{"total":1070,"rows":[{"id":"2006.09011","title":"Improved Techniques for Training Score-Based Generative Models","created":"2020-06-16","cited_by_count":1043,"area":"diffusion"},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995,"area":null},{"id":"2107.03312","title":"SoundStream: An End-to-End Neural Audio Codec","created":"2021-07-07","cited_by_count":771,"area":null},{"id":"2210.13438","title":"High Fidelity Neural Audio Compression","created":"2022-10-24","cited_by_count":687,"area":null},{"id":"2410.00037","title":"Moshi: a speech-text foundation model for real-time dialogue","created":"2024-09-17","cited_by_count":568,"area":null},{"id":"2310.16828","title":"TD-MPC2: Scalable, Robust World Models for Continuous Control","created":"2023-10-25","cited_by_count":512,"area":"wm"},{"id":"2102.11174","title":"Linear Transformers Are Secretly Fast Weight Programmers","created":"2021-02-22","cited_by_count":502,"area":null},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396,"area":null},{"id":"2202.03376","title":"Message Passing Neural PDE Solvers","created":"2022-02-07","cited_by_count":386,"area":null},{"id":"2103.02143","title":"Random Feature Attention","created":"2021-03-03","cited_by_count":354,"area":null},{"id":"2110.14446","title":"Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methods","created":"2021-10-27","cited_by_count":311,"area":null},{"id":"2209.15352","title":"AudioGen: Textually Guided Audio Generation","created":"2022-09-30","cited_by_count":295,"area":null},{"id":"2107.09559","title":"SynthSeg: Segmentation of brain MRI scans of any contrast and resolution without retraining","created":"2021-07-20","cited_by_count":237,"area":null},{"id":"2103.03212","title":"Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks","created":"2021-03-04","cited_by_count":221,"area":null},{"id":"2106.12575","title":"Weisfeiler and Lehman Go Cellular: CW Networks","created":"2021-06-23","cited_by_count":218,"area":null},{"id":"2202.08791","title":"cosFormer: Rethinking Softmax in Attention","created":"2022-02-17","cited_by_count":213,"area":"lr"},{"id":"2404.07143","title":"Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention","created":"2024-04-10","cited_by_count":200,"area":null},{"id":"2102.06514","title":"Large-Scale Representation Learning on Graphs via Bootstrapping","created":"2021-02-12","cited_by_count":186,"area":null},{"id":"2112.14936","title":"Are we really making much progress? Revisiting, benchmarking, and refining heterogeneous graph neural networks","created":"2021-12-30","cited_by_count":176,"area":null},{"id":"2103.04551","title":"Behavior From the Void: Unsupervised Active Pre-Training","created":"2021-03-08","cited_by_count":174,"area":null},{"id":"2111.03043","title":"A System for General In-Hand Object Re-Orientation","created":"2021-11-04","cited_by_count":165,"area":null},{"id":"2109.14545","title":"Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark","created":"2021-09-29","cited_by_count":155,"area":null},{"id":"2210.13702","title":"DeXtreme: Transfer of Agile In-hand Manipulation from Simulation to Reality","created":"2022-10-25","cited_by_count":149,"area":null},{"id":"2103.14910","title":"MINE: Towards Continuous Depth MPI with NeRF for Novel View Synthesis","created":"2021-03-27","cited_by_count":133,"area":null},{"id":"2211.07214","title":"Robust Collaborative 3D Object Detection in Presence of Pose Errors","created":"2022-11-14","cited_by_count":129,"area":null},{"id":"2408.16532","title":"WavTokenizer: an Efficient Acoustic Discrete Codec Tokenizer for Audio Language Modeling","created":"2024-08-29","cited_by_count":129,"area":null},{"id":"2303.00938","title":"UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy","created":"2023-03-02","cited_by_count":124,"area":null},{"id":"2006.04678","title":"Primal Wasserstein Imitation Learning","created":"2020-06-08","cited_by_count":121,"area":"offlinerl"},{"id":"2210.04887","title":"In-Hand Object Rotation via Rapid Motor Adaptation","created":"2022-10-10","cited_by_count":118,"area":null},{"id":"2111.14600","title":"TransMVSNet: Global Context-aware Multi-view Stereo Network with Transformers","created":"2021-11-29","cited_by_count":117,"area":null},{"id":"2109.09881","title":"Estimating and Exploiting the Aleatoric Uncertainty in Surface Normal Estimation","created":"2021-09-20","cited_by_count":116,"area":null},{"id":"2103.12593","title":"Accurate and efficient time-domain classification with adaptive spiking recurrent neural networks","created":"2021-03-12","cited_by_count":115,"area":null},{"id":"2108.03348","title":"Global Self-Attention as a Replacement for Graph Convolution","created":"2021-08-07","cited_by_count":114,"area":null},{"id":"2202.01361","title":"Generative Flow Networks for Discrete Probabilistic Modeling","created":"2022-02-03","cited_by_count":114,"area":null},{"id":"2108.13956","title":"APS: Active Pretraining with Successor Features","created":"2021-08-31","cited_by_count":112,"area":null},{"id":"2102.05034","title":"SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks","created":"2021-02-09","cited_by_count":110,"area":null},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109,"area":null},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107,"area":null},{"id":"2304.00464","title":"UniDexGrasp++: Improving Dexterous Grasping Policy Learning via Geometry-aware Curriculum and Iterative Generalist-Specialist Learning","created":"2023-04-02","cited_by_count":107,"area":null},{"id":"2204.04879","title":"How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision","created":"2022-04-11","cited_by_count":102,"area":null},{"id":"2211.11744","title":"Visual Dexterity: In-Hand Reorientation of Novel and Complex Object Shapes","created":"2022-11-21","cited_by_count":101,"area":null},{"id":"2309.09979","title":"General In-Hand Object Rotation with Vision and Touch","created":"2023-09-18","cited_by_count":99,"area":null},{"id":"2106.01540","title":"Luna: Linear Unified Nested Attention","created":"2021-06-03","cited_by_count":96,"area":null},{"id":"2310.04564","title":"ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models","created":"2023-10-06","cited_by_count":94,"area":null},{"id":"2210.15651","title":"Learning Single-Index Models with Shallow Neural Networks","created":"2022-10-27","cited_by_count":92,"area":null},{"id":"2102.11972","title":"Do Transformer Modifications Transfer Across Implementations and Applications?","created":"2021-02-23","cited_by_count":87,"area":null},{"id":"2308.16692","title":"SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models","created":"2023-08-31","cited_by_count":87,"area":null},{"id":"2205.10053","title":"What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders","created":"2022-05-20","cited_by_count":82,"area":null},{"id":"2104.01404","title":"New Benchmarks for Learning on Non-Homophilous Graphs","created":"2021-04-03","cited_by_count":81,"area":null},{"id":"2308.13234","title":"Decoding Natural Images from EEG for Object Recognition","created":"2023-08-25","cited_by_count":81,"area":null},{"id":"2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","created":"2021-08-13","cited_by_count":80,"area":null},{"id":"2202.07643","title":"Lie Point Symmetry Data Augmentation for Neural PDE Solvers","created":"2022-02-15","cited_by_count":77,"area":null},{"id":"2304.03571","title":"$\\beta$-Variational autoencoders and transformers for reduced-order modelling of fluid flows","created":"2023-04-07","cited_by_count":77,"area":null},{"id":"2306.02451","title":"For SALE: State-Action Representation Learning for Deep Reinforcement Learning","created":"2023-06-04","cited_by_count":75,"area":null},{"id":"2201.04439","title":"Real-Time Style Modelling of Human Locomotion via Feature-Wise Transformations and Local Motion Phases","created":"2022-01-12","cited_by_count":72,"area":null},{"id":"2311.12351","title":"Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Survey","created":"2023-11-21","cited_by_count":72,"area":null},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69,"area":null},{"id":"1810.03237","title":"Task-Embedded Control Networks for Few-Shot Imitation Learning","created":"2018-10-08","cited_by_count":66,"area":"offlinerl"},{"id":"2406.07456","title":"fKAN: Fractional Kolmogorov-Arnold Networks with trainable Jacobi basis functions","created":"2024-06-11","cited_by_count":64,"area":null},{"id":"2112.13047","title":"Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimation","created":"2021-12-24","cited_by_count":63,"area":null},{"id":"2312.07541","title":"SMERF: Streamable Memory Efficient Radiance Fields for Real-Time Large-Scene Exploration","created":"2023-12-12","cited_by_count":62,"area":null},{"id":"2109.09559","title":"Contrastive Learning of Subject-Invariant EEG Representations for Cross-Subject Emotion Recognition","created":"2021-09-20","cited_by_count":60,"area":null},{"id":"2405.10315","title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","created":"2024-05-16","cited_by_count":59,"area":null},{"id":"2206.02607","title":"CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations","created":"2022-06-06","cited_by_count":58,"area":null},{"id":"2509.24006","title":"SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention","created":"2025-09-28","cited_by_count":58,"area":"diffusion"},{"id":"2201.09802","title":"Constrained Policy Optimization via Bayesian World Models","created":"2022-01-24","cited_by_count":57,"area":"wm"},{"id":"2401.08898","title":"Bridging State and History Representations: Understanding Self-Predictive RL","created":"2024-01-17","cited_by_count":54,"area":"deeprl"},{"id":"2211.03660","title":"SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes","created":"2022-11-07","cited_by_count":52,"area":null},{"id":"2406.02486","title":"A Temporal Kolmogorov-Arnold Transformer for Time Series Forecasting","created":"2024-06-04","cited_by_count":52,"area":null},{"id":"2209.02032","title":"Robust machine learning segmentation for large-scale analysis of heterogeneous clinical brain MRI datasets","created":"2022-09-05","cited_by_count":51,"area":null},{"id":"2210.05805","title":"Exploration via Elliptical Episodic Bonuses","created":"2022-10-11","cited_by_count":51,"area":null},{"id":"2306.05415","title":"Causal normalizing flows: from theory to practice","created":"2023-06-08","cited_by_count":51,"area":"lr"},{"id":"2105.09513","title":"Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions","created":"2021-05-20","cited_by_count":49,"area":null},{"id":"2112.05957","title":"AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs","created":"2021-12-11","cited_by_count":49,"area":null},{"id":"2202.08938","title":"Improving Intrinsic Exploration with Language Abstractions","created":"2022-02-17","cited_by_count":49,"area":null},{"id":"2203.09634","title":"Predicate Invention for Bilevel Planning","created":"2022-03-17","cited_by_count":49,"area":null},{"id":"2102.04376","title":"Adversarially Guided Actor-Critic","created":"2021-02-08","cited_by_count":47,"area":null},{"id":"2112.08177","title":"Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry","created":"2021-12-15","cited_by_count":46,"area":null},{"id":"1910.01077","title":"Task-Relevant Adversarial Imitation Learning","created":"2019-10-02","cited_by_count":45,"area":"offlinerl"},{"id":"2210.04017","title":"Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model","created":"2022-10-08","cited_by_count":45,"area":"wm"},{"id":"2303.16504","title":"An Over-parameterized Exponential Regression","created":"2023-03-29","cited_by_count":45,"area":null},{"id":"2311.01015","title":"Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs","created":"2023-11-02","cited_by_count":45,"area":"diffusion"},{"id":"2101.08543","title":"Boost then Convolve: Gradient Boosting Meets Graph Neural Networks","created":"2021-01-21","cited_by_count":44,"area":null},{"id":"2101.08366","title":"Quadratic Residual Networks: A New Class of Neural Networks for Solving Forward and Inverse Problems in Physics Involving PDEs","created":"2021-01-20","cited_by_count":43,"area":null},{"id":"2105.14074","title":"Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning","created":"2021-05-28","cited_by_count":43,"area":null},{"id":"2306.13812","title":"Maintaining Plasticity in Deep Continual Learning","created":"2023-06-23","cited_by_count":43,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2206.05408","title":"Multi-instrument Music Synthesis with Spectrogram Diffusion","created":"2022-06-11","cited_by_count":42,"area":"diffusion"},{"id":"2501.16142","title":"Towards General-Purpose Model-Free Reinforcement Learning","created":"2025-01-27","cited_by_count":41,"area":"deeprl"},{"id":"2103.10978","title":"Probabilistic 3D Human Shape and Pose Estimation from Multiple Unconstrained Images in the Wild","created":"2021-03-19","cited_by_count":40,"area":null},{"id":"2206.07681","title":"Learning to Accelerate Partial Differential Equations via Latent Global Evolution","created":"2022-06-15","cited_by_count":39,"area":null},{"id":"2305.13689","title":"Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training","created":"2023-05-23","cited_by_count":39,"area":null},{"id":"2305.19302","title":"Smooth, exact rotational symmetrization for deep learning on point clouds","created":"2023-05-30","cited_by_count":39,"area":null},{"id":"2306.04251","title":"Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks","created":"2023-06-07","cited_by_count":39,"area":null},{"id":"2106.11303","title":"Understanding Object Dynamics for Interactive Image-to-Video Synthesis","created":"2021-06-21","cited_by_count":38,"area":null},{"id":"2108.09779","title":"Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger","created":"2021-08-22","cited_by_count":38,"area":null},{"id":"2111.13119","title":"Interesting Object, Curious Agent: Learning Task-Agnostic Exploration","created":"2021-11-25","cited_by_count":38,"area":null},{"id":"2202.06382","title":"Training with More Confidence: Mitigating Injected and Natural Backdoors During Training","created":"2022-02-13","cited_by_count":38,"area":null},{"id":"2101.08578","title":"MLPF: Efficient machine-learned particle-flow reconstruction using graph neural networks","created":"2021-01-21","cited_by_count":36,"area":null},{"id":"2104.09994","title":"Federated Learning for Malware Detection in IoT Devices","created":"2021-04-15","cited_by_count":36,"area":null}],"next_cursor":"100"}