{"list":"other","total":64,"rows":[{"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":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"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":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"id":"2104.08691","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","created":"2021-04-18","cited_by_count":3795},{"id":"2304.10592","title":"MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models","created":"2023-04-20","cited_by_count":2711},{"id":"1505.00468","title":"VQA: Visual Question Answering","created":"2015-05-03","cited_by_count":2506},{"id":"2305.10355","title":"Evaluating Object Hallucination in Large Vision-Language Models","created":"2023-05-17","cited_by_count":1729},{"id":"1904.08920","title":"Towards VQA Models That Can Read","created":"2019-04-18","cited_by_count":1718},{"id":"2203.12119","title":"Visual Prompt Tuning","created":"2022-03-23","cited_by_count":1681},{"id":"1910.10045","title":"Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI","created":"2019-10-22","cited_by_count":1552},{"id":"2310.01405","title":"Representation Engineering: A Top-Down Approach to AI Transparency","created":"2023-10-02","cited_by_count":1336},{"id":"2012.15723","title":"Making Pre-trained Language Models Better Few-shot Learners","created":"2020-12-31","cited_by_count":1256},{"id":"1712.09913","title":"Visualizing the Loss Landscape of Neural Nets","created":"2017-12-28","cited_by_count":1130},{"id":"2205.05638","title":"Few-Shot Parameter-Efficient Fine-Tuning is Better and Cheaper than In-Context Learning","created":"2022-05-11","cited_by_count":896},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"2211.07636","title":"EVA: Exploring the Limits of Masked Visual Representation Learning at Scale","created":"2022-11-14","cited_by_count":691},{"id":"2210.03117","title":"MaPLe: Multi-modal Prompt Learning","created":"2022-10-06","cited_by_count":687},{"id":"2403.14608","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","created":"2024-03-21","cited_by_count":656},{"id":"2302.11382","title":"A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT","created":"2023-02-21","cited_by_count":619},{"id":"2007.08745","title":"Backdoor Learning: A Survey","created":"2020-07-17","cited_by_count":426},{"id":"2106.02997","title":"Causal Abstractions of Neural Networks","created":"2021-06-06","cited_by_count":422},{"id":"2202.07123","title":"Rethinking Network Design and Local Geometry in Point Cloud: A Simple Residual MLP Framework","created":"2022-02-15","cited_by_count":379},{"id":"1910.00033","title":"Hidden Trigger Backdoor Attacks","created":"2019-09-30","cited_by_count":371},{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"1901.06706","title":"Visual Entailment: A Novel Task for Fine-Grained Image Understanding","created":"2019-01-20","cited_by_count":252},{"id":"1710.04806","title":"Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictions","created":"2017-10-13","cited_by_count":234},{"id":"2404.03592","title":"ReFT: Representation Finetuning for Language Models","created":"2024-04-04","cited_by_count":197},{"id":"2401.04925","title":"The Impact of Reasoning Step Length on Large Language Models","created":"2024-01-10","cited_by_count":153},{"id":"2201.05337","title":"A Survey of Controllable Text Generation using Transformer-based Pre-trained Language Models","created":"2022-01-14","cited_by_count":129},{"id":"2308.09936","title":"BLIVA: A Simple Multimodal LLM for Better Handling of Text-Rich Visual Questions","created":"2023-08-19","cited_by_count":125},{"id":"2012.11635","title":"A Distributional Approach to Controlled Text Generation","created":"2020-12-21","cited_by_count":119},{"id":"2212.10846","title":"From Images to Textual Prompts: Zero-shot VQA with Frozen Large Language Models","created":"2022-12-21","cited_by_count":115},{"id":"1907.09294","title":"The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanations","created":"2019-07-22","cited_by_count":97},{"id":"2303.14773","title":"BlackVIP: Black-Box Visual Prompting for Robust Transfer Learning","created":"2023-03-26","cited_by_count":70},{"id":"2307.13770","title":"E^2VPT: An Effective and Efficient Approach for Visual Prompt Tuning","created":"2023-07-25","cited_by_count":70},{"id":"2304.04947","title":"Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference","created":"2023-04-11","cited_by_count":69},{"id":"1912.02523","title":"Towards Explainable Deep Neural Networks (xDNN)","created":"2019-12-05","cited_by_count":61},{"id":"2404.07990","title":"OpenBias: Open-set Bias Detection in Text-to-Image Generative Models","created":"2024-04-11","cited_by_count":61},{"id":"2204.08831","title":"Probing for the Usage of Grammatical Number","created":"2022-04-19","cited_by_count":59},{"id":"2209.07383","title":"Visual Recognition with Deep Nearest Centroids","created":"2022-09-15","cited_by_count":59},{"id":"2310.15166","title":"Large Language Models are Visual Reasoning Coordinators","created":"2023-10-23","cited_by_count":58},{"id":"2408.12599","title":"Controllable Text Generation for Large Language Models: A Survey","created":"2024-08-22","cited_by_count":57},{"id":"1711.08792","title":"SPINE: SParse Interpretable Neural Embeddings","created":"2017-11-23","cited_by_count":55},{"id":"2411.13504","title":"Disentangling Memory and Reasoning Ability in Large Language Models","created":"2024-11-20","cited_by_count":44},{"id":"2310.19698","title":"When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations","created":"2023-10-30","cited_by_count":43},{"id":"2103.13886","title":"Robust and Accurate Object Detection via Adversarial Learning","created":"2021-03-23","cited_by_count":42},{"id":"2111.08429","title":"An Overview of Backdoor Attacks Against Deep Neural Networks and Possible Defences","created":"2021-11-16","cited_by_count":42},{"id":"2402.15179","title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing","created":"2024-02-23","cited_by_count":37},{"id":"2401.12902","title":"Facing the Elephant in the Room: Visual Prompt Tuning or Full Finetuning?","created":"2024-01-23","cited_by_count":31},{"id":"2411.01327","title":"Visual Fourier Prompt Tuning","created":"2024-11-02","cited_by_count":30},{"id":"2212.06202","title":"Doubly Right Object Recognition: A Why Prompt for Visual Rationales","created":"2022-12-12","cited_by_count":29},{"id":"2307.15054","title":"A Geometric Notion of Causal Probing","created":"2023-07-27","cited_by_count":25},{"id":"2404.13506","title":"Parameter Efficient Fine Tuning: A Comprehensive Analysis Across Applications","created":"2024-04-21","cited_by_count":25},{"id":"2207.06202","title":"Adversarially-Aware Robust Object Detector","created":"2022-07-13","cited_by_count":20},{"id":"2402.04744","title":"Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers","created":"2024-02-07","cited_by_count":18},{"id":"2006.16823","title":"Technical Report: Auxiliary Tuning and its Application to Conditional Text Generation","created":"2020-06-30","cited_by_count":17},{"id":"2312.04837","title":"Localized Symbolic Knowledge Distillation for Visual Commonsense Models","created":"2023-12-08","cited_by_count":12},{"id":"2210.07431","title":"PCFG-based Natural Language Interface Improves Generalization for Controlled Text Generation","created":"2022-10-14","cited_by_count":4},{"id":"2406.01559","title":"Prototypical Transformer as Unified Motion Learners","created":"2024-06-03","cited_by_count":4}],"next_cursor":null}