{"list":"other","total":62,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"1705.07874","title":"A Unified Approach to Interpreting Model Predictions","created":"2017-05-22","cited_by_count":6555},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"1602.04938","title":"\"Why Should I Trust You?\": Explaining the Predictions of Any Classifier","created":"2016-02-16","cited_by_count":5070},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2107.13586","title":"Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing","created":"2021-07-28","cited_by_count":2234},{"id":"2311.16502","title":"MMMU: A Massive Multi-discipline Multimodal Understanding and Reasoning Benchmark for Expert AGI","created":"2023-11-27","cited_by_count":2080},{"id":"2306.13394","title":"MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models","created":"2023-06-23","cited_by_count":1652},{"id":"2405.21075","title":"Video-MME: The First-Ever Comprehensive Evaluation Benchmark of Multi-modal LLMs in Video Analysis","created":"2024-05-31","cited_by_count":1413},{"id":"2306.13549","title":"A Survey on Multimodal Large Language Models","created":"2023-06-23","cited_by_count":909},{"id":"2302.14045","title":"Language Is Not All You Need: Aligning Perception with Language Models","created":"2023-02-27","cited_by_count":543},{"id":"2304.09842","title":"Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models","created":"2023-04-19","cited_by_count":356},{"id":"2309.01029","title":"Explainability for Large Language Models: A Survey","created":"2023-09-02","cited_by_count":333},{"id":"2110.01691","title":"AI Chains: Transparent and Controllable Human-AI Interaction by Chaining Large Language Model Prompts","created":"2021-10-04","cited_by_count":268},{"id":"1907.04135","title":"The What-If Tool: Interactive Probing of Machine Learning Models","created":"2019-07-09","cited_by_count":207},{"id":"2108.04840","title":"Post-hoc Interpretability for Neural NLP: A Survey","created":"2021-08-10","cited_by_count":156},{"id":"2203.06566","title":"PromptChainer: Chaining Large Language Model Prompts through Visual Programming","created":"2022-03-13","cited_by_count":134},{"id":"2008.05122","title":"The Language Interpretability Tool: Extensible, Interactive Visualizations and Analysis for NLP Models","created":"2020-08-12","cited_by_count":125},{"id":"2205.10747","title":"Language Models with Image Descriptors are Strong Few-Shot Video-Language Learners","created":"2022-05-22","cited_by_count":117},{"id":"2310.11207","title":"Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanations","created":"2023-10-17","cited_by_count":90},{"id":"2302.12247","title":"Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework","created":"2023-02-23","cited_by_count":83},{"id":"2309.13633","title":"EvalLM: Interactive Evaluation of Large Language Model Prompts on User-Defined Criteria","created":"2023-09-24","cited_by_count":74},{"id":"1904.02323","title":"Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizations","created":"2019-04-04","cited_by_count":72},{"id":"2208.07852","title":"Interactive and Visual Prompt Engineering for Ad-hoc Task Adaptation with Large Language Models","created":"2022-08-16","cited_by_count":70},{"id":"2304.09337","title":"Promptify: Text-to-Image Generation through Interactive Prompt Exploration with Large Language Models","created":"2023-04-18","cited_by_count":67},{"id":"2307.09036","title":"PromptMagician: Interactive Prompt Engineering for Text-to-Image Creation","created":"2023-07-18","cited_by_count":58},{"id":"2008.09632","title":"A Survey of Visual Analytics Techniques for Machine Learning","created":"2020-08-21","cited_by_count":56},{"id":"2305.03210","title":"AttentionViz: A Global View of Transformer Attention","created":"2023-05-04","cited_by_count":50},{"id":"2009.07053","title":"Attention Flows: Analyzing and Comparing Attention Mechanisms in Language Models","created":"2020-09-03","cited_by_count":49},{"id":"1710.10777","title":"Understanding Hidden Memories of Recurrent Neural Networks","created":"2017-10-30","cited_by_count":44},{"id":"2402.05403","title":"In-Context Principle Learning from Mistakes","created":"2024-02-08","cited_by_count":44},{"id":"2302.09466","title":"RePrompt: Automatic Prompt Editing to Refine AI-Generative Art Towards Precise Expressions","created":"2023-02-19","cited_by_count":43},{"id":"2204.09007","title":"Opal: Multimodal Image Generation for News Illustration","created":"2022-04-19","cited_by_count":36},{"id":"2207.00056","title":"MultiViz: Towards Visualizing and Understanding Multimodal Models","created":"2022-06-30","cited_by_count":36},{"id":"2302.04732","title":"Zeno: An Interactive Framework for Behavioral Evaluation of Machine Learning","created":"2023-02-09","cited_by_count":33},{"id":"2310.15428","title":"ConstitutionMaker: Interactively Critiquing Large Language Models by Converting Feedback into Principles","created":"2023-10-24","cited_by_count":33},{"id":"2310.05771","title":"Foundation Models Meet Visualizations: Challenges and Opportunities","created":"2023-10-09","cited_by_count":31},{"id":"2107.08264","title":"M2Lens: Visualizing and Explaining Multimodal Models for Sentiment Analysis","created":"2021-07-17","cited_by_count":29},{"id":"2107.09234","title":"Shared Interest: Measuring Human-AI Alignment to Identify Recurring Patterns in Model Behavior","created":"2021-07-20","cited_by_count":29},{"id":"2103.14625","title":"Dodrio: Exploring Transformer Models with Interactive Visualization","created":"2021-03-26","cited_by_count":28},{"id":"2310.13127","title":"Auto-Instruct: Automatic Instruction Generation and Ranking for Black-Box Language Models","created":"2023-10-19","cited_by_count":21},{"id":"2302.07346","title":"ScatterShot: Interactive In-context Example Curation for Text Transformation","created":"2023-02-14","cited_by_count":20},{"id":"2104.00926","title":"VisQA: X-raying Vision and Language Reasoning in Transformers","created":"2021-04-02","cited_by_count":19},{"id":"2304.01964","title":"PromptAid: Prompt Exploration, Perturbation, Testing and Iteration using Visual Analytics for Large Language Models","created":"2023-04-04","cited_by_count":19},{"id":"2206.09355","title":"A Unified Understanding of Deep NLP Models for Text Classification","created":"2022-06-19","cited_by_count":18},{"id":"2310.09036","title":"MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks","created":"2023-10-13","cited_by_count":18},{"id":"2311.00738","title":"Can Foundation Models Watch, Talk and Guide You Step by Step to Make a Cake?","created":"2023-11-01","cited_by_count":18},{"id":"1907.12918","title":"EmoCo: Visual Analysis of Emotion Coherence in Presentation Videos","created":"2019-07-29","cited_by_count":13},{"id":"2108.13587","title":"T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP","created":"2021-08-31","cited_by_count":11},{"id":"2305.09758","title":"A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot","created":"2023-05-16","cited_by_count":11},{"id":"2306.04125","title":"Multimodal Fusion Interactions: A Study of Human and Automatic Quantification","created":"2023-06-07","cited_by_count":9},{"id":"2311.05085","title":"Characterizing Large Language Models as Rationalizers of Knowledge-intensive Tasks","created":"2023-11-09","cited_by_count":9},{"id":"2403.04894","title":"ConstitutionalExperts: Training a Mixture of Principle-based Prompts","created":"2024-03-07","cited_by_count":8},{"id":"2308.00401","title":"VideoPro: A Visual Analytics Approach for Interactive Video Programming","created":"2023-08-01","cited_by_count":7},{"id":"2403.04758","title":"KnowledgeVIS: Interpreting Language Models by Comparing Fill-in-the-Blank Prompts","created":"2024-03-07","cited_by_count":7},{"id":"2309.10783","title":"Language as the Medium: Multimodal Video Classification through text only","created":"2023-09-19","cited_by_count":3},{"id":"2307.12382","title":"CommonsenseVIS: Visualizing and Understanding Commonsense Reasoning Capabilities of Natural Language Models","created":"2023-07-23","cited_by_count":2}],"next_cursor":null}