{"list":"other","total":67,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1610.02391","title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization","created":"2016-10-07","cited_by_count":6733},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2502.13923","title":"Qwen2.5-VL Technical Report","created":"2025-02-19","cited_by_count":5587},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2412.15115","title":"Qwen2.5 Technical Report","created":"2024-12-19","cited_by_count":4942},{"id":"2004.04906","title":"Dense Passage Retrieval for Open-Domain Question Answering","created":"2020-04-10","cited_by_count":3824},{"id":"2507.06261","title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","created":"2025-07-07","cited_by_count":3796},{"id":"2303.18223","title":"A Survey of Large Language Models","created":"2023-03-31","cited_by_count":2576},{"id":"2312.10997","title":"Retrieval-Augmented Generation for Large Language Models: A Survey","created":"2023-12-18","cited_by_count":2212},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2112.03570","title":"Membership Inference Attacks From First Principles","created":"2021-12-07","cited_by_count":878},{"id":"2501.17811","title":"Janus-Pro: Unified Multimodal Understanding and Generation with Data and Model Scaling","created":"2025-01-29","cited_by_count":812},{"id":"2301.12652","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","created":"2023-01-30","cited_by_count":792},{"id":"2308.03281","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","created":"2023-08-07","cited_by_count":723},{"id":"2308.10792","title":"Instruction Tuning for Large Language Models: A Survey","created":"2023-08-21","cited_by_count":623},{"id":"2009.07896","title":"Captum: A unified and generic model interpretability library for PyTorch","created":"2020-09-16","cited_by_count":547},{"id":"1806.01246","title":"ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models","created":"2018-06-04","cited_by_count":498},{"id":"2405.06211","title":"A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models","created":"2024-05-10","cited_by_count":452},{"id":"2007.14321","title":"Label-Only Membership Inference Attacks","created":"2020-07-28","cited_by_count":388},{"id":"2310.16789","title":"Detecting Pretraining Data from Large Language Models","created":"2023-10-25","cited_by_count":387},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2103.07853","title":"Membership Inference Attacks on Machine Learning: A Survey","created":"2021-03-14","cited_by_count":321},{"id":"2103.01913","title":"WIT: Wikipedia-based Image Text Dataset for Multimodal Multilingual Machine Learning","created":"2021-03-02","cited_by_count":287},{"id":"2401.13601","title":"MM-LLMs: Recent Advances in MultiModal Large Language Models","created":"2024-01-24","cited_by_count":278},{"id":"2309.07430","title":"Adapted Large Language Models Can Outperform Medical Experts in Clinical Text Summarization","created":"2023-09-14","cited_by_count":246},{"id":"2006.06224","title":"A Primer on Zeroth-Order Optimization in Signal Processing and Machine Learning","created":"2020-06-11","cited_by_count":162},{"id":"2311.12075","title":"BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning","created":"2023-11-20","cited_by_count":115},{"id":"2406.04031","title":"Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt","created":"2024-06-06","cited_by_count":109},{"id":"2409.15700","title":"Making Text Embedders Few-Shot Learners","created":"2024-09-24","cited_by_count":79},{"id":"2411.15296","title":"MME-Survey: A Comprehensive Survey on Evaluation of Multimodal LLMs","created":"2024-11-22","cited_by_count":72},{"id":"2406.18844","title":"Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift","created":"2024-06-27","cited_by_count":49},{"id":"2502.18943","title":"Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models","created":"2025-02-26","cited_by_count":37},{"id":"2504.08748","title":"A Survey of Multimodal Retrieval-Augmented Generation","created":"2025-03-26","cited_by_count":37},{"id":"2312.05491","title":"Using Captum to Explain Generative Language Models","created":"2023-12-09","cited_by_count":33},{"id":"2411.02902","title":"Membership Inference Attacks against Large Vision-Language Models","created":"2024-11-05","cited_by_count":33},{"id":"2305.14888","title":"Privacy Implications of Retrieval-Based Language Models","created":"2023-05-24","cited_by_count":32},{"id":"2303.00534","title":"RAMM: Retrieval-augmented Biomedical Visual Question Answering with Multi-modal Pre-training","created":"2023-03-01","cited_by_count":31},{"id":"2407.00600","title":"GenderBias-\\emph{VL}: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing","created":"2024-06-30","cited_by_count":31},{"id":"2412.06157","title":"Membership Inference Attacks and Defenses in Federated Learning: A Survey","created":"2024-12-09","cited_by_count":31},{"id":"2501.18624","title":"Membership Inference Attacks Against Vision-Language Models","created":"2025-01-27","cited_by_count":29},{"id":"1805.09898","title":"Performing Co-Membership Attacks Against Deep Generative Models","created":"2018-05-24","cited_by_count":26},{"id":"2406.13663","title":"Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation","created":"2024-06-19","cited_by_count":25},{"id":"2405.09800","title":"Manifold Integrated Gradients: Riemannian Geometry for Feature Attribution","created":"2024-05-16","cited_by_count":21},{"id":"2505.02214","title":"An Empirical Study of Qwen3 Quantization","created":"2025-05-04","cited_by_count":21},{"id":"2503.19338","title":"Membership Inference Attacks on Large-Scale Models: A Survey","created":"2025-03-25","cited_by_count":18},{"id":"2504.15512","title":"T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models","created":"2025-04-22","cited_by_count":18},{"id":"2305.15748","title":"ReactFace: Online Multiple Appropriate Facial Reaction Generation in Dyadic Interactions","created":"2023-05-25","cited_by_count":17},{"id":"2502.18495","title":"A Comprehensive Survey on Composed Image Retrieval","created":"2025-02-19","cited_by_count":17},{"id":"2408.08661","title":"MIA-Tuner: Adapting Large Language Models as Pre-training Text Detector","created":"2024-08-16","cited_by_count":15},{"id":"2503.13891","title":"Where do Large Vision-Language Models Look at when Answering Questions?","created":"2025-03-18","cited_by_count":15},{"id":"2402.00794","title":"ReAGent: A Model-agnostic Feature Attribution Method for Generative Language Models","created":"2024-02-01","cited_by_count":12},{"id":"2503.04833","title":"E$^2$AT: Multimodal Jailbreak Defense via Dynamic Joint Optimization for Multimodal Large Language Models","created":"2025-03-05","cited_by_count":12},{"id":"2506.12430","title":"Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025","created":"2025-06-14","cited_by_count":12},{"id":"2411.19876","title":"LUMIA: Linear probing for Unimodal and MultiModal Membership Inference Attacks leveraging internal LLM states","created":"2024-11-29","cited_by_count":10},{"id":"2410.15944","title":"Developing Retrieval Augmented Generation (RAG) based LLM Systems from PDFs: An Experience Report","created":"2024-10-21","cited_by_count":8},{"id":"2504.07787","title":"Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models","created":"2025-04-10","cited_by_count":8},{"id":"2308.04708","title":"Generative Perturbation Analysis for Probabilistic Black-Box Anomaly Attribution","created":"2023-08-09","cited_by_count":6},{"id":"2503.08240","title":"Tangentially Aligned Integrated Gradients for User-Friendly Explanations","created":"2025-03-11","cited_by_count":3},{"id":"2308.09381","title":"On Gradient-like Explanation under a Black-box Setting: When Black-box Explanations Become as Good as White-box","created":"2023-08-18","cited_by_count":2},{"id":"2401.10927","title":"Semidefinite programming relaxations and debiasing for MAXCUT-based clustering","created":"2024-01-16","cited_by_count":1}],"next_cursor":null}