{"list":"other","total":88,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2203.02155","title":"Training language models to follow instructions with human feedback","created":"2022-03-04","cited_by_count":15971},{"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":"1908.10084","title":"Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks","created":"2019-08-27","cited_by_count":9170},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"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":"2205.11916","title":"Large Language Models are Zero-Shot Reasoners","created":"2022-05-24","cited_by_count":4374},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2212.04356","title":"Robust Speech Recognition via Large-Scale Weak Supervision","created":"2022-12-06","cited_by_count":4057},{"id":"2108.07258","title":"On the Opportunities and Risks of Foundation Models","created":"2021-08-16","cited_by_count":4033},{"id":"1411.7766","title":"Deep Learning Face Attributes in the Wild","created":"2014-11-28","cited_by_count":3693},{"id":"2310.06825","title":"Mistral 7B","created":"2023-10-10","cited_by_count":3164},{"id":"2006.09882","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","created":"2020-06-17","cited_by_count":2857},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1607.06520","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","created":"2016-07-21","cited_by_count":1312},{"id":"1911.08731","title":"Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization","created":"2019-11-20","cited_by_count":1247},{"id":"2306.14824","title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","created":"2023-06-26","cited_by_count":1089},{"id":"1612.03975","title":"ConceptNet 5.5: An Open Multilingual Graph of General Knowledge","created":"2016-12-12","cited_by_count":1067},{"id":"1609.04747","title":"An overview of gradient descent optimization algorithms","created":"2016-09-15","cited_by_count":1033},{"id":"1807.05520","title":"Deep Clustering for Unsupervised Learning of Visual Features","created":"2018-07-15","cited_by_count":1028},{"id":"1511.06335","title":"Unsupervised Deep Embedding for Clustering Analysis","created":"2015-11-19","cited_by_count":767},{"id":"2407.07895","title":"LLaVA-NeXT-Interleave: Tackling Multi-image, Video, and 3D in Large Multimodal Models","created":"2024-07-10","cited_by_count":584},{"id":"2107.09044","title":"Just Train Twice: Improving Group Robustness without Training Group Information","created":"2021-07-19","cited_by_count":523},{"id":"2210.13382","title":"Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task","created":"2022-10-24","cited_by_count":431},{"id":"2402.00253","title":"A Survey on Hallucination in Large Vision-Language Models","created":"2024-02-01","cited_by_count":357},{"id":"2005.12320","title":"SCAN: Learning to Classify Images without Labels","created":"2020-05-25","cited_by_count":352},{"id":"2403.10517","title":"VideoAgent: Long-form Video Understanding with Large Language Model as Agent","created":"2024-03-15","cited_by_count":332},{"id":"2211.03759","title":"Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale","created":"2022-11-07","cited_by_count":262},{"id":"2201.02609","title":"Generalized Category Discovery","created":"2022-01-07","cited_by_count":211},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203},{"id":"2310.09219","title":"\"Kelly is a Warm Person, Joseph is a Role Model\": Gender Biases in LLM-Generated Reference Letters","created":"2023-10-13","cited_by_count":199},{"id":"2103.11790","title":"Large Pre-trained Language Models Contain Human-like Biases of What is Right and Wrong to Do","created":"2021-03-08","cited_by_count":178},{"id":"2310.01469","title":"LLM Lies: Hallucinations are not Bugs, but Features as Adversarial Examples","created":"2023-10-02","cited_by_count":177},{"id":"2203.01517","title":"Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations","created":"2022-03-03","cited_by_count":172},{"id":"2102.04130","title":"Bias Out-of-the-Box: An Empirical Analysis of Intersectional Occupational Biases in Popular Generative Language Models","created":"2021-02-08","cited_by_count":141},{"id":"2004.07999","title":"REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasets","created":"2020-04-16","cited_by_count":136},{"id":"2304.06034","title":"Social Biases through the Text-to-Image Generation Lens","created":"2023-03-30","cited_by_count":127},{"id":"2302.12254","title":"Change is Hard: A Closer Look at Subpopulation Shift","created":"2023-02-23","cited_by_count":120},{"id":"2106.15252","title":"AutoNovel: Automatically Discovering and Learning Novel Visual Categories","created":"2021-06-29","cited_by_count":116},{"id":"1407.3867","title":"Part-based R-CNNs for Fine-grained Category Detection","created":"2014-07-15","cited_by_count":109},{"id":"2305.17066","title":"Mindstorms in Natural Language-Based Societies of Mind","created":"2023-05-26","cited_by_count":107},{"id":"2310.09291","title":"Vision-by-Language for Training-Free Compositional Image Retrieval","created":"2023-10-13","cited_by_count":103},{"id":"2405.09589","title":"A Comprehensive Survey of Hallucination in Large Language, Image, Video and Audio Foundation Models","created":"2024-05-15","cited_by_count":100},{"id":"2301.00184","title":"Cap4Video: What Can Auxiliary Captions Do for Text-Video Retrieval?","created":"2022-12-31","cited_by_count":90},{"id":"2303.06594","title":"ChatGPT Asks, BLIP-2 Answers: Automatic Questioning Towards Enriched Visual Descriptions","created":"2023-03-12","cited_by_count":86},{"id":"2210.04142","title":"Deep Clustering: A Comprehensive Survey","created":"2022-10-09","cited_by_count":78},{"id":"1711.06526","title":"Multi-Label Zero-Shot Learning with Structured Knowledge Graphs","created":"2017-11-17","cited_by_count":72},{"id":"2307.00524","title":"Large Language Models Enable Few-Shot Clustering","created":"2023-07-02","cited_by_count":72},{"id":"2305.14871","title":"ClusterLLM: Large Language Models as a Guide for Text Clustering","created":"2023-05-24","cited_by_count":70},{"id":"2402.02420","title":"Factuality of Large Language Models: A Survey","created":"2024-02-04","cited_by_count":66},{"id":"2104.01429","title":"Graph Contrastive Clustering","created":"2021-04-03","cited_by_count":61},{"id":"2311.17055","title":"No Representation Rules Them All in Category Discovery","created":"2023-11-28","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":"2405.18870","title":"LLMs achieve adult human performance on higher-order theory of mind tasks","created":"2024-05-29","cited_by_count":61},{"id":"2301.11104","title":"Discovering and Mitigating Visual Biases through Keyword Explanation","created":"2023-01-26","cited_by_count":58},{"id":"2309.00035","title":"FACET: Fairness in Computer Vision Evaluation Benchmark","created":"2023-08-31","cited_by_count":58},{"id":"2312.02974","title":"Describing Differences in Image Sets with Natural Language","created":"2023-12-05","cited_by_count":53},{"id":"1704.02792","title":"Fine-graind Image Classification via Combining Vision and Language","created":"2017-04-10","cited_by_count":51},{"id":"2405.02363","title":"LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model","created":"2024-05-03","cited_by_count":44},{"id":"2310.11989","title":"Image Clustering with External Guidance","created":"2023-10-18","cited_by_count":36},{"id":"1712.00580","title":"Fruit recognition from images using deep learning","created":"2017-12-02","cited_by_count":35},{"id":"2306.00917","title":"Vocabulary-free Image Classification","created":"2023-06-01","cited_by_count":35},{"id":"2306.07272","title":"Zero-shot Composed Text-Image Retrieval","created":"2023-06-12","cited_by_count":32},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28},{"id":"2310.18297","title":"Image Clustering Conditioned on Text Criteria","created":"2023-10-27","cited_by_count":26},{"id":"2401.13837","title":"Democratizing Fine-grained Visual Recognition with Large Language Models","created":"2024-01-24","cited_by_count":25},{"id":"2404.15655","title":"Multi-Modal Proxy Learning Towards Personalized Visual Multiple Clustering","created":"2024-04-24","cited_by_count":21},{"id":"2409.08466","title":"Explaining Datasets in Words: Statistical Models with Natural Language Parameters","created":"2024-09-13","cited_by_count":21},{"id":"2210.09162","title":"Table-To-Text generation and pre-training with TabT5","created":"2022-10-17","cited_by_count":20},{"id":"2305.19329","title":"Mitigating Test-Time Bias for Fair Image Retrieval","created":"2023-05-23","cited_by_count":20},{"id":"2101.11606","title":"Generative Multi-Label Zero-Shot Learning","created":"2021-01-27","cited_by_count":19},{"id":"2304.01042","title":"DivClust: Controlling Diversity in Deep Clustering","created":"2023-04-03","cited_by_count":18},{"id":"2306.13023","title":"AugDMC: Data Augmentation Guided Deep Multiple Clustering","created":"2023-06-22","cited_by_count":15},{"id":"2401.03105","title":"Incorporating Visual Experts to Resolve the Information Loss in Multimodal Large Language Models","created":"2024-01-06","cited_by_count":12},{"id":"2303.15975","title":"Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery","created":"2023-03-28","cited_by_count":11},{"id":"2405.10053","title":"SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection","created":"2024-05-16","cited_by_count":11},{"id":"2304.02364","title":"What's in a Name? Beyond Class Indices for Image Recognition","created":"2023-04-05","cited_by_count":9},{"id":"2405.00988","title":"Context-Aware Clustering using Large Language Models","created":"2024-05-02","cited_by_count":9},{"id":"2406.14830","title":"CLIP-Decoder : ZeroShot Multilabel Classification using Multimodal CLIP Aligned Representation","created":"2024-06-21","cited_by_count":9},{"id":"2007.15610","title":"Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge","created":"2020-07-30","cited_by_count":6},{"id":"2408.04471","title":"What could go wrong? Discovering and describing failure modes in computer vision","created":"2024-08-08","cited_by_count":5}],"next_cursor":null}