{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1312.6034","title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","created":"2013-12-20","cited_by_count":2371},{"id":"1905.02244","title":"Searching for MobileNetV3","created":"2019-05-06","cited_by_count":1994},{"id":"2004.07780","title":"Shortcut Learning in Deep Neural Networks","created":"2020-04-16","cited_by_count":1969},{"id":"1603.05027","title":"Identity Mappings in Deep Residual Networks","created":"2016-03-16","cited_by_count":1965},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"1905.13549","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","created":"2019-05-29","cited_by_count":1013},{"id":"2106.04560","title":"Scaling Vision Transformers","created":"2021-06-08","cited_by_count":999},{"id":"2302.05442","title":"Scaling Vision Transformers to 22 Billion Parameters","created":"2023-02-10","cited_by_count":694},{"id":"2104.10972","title":"ImageNet-21K Pretraining for the Masses","created":"2021-04-22","cited_by_count":613},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2405.07987","title":"The Platonic Representation Hypothesis","created":"2024-05-13","cited_by_count":382},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1812.03411","title":"Feature Denoising for Improving Adversarial Robustness","created":"2018-12-09","cited_by_count":314},{"id":"2307.02477","title":"Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks","created":"2023-07-05","cited_by_count":246},{"id":"1808.08750","title":"Generalisation in humans and deep neural networks","created":"2018-08-27","cited_by_count":237},{"id":"2106.07411","title":"Partial success in closing the gap between human and machine vision","created":"2021-06-14","cited_by_count":185},{"id":"2309.13638","title":"Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve","created":"2023-09-24","cited_by_count":178},{"id":"2003.13630","title":"TResNet: High Performance GPU-Dedicated Architecture","created":"2020-03-30","cited_by_count":119},{"id":"1805.08315","title":"Learning long-range spatial dependencies with horizontal gated-recurrent units","created":"2018-05-21","cited_by_count":98},{"id":"2006.16736","title":"Beyond accuracy: quantifying trial-by-trial behaviour of CNNs and humans by measuring error consistency","created":"2020-06-30","cited_by_count":78},{"id":"2210.08340","title":"Toward Next-Generation Artificial Intelligence: Catalyzing the NeuroAI Revolution","created":"2022-10-15","cited_by_count":78},{"id":"2111.04138","title":"Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis","created":"2021-11-07","cited_by_count":65},{"id":"2007.16189","title":"Self-supervised learning through the eyes of a child","created":"2020-07-31","cited_by_count":61},{"id":"2211.04533","title":"Harmonizing the object recognition strategies of deep neural networks with humans","created":"2022-11-08","cited_by_count":59},{"id":"1903.05946","title":"Recurrence is required to capture the representational dynamics of the human visual system","created":"2019-03-14","cited_by_count":58},{"id":"1610.01563","title":"DeepGaze II: Reading fixations from deep features trained on object recognition","created":"2016-10-05","cited_by_count":55},{"id":"1803.07770","title":"Emergence of grid-like representations by training recurrent neural networks to perform spatial localization","created":"2018-03-21","cited_by_count":52},{"id":"1406.3284","title":"Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition","created":"2014-06-12","cited_by_count":50},{"id":"2209.03718","title":"The neuroconnectionist research programme","created":"2022-09-08","cited_by_count":48},{"id":"1604.03640","title":"Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex","created":"2016-04-13","cited_by_count":42},{"id":"2312.05355","title":"Neither hype nor gloom do DNNs justice","created":"2023-12-08","cited_by_count":40},{"id":"1702.01825","title":"Deep Learning Models of the Retinal Response to Natural Scenes","created":"2017-02-06","cited_by_count":36},{"id":"1906.01558","title":"Disentangling neural mechanisms for perceptual grouping","created":"2019-06-04","cited_by_count":28},{"id":"2107.14344","title":"Towards robust vision by multi-task learning on monkey visual cortex","created":"2021-07-29","cited_by_count":28},{"id":"1807.00053","title":"Task-Driven Convolutional Recurrent Models of the Visual System","created":"2018-06-20","cited_by_count":27},{"id":"2306.06805","title":"Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization","created":"2023-06-11","cited_by_count":27},{"id":"1911.09451","title":"Deep neuroethology of a virtual rodent","created":"2019-11-21","cited_by_count":23},{"id":"2010.15314","title":"Recurrent neural circuits for contour detection","created":"2020-10-29","cited_by_count":23},{"id":"2305.15372","title":"Learning high-level visual representations from a child's perspective without strong inductive biases","created":"2023-05-24","cited_by_count":22},{"id":"2406.19087","title":"Dimensions underlying the representational alignment of deep neural networks with humans","created":"2024-06-27","cited_by_count":22},{"id":"1803.10827","title":"Who Let The Dogs Out? Modeling Dog Behavior From Visual Data","created":"2018-03-28","cited_by_count":20},{"id":"2005.11362","title":"Stable and expressive recurrent vision models","created":"2020-05-22","cited_by_count":20},{"id":"2003.12128","title":"Going in circles is the way forward: the role of recurrence in visual inference","created":"2020-03-26","cited_by_count":19},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19},{"id":"2306.03779","title":"Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex","created":"2023-06-06","cited_by_count":18},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16},{"id":"2206.08666","title":"The Sensorium competition on predicting large-scale mouse primary visual cortex activity","created":"2022-06-17","cited_by_count":14},{"id":"2409.05862","title":"Evaluating Multiview Object Consistency in Humans and Image Models","created":"2024-09-09","cited_by_count":13},{"id":"2411.05712","title":"Scaling Laws for Task-Optimized Models of the Primate Visual Ventral Stream","created":"2024-11-08","cited_by_count":13},{"id":"2502.16238","title":"Brain-Model Evaluations Need the NeuroAI Turing Test","created":"2025-02-22","cited_by_count":13},{"id":"2105.13351","title":"Tracking Without Re-recognition in Humans and Machines","created":"2021-05-27","cited_by_count":12},{"id":"2410.11516","title":"TopoLM: brain-like spatio-functional organization in a topographic language model","created":"2024-10-15","cited_by_count":12},{"id":"1912.06207","title":"From deep learning to mechanistic understanding in neuroscience: the structure of retinal prediction","created":"2019-12-12","cited_by_count":11},{"id":"2404.09991","title":"EgoPet: Egomotion and Interaction Data from an Animal's Perspective","created":"2024-04-15","cited_by_count":11},{"id":"2004.12676","title":"Crowding Reveals Fundamental Differences in Local vs. Global Processing in Humans and Machines","created":"2020-04-27","cited_by_count":9},{"id":"2306.03229","title":"Adversarial alignment: Breaking the trade-off between the strength of an attack and its relevance to human perception","created":"2023-06-05","cited_by_count":7},{"id":"2410.02094","title":"Tracking objects that change in appearance with phase synchrony","created":"2024-10-02","cited_by_count":3},{"id":"2411.03630","title":"RTify: Aligning Deep Neural Networks with Human Behavioral Decisions","created":"2024-11-06","cited_by_count":3},{"id":"2203.11910","title":"Improving Neural Predictivity in the Visual Cortex with Gated Recurrent Connections","created":"2022-03-22","cited_by_count":1}],"next_cursor":null}