{"total":115,"rows":[{"id":"2103.11251","title":"Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges","created":"2021-03-20","cited_by_count":367,"area":null},{"id":"2206.02647","title":"Scaling Vision Transformers to Gigapixel Images via Hierarchical Self-Supervised Learning","created":"2022-06-06","cited_by_count":359,"area":null},{"id":"2212.13345","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","created":"2022-12-27","cited_by_count":266,"area":null},{"id":"2108.05895","title":"Mobile-Former: Bridging MobileNet and Transformer","created":"2021-08-12","cited_by_count":235,"area":null},{"id":"2203.06717","title":"Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs","created":"2022-03-13","cited_by_count":155,"area":null},{"id":"2110.11405","title":"Illiterate DALL-E Learns to Compose","created":"2021-10-17","cited_by_count":147,"area":null},{"id":"2206.10207","title":"SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders","created":"2022-06-21","cited_by_count":114,"area":null},{"id":"2103.15949","title":"Transformer visualization via dictionary learning: contextualized embedding as a linear superposition of transformer factors","created":"2021-03-29","cited_by_count":108,"area":null},{"id":"2112.08313","title":"Measure and Improve Robustness in NLP Models: A Survey","created":"2021-12-15","cited_by_count":107,"area":null},{"id":"2206.12126","title":"Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning","created":"2022-06-24","cited_by_count":86,"area":null},{"id":"2306.01129","title":"White-Box Transformers via Sparse Rate Reduction","created":"2023-06-01","cited_by_count":80,"area":null},{"id":"2108.08487","title":"Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domain","created":"2021-08-19","cited_by_count":71,"area":null},{"id":"2111.03643","title":"TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering","created":"2021-11-05","cited_by_count":70,"area":null},{"id":"2112.15424","title":"A Survey on Hyperdimensional Computing aka Vector Symbolic Architectures, Part II: Applications, Cognitive Models, and Challenges","created":"2021-11-12","cited_by_count":69,"area":null},{"id":"2212.00653","title":"Hyperbolic Contrastive Learning for Visual Representations beyond Objects","created":"2022-12-01","cited_by_count":61,"area":null},{"id":"2305.18203","title":"Concept Decomposition for Visual Exploration and Inspiration","created":"2023-05-29","cited_by_count":61,"area":null},{"id":"2302.04973","title":"Invariant Slot Attention: Object Discovery with Slot-Centric Reference Frames","created":"2023-02-09","cited_by_count":51,"area":null},{"id":"2112.00002","title":"Recovery of Continuous 3D Refractive Index Maps from Discrete Intensity-Only Measurements using Neural Fields","created":"2021-11-27","cited_by_count":48,"area":null},{"id":"2305.14229","title":"Provably Learning Object-Centric Representations","created":"2023-05-23","cited_by_count":45,"area":null},{"id":"2312.05355","title":"Neither hype nor gloom do DNNs justice","created":"2023-12-08","cited_by_count":40,"area":null},{"id":"2306.04898","title":"Understanding Masked Autoencoders via Hierarchical Latent Variable Models","created":"2023-06-08","cited_by_count":39,"area":null},{"id":"2208.00281","title":"Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding","created":"2022-07-30","cited_by_count":35,"area":null},{"id":"2112.05136","title":"PTR: A Benchmark for Part-based Conceptual, Relational, and Physical Reasoning","created":"2021-12-09","cited_by_count":34,"area":null},{"id":"2212.11696","title":"Reversible Column Networks","created":"2022-12-22","cited_by_count":32,"area":null},{"id":"2305.13031","title":"HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation","created":"2023-05-22","cited_by_count":32,"area":null},{"id":"2112.06390","title":"PartGlot: Learning Shape Part Segmentation from Language Reference Games","created":"2021-12-13","cited_by_count":30,"area":null},{"id":"2306.00600","title":"Rotating Features for Object Discovery","created":"2023-06-01","cited_by_count":29,"area":null},{"id":"2203.09064","title":"Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-shot Learning","created":"2022-03-17","cited_by_count":27,"area":null},{"id":"2108.00580","title":"GraphFPN: Graph Feature Pyramid Network for Object Detection","created":"2021-08-02","cited_by_count":25,"area":null},{"id":"2308.16271","title":"Emergence of Segmentation with Minimalistic White-Box Transformers","created":"2023-08-30","cited_by_count":24,"area":null},{"id":"2103.12975","title":"VLGrammar: Grounded Grammar Induction of Vision and Language","created":"2021-03-24","cited_by_count":22,"area":null},{"id":"2112.00319","title":"Object-Aware Cropping for Self-Supervised Learning","created":"2021-12-01","cited_by_count":22,"area":null},{"id":"2302.03985","title":"Cross-Layer Retrospective Retrieving via Layer Attention","created":"2023-02-08","cited_by_count":22,"area":null},{"id":"2410.08063","title":"Reversible Decoupling Network for Single Image Reflection Removal","created":"2024-10-10","cited_by_count":22,"area":null},{"id":"2107.05790","title":"Visual Parser: Representing Part-whole Hierarchies with Transformers","created":"2021-07-13","cited_by_count":21,"area":null},{"id":"2303.13095","title":"Modeling Entities as Semantic Points for Visual Information Extraction in the Wild","created":"2023-03-23","cited_by_count":20,"area":null},{"id":"2307.09437","title":"Grounded Object Centric Learning","created":"2023-07-18","cited_by_count":17,"area":null},{"id":"2203.12054","title":"Self-supervision through Random Segments with Autoregressive Coding (RandSAC)","created":"2022-03-22","cited_by_count":16,"area":null},{"id":"2305.12689","title":"FIT: Far-reaching Interleaved Transformers","created":"2023-05-22","cited_by_count":16,"area":null},{"id":"2205.08515","title":"Unsupervised Segmentation in Real-World Images via Spelke Object Inference","created":"2022-05-17","cited_by_count":15,"area":null},{"id":"2407.17929","title":"GLASS: Guided Latent Slot Diffusion for Object-Centric Learning","created":"2024-07-25","cited_by_count":14,"area":null},{"id":"2103.01043","title":"Persistent Message Passing","created":"2021-03-01","cited_by_count":13,"area":null},{"id":"2404.15672","title":"Representing Part-Whole Hierarchies in Foundation Models by Learning Localizability, Composability, and Decomposability from Anatomy via Self-Supervision","created":"2024-04-24","cited_by_count":13,"area":null},{"id":"2202.00838","title":"Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks","created":"2022-02-02","cited_by_count":11,"area":null},{"id":"2203.03282","title":"Interpretable part-whole hierarchies and conceptual-semantic relationships in neural networks","created":"2022-03-07","cited_by_count":11,"area":null},{"id":"2203.05997","title":"Towards Self-Supervised Learning of Global and Object-Centric Representations","created":"2022-03-11","cited_by_count":11,"area":null},{"id":"2206.02664","title":"Learning with Capsules: A Survey","created":"2022-06-06","cited_by_count":10,"area":null},{"id":"2405.18616","title":"Wavelet-Based Image Tokenizer for Vision Transformers","created":"2024-05-28","cited_by_count":10,"area":null},{"id":"2406.07141","title":"Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention","created":"2024-06-11","cited_by_count":9,"area":null},{"id":"2207.02334","title":"Weakly Supervised Grounding for VQA in Vision-Language Transformers","created":"2022-07-05","cited_by_count":8,"area":null},{"id":"2405.17283","title":"Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery","created":"2024-05-27","cited_by_count":8,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2201.08813","title":"Active Predictive Coding Networks: A Neural Solution to the Problem of Learning Reference Frames and Part-Whole Hierarchies","created":"2022-01-14","cited_by_count":6,"area":null},{"id":"2209.15261","title":"Minimalistic Unsupervised Learning with the Sparse Manifold Transform","created":"2022-09-30","cited_by_count":6,"area":null},{"id":"2301.01583","title":"Why Capsule Neural Networks Do Not Scale: Challenging the Dynamic Parse-Tree Assumption","created":"2023-01-04","cited_by_count":6,"area":null},{"id":"2410.19553","title":"On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes","created":"2024-10-25","cited_by_count":6,"area":null},{"id":"2106.08318","title":"Gradient Forward-Propagation for Large-Scale Temporal Video Modelling","created":"2021-06-15","cited_by_count":5,"area":null},{"id":"2403.13351","title":"OrthCaps: An Orthogonal CapsNet with Sparse Attention Routing and Pruning","created":"2024-03-20","cited_by_count":5,"area":null},{"id":"2107.02036","title":"A topological solution to object segmentation and tracking","created":"2021-07-05","cited_by_count":4,"area":null},{"id":"2203.01668","title":"Translational Lung Imaging Analysis Through Disentangled Representations","created":"2022-03-03","cited_by_count":4,"area":null},{"id":"2203.12686","title":"Possibility Before Utility: Learning And Using Hierarchical Affordances","created":"2022-03-23","cited_by_count":4,"area":null},{"id":"2207.13428","title":"Leveraging GAN Priors for Few-Shot Part Segmentation","created":"2022-07-27","cited_by_count":4,"area":null},{"id":"2309.01005","title":"RevColV2: Exploring Disentangled Representations in Masked Image Modeling","created":"2023-09-02","cited_by_count":4,"area":null},{"id":"2309.11955","title":"A Study of Forward-Forward Algorithm for Self-Supervised Learning","created":"2023-09-21","cited_by_count":4,"area":null},{"id":"2309.16515","title":"Latent Noise Segmentation: How Neural Noise Leads to the Emergence of Segmentation and Grouping","created":"2023-09-28","cited_by_count":4,"area":null},{"id":"2311.18296","title":"Perceptual Group Tokenizer: Building Perception with Iterative Grouping","created":"2023-11-30","cited_by_count":4,"area":null},{"id":"2403.02598","title":"Pooling Image Datasets With Multiple Covariate Shift and Imbalance","created":"2024-03-05","cited_by_count":4,"area":null},{"id":"2407.12870","title":"Revisiting Adaptive Cellular Recognition Under Domain Shifts: A Contextual Correspondence View","created":"2024-07-14","cited_by_count":4,"area":null},{"id":"2411.02134","title":"Optimizing Multi-Scale Representations to Detect Effect Heterogeneity Using Earth Observation and Computer Vision: Applications to Two Anti-Poverty RCTs","created":"2024-11-04","cited_by_count":4,"area":null},{"id":"2103.15553","title":"Connectionism, Complexity, and Living Systems: a comparison of Artificial and Biological Neural Networks","created":"2021-03-15","cited_by_count":3,"area":null},{"id":"2105.13978","title":"What Is Considered Complete for Visual Recognition?","created":"2021-05-28","cited_by_count":3,"area":null},{"id":"2108.11762","title":"Disentangling What and Where for 3D Object-Centric Representations Through Active Inference","created":"2021-08-26","cited_by_count":3,"area":null},{"id":"2112.09741","title":"Envisioning Future Deep Learning Theories: Some Basic Concepts and Characteristics","created":"2021-12-17","cited_by_count":3,"area":null},{"id":"2103.13512","title":"Projection: A Mechanism for Human-like Reasoning in Artificial Intelligence","created":"2021-03-24","cited_by_count":2,"area":null},{"id":"2110.04954","title":"Recurrent Attention Models with Object-centric Capsule Representation for Multi-object Recognition","created":"2021-10-11","cited_by_count":2,"area":null},{"id":"2203.05006","title":"Resource-Efficient Invariant Networks: Exponential Gains by Unrolled Optimization","created":"2022-03-09","cited_by_count":2,"area":null},{"id":"2206.08462","title":"Recursive Neural Programs: Variational Learning of Image Grammars and Part-Whole Hierarchies","created":"2022-06-16","cited_by_count":2,"area":null},{"id":"2207.02126","title":"Improving Semantic Segmentation in Transformers using Hierarchical Inter-Level Attention","created":"2022-07-05","cited_by_count":2,"area":null},{"id":"2401.08603","title":"Representation Learning in a Decomposed Encoder Design for Bio-inspired Hebbian Learning","created":"2023-11-22","cited_by_count":2,"area":null},{"id":"2410.20535","title":"Asynchronous Perception Machine For Efficient Test-Time-Training","created":"2024-10-27","cited_by_count":2,"area":null},{"id":"2104.01523","title":"ASPER: Attention-based Approach to Extract Syntactic Patterns denoting Semantic Relations in Sentential Context","created":"2021-04-04","cited_by_count":1,"area":null},{"id":"2104.03722","title":"HindSight: A Graph-Based Vision Model Architecture For Representing Part-Whole Hierarchies","created":"2021-04-08","cited_by_count":1,"area":null},{"id":"2203.10087","title":"But that's not why: Inference adjustment by interactive prototype revision","created":"2022-03-18","cited_by_count":1,"area":null},{"id":"2209.00232","title":"Hybrid Gromov-Wasserstein Embedding for Capsule Learning","created":"2022-09-01","cited_by_count":1,"area":null},{"id":"2211.16564","title":"Testing GLOM's ability to infer wholes from ambiguous parts","created":"2022-11-29","cited_by_count":1,"area":null},{"id":"2303.00077","title":"Beyond the limitations of any imaginable mechanism: large language models and psycholinguistics","created":"2023-02-28","cited_by_count":1,"area":null},{"id":"2303.14537","title":"Deep Augmentation: Dropout as Augmentation for Self-Supervised Learning","created":"2023-03-25","cited_by_count":1,"area":null},{"id":"2304.11330","title":"Self-supervised Learning by View Synthesis","created":"2023-04-22","cited_by_count":1,"area":null},{"id":"2308.02000","title":"Bridging Neural and Symbolic Representations with Transitional Dictionary Learning","created":"2023-08-03","cited_by_count":1,"area":null},{"id":"2403.11004","title":"Forward Learning of Graph Neural Networks","created":"2024-03-16","cited_by_count":1,"area":null},{"id":"2406.12944","title":"Semantic Graph Consistency: Going Beyond Patches for Regularizing Self-Supervised Vision Transformers","created":"2024-06-18","cited_by_count":1,"area":null},{"id":"2406.14239","title":"LeYOLO, New Embedded Architecture for Object Detection","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2407.14792","title":"FedPartWhole: Federated domain generalization via consistent part-whole hierarchies","created":"2024-07-20","cited_by_count":1,"area":null},{"id":"2501.04144","title":"Chirpy3D: Part-Aware Multi-View Diffusion for Creative Fine-Grained Object Generation","created":"2025-01-07","cited_by_count":1,"area":null},{"id":"2501.10131","title":"ACE: Anatomically Consistent Embeddings in Composition and Decomposition","created":"2025-01-17","cited_by_count":1,"area":null},{"id":"2504.09155","title":"Evolved Hierarchical Masking for Self-Supervised Learning","created":"2025-04-12","cited_by_count":1,"area":null},{"id":"2603.14022","title":"A Hyperbolic Perspective on Hierarchical Structure in Object-Centric Scene Representations","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2103.14561","title":"User-Oriented Smart General AI System under Causal Inference","created":"2021-03-25","cited_by_count":0,"area":null},{"id":"2103.15294","title":"\"Weak AI\" is Likely to Never Become \"Strong AI\", So What is its Greatest Value for us?","created":"2021-03-29","cited_by_count":0,"area":null},{"id":"2110.02057","title":"Structured Prediction in NLP -- A survey","created":"2021-08-31","cited_by_count":0,"area":null}],"next_cursor":"100"}