{"total":1304,"rows":[{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218,"area":"wm"},{"id":"2208.04933","title":"Simplified State Space Layers for Sequence Modeling","created":"2022-08-09","cited_by_count":788,"area":"ssm"},{"id":"2401.06121","title":"TOFU: A Task of Fictitious Unlearning for LLMs","created":"2024-01-11","cited_by_count":533,"area":"safety"},{"id":"2402.06196","title":"Large Language Models: A Survey","created":"2024-02-09","cited_by_count":525,"area":null},{"id":"2212.14052","title":"Hungry Hungry Hippos: Towards Language Modeling with State Space Models","created":"2022-12-28","cited_by_count":499,"area":null},{"id":"2207.07115","title":"XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model","created":"2022-07-14","cited_by_count":439,"area":null},{"id":"2303.06349","title":"Resurrecting Recurrent Neural Networks for Long Sequences","created":"2023-03-11","cited_by_count":408,"area":null},{"id":"2105.04165","title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","created":"2021-05-10","cited_by_count":383,"area":null},{"id":"2103.07719","title":"Spectral Temporal Graph Neural Network for Multivariate Time-series Forecasting","created":"2021-03-13","cited_by_count":299,"area":null},{"id":"2211.14305","title":"SpaText: Spatio-Textual Representation for Controllable Image Generation","created":"2022-11-25","cited_by_count":217,"area":"diffusion"},{"id":"2207.06881","title":"Recurrent Memory Transformer","created":"2022-07-14","cited_by_count":203,"area":null},{"id":"2203.10421","title":"CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation","created":"2022-03-20","cited_by_count":194,"area":null},{"id":"2310.12982","title":"Putting the Object Back into Video Object Segmentation","created":"2023-10-19","cited_by_count":188,"area":null},{"id":"2103.09504","title":"PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning","created":"2021-03-17","cited_by_count":182,"area":null},{"id":"2208.09481","title":"Graph neural networks for materials science and chemistry","created":"2022-08-05","cited_by_count":182,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2103.14675","title":"Synthesis of Compositional Animations from Textual Descriptions","created":"2021-03-26","cited_by_count":178,"area":null},{"id":"2204.11817","title":"Translation between Molecules and Natural Language","created":"2022-04-25","cited_by_count":177,"area":null},{"id":"2305.06242","title":"Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving","created":"2023-05-10","cited_by_count":169,"area":"driving"},{"id":"2203.16804","title":"BRIO: Bringing Order to Abstractive Summarization","created":"2022-03-31","cited_by_count":161,"area":null},{"id":"2303.13047","title":"Towards Better Dynamic Graph Learning: New Architecture and Unified Library","created":"2023-03-23","cited_by_count":157,"area":null},{"id":"2101.05068","title":"Probabilistic Embeddings for Cross-Modal Retrieval","created":"2021-01-13","cited_by_count":151,"area":null},{"id":"2208.05233","title":"Spatial-Temporal Identity: A Simple yet Effective Baseline for Multivariate Time Series Forecasting","created":"2022-08-10","cited_by_count":151,"area":null},{"id":"2302.07387","title":"PolyFormer: Referring Image Segmentation as Sequential Polygon Generation","created":"2023-02-14","cited_by_count":148,"area":null},{"id":"2301.07608","title":"Human-Timescale Adaptation in an Open-Ended Task Space","created":"2023-01-18","cited_by_count":138,"area":null},{"id":"2211.05244","title":"Deep Learning for Time Series Anomaly Detection: A Survey","created":"2022-11-09","cited_by_count":131,"area":null},{"id":"2105.04387","title":"Recent Advances in Deep Learning Based Dialogue Systems: A Systematic Survey","created":"2021-05-10","cited_by_count":130,"area":null},{"id":"2104.01111","title":"A Comprehensive Survey of Scene Graphs: Generation and Application","created":"2021-03-17","cited_by_count":125,"area":null},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124,"area":null},{"id":"2206.09112","title":"Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting","created":"2022-06-18","cited_by_count":123,"area":null},{"id":"2206.09113","title":"Pre-training Enhanced Spatial-temporal Graph Neural Network for Multivariate Time Series Forecasting","created":"2022-06-18","cited_by_count":117,"area":null},{"id":"2310.06119","title":"Exploring Progress in Multivariate Time Series Forecasting: Comprehensive Benchmarking and Heterogeneity Analysis","created":"2023-10-09","cited_by_count":117,"area":null},{"id":"2106.11342","title":"Dive into Deep Learning","created":"2021-06-21","cited_by_count":111,"area":null},{"id":"2106.15115","title":"Neural Machine Translation for Low-Resource Languages: A Survey","created":"2021-06-29","cited_by_count":109,"area":null},{"id":"2503.02881","title":"Reactive Diffusion Policy: Slow-Fast Visual-Tactile Policy Learning for Contact-Rich Manipulation","created":"2025-03-04","cited_by_count":108,"area":"diffusion"},{"id":"2111.11344","title":"Modeling Irregular Time Series with Continuous Recurrent Units","created":"2021-11-22","cited_by_count":103,"area":null},{"id":"2110.13040","title":"Neural Flows: Efficient Alternative to Neural ODEs","created":"2021-10-25","cited_by_count":101,"area":null},{"id":"2304.05206","title":"The Capacity and Robustness Trade-off: Revisiting the Channel Independent Strategy for Multivariate Time Series Forecasting","created":"2023-04-11","cited_by_count":101,"area":null},{"id":"2304.11062","title":"Scaling Transformer to 1M tokens and beyond with RMT","created":"2023-04-19","cited_by_count":98,"area":null},{"id":"2103.13076","title":"Finetuning Pretrained Transformers into RNNs","created":"2021-03-24","cited_by_count":96,"area":null},{"id":"2502.14819","title":"Learning from Reward-Free Offline Data: A Case for Planning with Latent Dynamics Models","created":"2025-02-20","cited_by_count":89,"area":null},{"id":"2303.11717","title":"A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?","created":"2023-03-21","cited_by_count":84,"area":null},{"id":"2104.12668","title":"Appearance-based Gaze Estimation With Deep Learning: A Review and Benchmark","created":"2021-04-26","cited_by_count":82,"area":null},{"id":"2305.04111","title":"Efficient and Degree-Guided Graph Generation via Discrete Diffusion Modeling","created":"2023-05-06","cited_by_count":80,"area":"diffusion"},{"id":"2205.10337","title":"UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes","created":"2022-05-20","cited_by_count":78,"area":null},{"id":"2104.08336","title":"Self-Supervised Graph Neural Networks for Improved Electroencephalographic Seizure Analysis","created":"2021-04-16","cited_by_count":76,"area":null},{"id":"2403.14117","title":"A Design Space for Intelligent and Interactive Writing Assistants","created":"2024-03-21","cited_by_count":76,"area":null},{"id":"2404.14197","title":"SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion","created":"2024-04-22","cited_by_count":76,"area":null},{"id":"2206.08332","title":"BYOL-Explore: Exploration by Bootstrapped Prediction","created":"2022-06-16","cited_by_count":73,"area":null},{"id":"2205.08514","title":"Recovering Private Text in Federated Learning of Language Models","created":"2022-05-17","cited_by_count":70,"area":null},{"id":"2110.07238","title":"On the difficulty of learning chaotic dynamics with RNNs","created":"2021-10-14","cited_by_count":67,"area":null},{"id":"2202.02440","title":"Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation","created":"2022-02-05","cited_by_count":67,"area":null},{"id":"2104.02495","title":"Deep Animation Video Interpolation in the Wild","created":"2021-04-06","cited_by_count":65,"area":null},{"id":"2108.04718","title":"Sampling-Based Approximations to Minimum Bayes Risk Decoding for Neural Machine Translation","created":"2021-08-10","cited_by_count":65,"area":null},{"id":"2303.05970","title":"Exploring Recurrent Long-term Temporal Fusion for Multi-view 3D Perception","created":"2023-03-10","cited_by_count":65,"area":null},{"id":"2203.11335","title":"Global Matching with Overlapping Attention for Optical Flow Estimation","created":"2022-03-21","cited_by_count":64,"area":null},{"id":"2203.14263","title":"A General Survey on Attention Mechanisms in Deep Learning","created":"2022-03-27","cited_by_count":64,"area":null},{"id":"2203.16952","title":"Multimodal Fusion Transformer for Remote Sensing Image Classification","created":"2022-03-31","cited_by_count":64,"area":null},{"id":"2108.04556","title":"SynCoBERT: Syntax-Guided Multi-Modal Contrastive Pre-Training for Code Representation","created":"2021-08-10","cited_by_count":63,"area":null},{"id":"2111.12073","title":"Multi-Person 3D Motion Prediction with Multi-Range Transformers","created":"2021-11-23","cited_by_count":63,"area":null},{"id":"2402.10635","title":"ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling","created":"2024-02-16","cited_by_count":63,"area":null},{"id":"2101.12249","title":"A Survey of Complex-Valued Neural Networks","created":"2021-01-28","cited_by_count":61,"area":null},{"id":"2312.00786","title":"Dense Optical Tracking: Connecting the Dots","created":"2023-12-01","cited_by_count":61,"area":null},{"id":"2305.04868","title":"SignBERT+: Hand-model-aware Self-supervised Pre-training for Sign Language Understanding","created":"2023-05-08","cited_by_count":59,"area":null},{"id":"2306.04406","title":"Generalized Teacher Forcing for Learning Chaotic Dynamics","created":"2023-06-07","cited_by_count":58,"area":null},{"id":"2103.16083","title":"Fully Convolutional Scene Graph Generation","created":"2021-03-30","cited_by_count":57,"area":null},{"id":"2304.00008","title":"On the Creativity of Large Language Models","created":"2023-03-27","cited_by_count":57,"area":null},{"id":"2102.09546","title":"Deep Gait Recognition: A Survey","created":"2021-02-18","cited_by_count":54,"area":null},{"id":"2104.13918","title":"High-Resolution Optical Flow from 1D Attention and Correlation","created":"2021-04-28","cited_by_count":54,"area":null},{"id":"2108.06688","title":"Complex Knowledge Base Question Answering: A Survey","created":"2021-08-15","cited_by_count":52,"area":null},{"id":"2103.16775","title":"Attention, please! A survey of Neural Attention Models in Deep Learning","created":"2021-03-31","cited_by_count":51,"area":null},{"id":"2107.00096","title":"Improving black-box optimization in VAE latent space using decoder uncertainty","created":"2021-06-30","cited_by_count":51,"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":"2310.01387","title":"It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk","created":"2023-10-02","cited_by_count":51,"area":null},{"id":"2010.05134","title":"Deep Imitation Learning for Bimanual Robotic Manipulation","created":"2020-10-11","cited_by_count":50,"area":"offlinerl"},{"id":"2112.00544","title":"Molecular Contrastive Learning with Chemical Element Knowledge Graph","created":"2021-12-01","cited_by_count":50,"area":null},{"id":"2101.06116","title":"Hyperspectral Image Classification-Traditional to Deep Models: A Survey for Future Prospects","created":"2021-01-15","cited_by_count":49,"area":null},{"id":"2103.05558","title":"Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis","created":"2021-03-09","cited_by_count":49,"area":null},{"id":"2401.12665","title":"ClipSAM: CLIP and SAM Collaboration for Zero-Shot Anomaly Segmentation","created":"2024-01-23","cited_by_count":49,"area":null},{"id":"2104.05485","title":"Predicting Pedestrian Crossing Intention with Feature Fusion and Spatio-Temporal Attention","created":"2021-04-12","cited_by_count":48,"area":null},{"id":"2302.03548","title":"PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer","created":"2023-02-07","cited_by_count":48,"area":null},{"id":"2412.05149","title":"Findings of the Second BabyLM Challenge: Sample-Efficient Pretraining on Developmentally Plausible Corpora","created":"2024-12-06","cited_by_count":48,"area":null},{"id":"2308.11184","title":"ReFit: Recurrent Fitting Network for 3D Human Recovery","created":"2023-08-22","cited_by_count":47,"area":null},{"id":"2309.00810","title":"RenAIssance: A Survey into AI Text-to-Image Generation in the Era of Large Model","created":"2023-09-02","cited_by_count":47,"area":"diffusion"},{"id":"2510.00695","title":"HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy","created":"2025-10-01","cited_by_count":46,"area":"vla"},{"id":"2108.04468","title":"End-to-End User Behavior Retrieval in Click-Through RatePrediction Model","created":"2021-08-10","cited_by_count":45,"area":null},{"id":"2301.06574","title":"Causal Recurrent Variational Autoencoder for Medical Time Series Generation","created":"2023-01-16","cited_by_count":45,"area":null},{"id":"2309.12252","title":"Parallelizing non-linear sequential models over the sequence length","created":"2023-09-21","cited_by_count":45,"area":null},{"id":"1909.03449","title":"Imitation Learning for Human Pose Prediction","created":"2019-09-08","cited_by_count":44,"area":"offlinerl"},{"id":"2203.10316","title":"Learning to Reason Deductively: Math Word Problem Solving as Complex Relation Extraction","created":"2022-03-19","cited_by_count":44,"area":"lr"},{"id":"2210.09539","title":"Hierarchical Model-Based Imitation Learning for Planning in Autonomous Driving","created":"2022-10-18","cited_by_count":44,"area":"driving"},{"id":"2106.09373","title":"Unsupervised Path Representation Learning with Curriculum Negative Sampling","created":"2021-06-17","cited_by_count":42,"area":null},{"id":"2304.10168","title":"High-Fidelity and Freely Controllable Talking Head Video Generation","created":"2023-04-20","cited_by_count":42,"area":null},{"id":"2411.17190","title":"SelfSplat: Pose-Free and 3D Prior-Free Generalizable 3D Gaussian Splatting","created":"2024-11-26","cited_by_count":42,"area":null},{"id":"2203.09773","title":"Local-Global Context Aware Transformer for Language-Guided Video Segmentation","created":"2022-03-18","cited_by_count":41,"area":null},{"id":"2204.01726","title":"Lip to Speech Synthesis with Visual Context Attentional GAN","created":"2022-04-04","cited_by_count":41,"area":null},{"id":"2105.04090","title":"MuseMorphose: Full-Song and Fine-Grained Piano Music Style Transfer with One Transformer VAE","created":"2021-05-10","cited_by_count":40,"area":null},{"id":"2309.09294","title":"LivelySpeaker: Towards Semantic-Aware Co-Speech Gesture Generation","created":"2023-09-17","cited_by_count":40,"area":null},{"id":"2204.01725","title":"Distinguishing Homophenes Using Multi-Head Visual-Audio Memory for Lip Reading","created":"2022-04-04","cited_by_count":39,"area":null},{"id":"2204.09484","title":"Generalizing to the Future: Mitigating Entity Bias in Fake News Detection","created":"2022-04-20","cited_by_count":39,"area":null}],"next_cursor":"100"}