{"list":"other","total":81,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2201.11903","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","created":"2022-01-28","cited_by_count":12459},{"id":"2002.05709","title":"A Simple Framework for Contrastive Learning of Visual Representations","created":"2020-02-13","cited_by_count":12049},{"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":"1807.03748","title":"Representation Learning with Contrastive Predictive Coding","created":"2018-07-10","cited_by_count":7777},{"id":"1911.05722","title":"Momentum Contrast for Unsupervised Visual Representation Learning","created":"2019-11-13","cited_by_count":7513},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2006.07733","title":"Bootstrap your own latent: A new approach to self-supervised Learning","created":"2020-06-13","cited_by_count":4750},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1809.09600","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","created":"2018-09-25","cited_by_count":3754},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"2011.10566","title":"Exploring Simple Siamese Representation Learning","created":"2020-11-20","cited_by_count":2866},{"id":"1711.03938","title":"CARLA: An Open Urban Driving Simulator","created":"2017-11-10","cited_by_count":2449},{"id":"2012.07436","title":"Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting","created":"2020-12-14","cited_by_count":2169},{"id":"1706.05587","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","created":"2017-06-17","cited_by_count":2161},{"id":"2211.14730","title":"A Time Series is Worth 64 Words: Long-term Forecasting with Transformers","created":"2022-11-27","cited_by_count":2039},{"id":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"1611.09268","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","created":"2016-11-28","cited_by_count":1605},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"id":"2212.10509","title":"Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions","created":"2022-12-20","cited_by_count":923},{"id":"2108.00573","title":"MuSiQue: Multihop Questions via Single-hop Question Composition","created":"2021-08-02","cited_by_count":916},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2305.14627","title":"Enabling Large Language Models to Generate Text with Citations","created":"2023-05-24","cited_by_count":595},{"id":"1504.06375","title":"Holistically-Nested Edge Detection","created":"2015-04-24","cited_by_count":592},{"id":"2106.10466","title":"TS2Vec: Towards Universal Representation of Time Series","created":"2021-06-19","cited_by_count":471},{"id":"2010.02803","title":"A Transformer-based Framework for Multivariate Time Series Representation Learning","created":"2020-10-06","cited_by_count":453},{"id":"2105.10497","title":"Intriguing Properties of Vision Transformers","created":"2021-05-21","cited_by_count":446},{"id":"1810.07758","title":"The UCR Time Series Archive","created":"2018-10-17","cited_by_count":431},{"id":"1802.04431","title":"Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding","created":"2018-02-13","cited_by_count":410},{"id":"2106.14112","title":"Time-Series Representation Learning via Temporal and Contextual Contrasting","created":"2021-06-26","cited_by_count":345},{"id":"2104.14548","title":"With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations","created":"2021-04-29","cited_by_count":326},{"id":"2210.08726","title":"RARR: Researching and Revising What Language Models Say, Using Language Models","created":"2022-10-17","cited_by_count":287},{"id":"2305.12740","title":"Can We Edit Factual Knowledge by In-Context Learning?","created":"2023-05-22","cited_by_count":285},{"id":"1901.10738","title":"Unsupervised Scalable Representation Learning for Multivariate Time Series","created":"2019-01-30","cited_by_count":269},{"id":"1904.00760","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","created":"2019-03-20","cited_by_count":260},{"id":"2112.12870","title":"Measuring Attribution in Natural Language Generation Models","created":"2021-12-23","cited_by_count":256},{"id":"2206.08496","title":"Self-Supervised Contrastive Pre-Training For Time Series via Time-Frequency Consistency","created":"2022-06-17","cited_by_count":250},{"id":"2106.00750","title":"Unsupervised Representation Learning for Time Series with Temporal Neighborhood Coding","created":"2021-06-01","cited_by_count":224},{"id":"2010.07922","title":"Representation Learning via Invariant Causal Mechanisms","created":"2020-10-15","cited_by_count":199},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2301.13808","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","created":"2023-01-31","cited_by_count":178},{"id":"1602.02410","title":"Exploring the Limits of Language Modeling","created":"2016-02-07","cited_by_count":173},{"id":"2005.13249","title":"CLOCS: Contrastive Learning of Cardiac Signals Across Space, Time, and Patients","created":"2020-05-27","cited_by_count":171},{"id":"2401.06855","title":"Fine-grained Hallucination Detection and Editing for Language Models","created":"2024-01-12","cited_by_count":149},{"id":"2202.01575","title":"CoST: Contrastive Learning of Disentangled Seasonal-Trend Representations for Time Series Forecasting","created":"2022-02-03","cited_by_count":144},{"id":"2110.06848","title":"Decoupled Contrastive Learning","created":"2021-10-13","cited_by_count":143},{"id":"2302.00861","title":"SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling","created":"2023-02-02","cited_by_count":115},{"id":"2212.08037","title":"Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Models","created":"2022-12-15","cited_by_count":112},{"id":"2305.11859","title":"Complex Claim Verification with Evidence Retrieved in the Wild","created":"2023-05-19","cited_by_count":110},{"id":"2105.07197","title":"Are Convolutional Neural Networks or Transformers more like human vision?","created":"2021-05-15","cited_by_count":109},{"id":"2108.05988","title":"TVT: Transferable Vision Transformer for Unsupervised Domain Adaptation","created":"2021-08-12","cited_by_count":81},{"id":"2010.05981","title":"Shape-Texture Debiased Neural Network Training","created":"2020-10-12","cited_by_count":76},{"id":"2210.01613","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","created":"2022-10-04","cited_by_count":72},{"id":"2308.06374","title":"Large Language Models and Knowledge Graphs: Opportunities and Challenges","created":"2023-08-11","cited_by_count":71},{"id":"2203.09270","title":"Mixing Up Contrastive Learning: Self-Supervised Representation Learning for Time Series","created":"2022-03-17","cited_by_count":54},{"id":"2101.11604","title":"Shape or Texture: Understanding Discriminative Features in CNNs","created":"2021-01-27","cited_by_count":52},{"id":"2303.11911","title":"Time Series Contrastive Learning with Information-Aware Augmentations","created":"2023-03-21","cited_by_count":52},{"id":"2311.07838","title":"LLatrieval: LLM-Verified Retrieval for Verifiable Generation","created":"2023-11-14","cited_by_count":52},{"id":"2312.16424","title":"Soft Contrastive Learning for Time Series","created":"2023-12-27","cited_by_count":51},{"id":"2407.04121","title":"Hallucination Detection: Robustly Discerning Reliable Answers in Large Language Models","created":"2024-07-04","cited_by_count":44},{"id":"2405.14170","title":"Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning","created":"2024-05-23","cited_by_count":41},{"id":"2311.09114","title":"Ever: Mitigating Hallucination in Large Language Models through Real-Time Verification and Rectification","created":"2023-11-15","cited_by_count":38},{"id":"2112.02300","title":"Unsupervised Domain Generalization by Learning a Bridge Across Domains","created":"2021-12-04","cited_by_count":33},{"id":"2104.09789","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","created":"2021-04-20","cited_by_count":32},{"id":"2106.05142","title":"Neighborhood Contrastive Learning Applied to Online Patient Monitoring","created":"2021-06-09","cited_by_count":32},{"id":"2305.15053","title":"Decomposing Complex Queries for Tip-of-the-tongue Retrieval","created":"2023-05-24","cited_by_count":24},{"id":"2403.09193","title":"Can We Talk Models Into Seeing the World Differently?","created":"2024-03-14","cited_by_count":23},{"id":"2305.14332","title":"Evaluating and Modeling Attribution for Cross-Lingual Question Answering","created":"2023-05-23","cited_by_count":21},{"id":"2402.12545","title":"TrustScore: Reference-Free Evaluation of LLM Response Trustworthiness","created":"2024-02-19","cited_by_count":19},{"id":"1803.07739","title":"Assessing Shape Bias Property of Convolutional Neural Networks","created":"2018-03-21","cited_by_count":18},{"id":"2010.05495","title":"Increasing the Robustness of Semantic Segmentation Models with Painting-by-Numbers","created":"2020-10-12","cited_by_count":17},{"id":"2401.14640","title":"Can LLMs Evaluate Complex Attribution in QA? Automatic Benchmarking using Knowledge Graphs","created":"2024-01-26","cited_by_count":17},{"id":"2409.19753","title":"CoTKR: Chain-of-Thought Enhanced Knowledge Rewriting for Complex Knowledge Graph Question Answering","created":"2024-09-29","cited_by_count":17},{"id":"2305.06568","title":"Convolutional Neural Networks Rarely Learn Shape for Semantic Segmentation","created":"2023-05-11","cited_by_count":12},{"id":"2305.15056","title":"Reasoning over Hierarchical Question Decomposition Tree for Explainable Question Answering","created":"2023-05-24","cited_by_count":11},{"id":"2402.09530","title":"Reducing Texture Bias of Deep Neural Networks via Edge Enhancing Diffusion","created":"2024-02-14","cited_by_count":11},{"id":"2312.04142","title":"TimeDRL: Disentangled Representation Learning for Multivariate Time-Series","created":"2023-12-07","cited_by_count":10},{"id":"2401.09109","title":"Trapped in texture bias? A large scale comparison of deep instance segmentation","created":"2024-01-17","cited_by_count":10},{"id":"1911.08432","title":"Defective Convolutional Networks","created":"2019-11-19","cited_by_count":5}],"next_cursor":null}