_count":8,"area":null},{"id":"2406.13912","title":"From Descriptive Richness to Bias: Unveiling the Dark Side of Generative Image Caption Enrichment","created":"2024-06-20","cited_by_count":8,"area":"mllm"},{"id":"2407.05578","title":"FALIP: Visual Prompt as Foveal Attention Boosts CLIP Zero-Shot Performance","created":"2024-07-08","cited_by_count":8,"area":null},{"id":"2407.07478","title":"EA-VTR: Event-Aware Video-Text Retrieval","created":"2024-07-10","cited_by_count":8,"area":null},{"id":"2501.00962","title":"OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypes","created":"2025-01-01","cited_by_count":8,"area":null},{"id":"2502.16427","title":"Fine-Grained Captioning of Long Videos through Scene Graph Consolidation","created":"2025-02-23","cited_by_count":8,"area":"mllm"},{"id":"2211.16504","title":"Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles","created":"2022-11-29","cited_by_count":7,"area":"mllm"},{"id":"2305.18072","title":"Image Captioning with Multi-Context Synthetic Data","created":"2023-05-29","cited_by_count":7,"area":"diffusion"},{"id":"2311.17315","title":"Explaining CLIP's performance disparities on data from blind/low vision users","created":"2023-11-29","cited_by_count":7,"area":"mllm"},{"id":"2402.19366","title":"Exploring the Potential of Large Language Models for Improving Digital Forensic Investigation Efficiency","created":"2024-02-29","cited_by_count":7,"area":null},{"id":"2403.12026","title":"FlexCap: Describe Anything in Images in Controllable Detail","created":"2024-03-18","cited_by_count":7,"area":"mllm"},{"id":"2406.14150","title":"Multi-modal Transfer Learning between Biological Foundation Models","created":"2024-06-20","cited_by_count":7,"area":null},{"id":"2501.00437","title":"Unleashing Text-to-Image Diffusion Prior for Zero-Shot Image Captioning","created":"2024-12-31","cited_by_count":7,"area":"diffusion"},{"id":"2306.00310","title":"Prompt Algebra for Task Composition","created":"2023-06-01","cited_by_count":6,"area":null},{"id":"2309.15729","title":"MindGPT: Interpreting What You See with Non-invasive Brain Recordings","created":"2023-09-27","cited_by_count":6,"area":null},{"id":"2403.11197","title":"TAG: Guidance-free Open-Vocabulary Semantic Segmentation","created":"2024-03-17","cited_by_count":6,"area":null},{"id":"2403.19603","title":"Semantic Map-based Generation of Navigation Instructions","created":"2024-03-28","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":"2306.16649","title":"ZeroGen: Zero-shot Multimodal Controllable Text Generation with Multiple Oracles","created":"2023-06-29","cited_by_count":5,"area":null},{"id":"2309.08928","title":"In-Style: Bridging Text and Uncurated Videos with Style Transfer for Text-Video Retrieval","created":"2023-09-16","cited_by_count":5,"area":"mllm"},{"id":"2405.07046","title":"RETTA: Retrieval-Enhanced Test-Time Adaptation for Zero-Shot Video Captioning","created":"2024-05-11","cited_by_count":5,"area":null},{"id":"2407.17095","title":"MemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models","created":"2024-07-24","cited_by_count":5,"area":"diffusion"},{"id":"2408.07249","title":"Bridging Information Asymmetry in Text-video Retrieval: A Data-centric Approach","created":"2024-08-14","cited_by_count":5,"area":null},{"id":"2408.14547","title":"Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization","created":"2024-08-26","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":"2307.02682","title":"Zero-Shot Dense Video Captioning by Jointly Optimizing Text and Moment","created":"2023-07-05","cited_by_count":4,"area":null},{"id":"2309.15857","title":"A Survey on Image-text Multimodal Models","created":"2023-09-23","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}],"next_cursor":"100"}