{"total":692,"rows":[{"id":"2302.06675","title":"Symbolic Discovery of Optimization Algorithms","created":"2023-02-13","cited_by_count":434,"area":null},{"id":"2104.06378","title":"QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering","created":"2021-04-13","cited_by_count":388,"area":null},{"id":"2111.14887","title":"DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation","created":"2021-11-29","cited_by_count":300,"area":null},{"id":"2309.14322","title":"Small-scale proxies for large-scale Transformer training instabilities","created":"2023-09-25","cited_by_count":183,"area":null},{"id":"2203.00555","title":"DeepNet: Scaling Transformers to 1,000 Layers","created":"2022-03-01","cited_by_count":178,"area":null},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177,"area":null},{"id":"2208.06677","title":"Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models","created":"2022-08-13","cited_by_count":174,"area":null},{"id":"2203.08065","title":"Surrogate Gap Minimization Improves Sharpness-Aware Training","created":"2022-03-15","cited_by_count":172,"area":null},{"id":"2204.00928","title":"SinNeRF: Training Neural Radiance Fields on Complex Scenes from a Single Image","created":"2022-04-02","cited_by_count":165,"area":null},{"id":"2102.12145","title":"GDRNPP: A Geometry-guided and Fully Learning-based Object Pose Estimator","created":"2021-02-24","cited_by_count":148,"area":null},{"id":"2104.05833","title":"Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization","created":"2021-04-12","cited_by_count":141,"area":null},{"id":"2206.03126","title":"Signal Propagation in Transformers: Theoretical Perspectives and the Role of Rank Collapse","created":"2022-06-07","cited_by_count":141,"area":null},{"id":"2402.16788","title":"Why Transformers Need Adam: A Hessian Perspective","created":"2024-02-26","cited_by_count":124,"area":null},{"id":"2208.09632","title":"Adam Can Converge Without Any Modification On Update Rules","created":"2022-08-20","cited_by_count":114,"area":null},{"id":"2204.05255","title":"Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information","created":"2022-04-11","cited_by_count":103,"area":null},{"id":"2304.02211","title":"METransformer: Radiology Report Generation by Transformer with Multiple Learnable Expert Tokens","created":"2023-04-05","cited_by_count":101,"area":null},{"id":"2202.03772","title":"Particle Transformer for Jet Tagging","created":"2022-02-08","cited_by_count":98,"area":null},{"id":"2203.07918","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","created":"2022-03-15","cited_by_count":94,"area":null},{"id":"2301.11189","title":"Improving Statistical Fidelity for Neural Image Compression with Implicit Local Likelihood Models","created":"2023-01-26","cited_by_count":94,"area":null},{"id":"2102.02754","title":"Only a Matter of Style: Age Transformation Using a Style-Based Regression Model","created":"2021-02-04","cited_by_count":92,"area":null},{"id":"2304.06819","title":"Modeling Dense Multimodal Interactions Between Biological Pathways and Histology for Survival Prediction","created":"2023-04-13","cited_by_count":92,"area":null},{"id":"2303.04947","title":"InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning","created":"2023-03-08","cited_by_count":90,"area":null},{"id":"2108.08367","title":"SO-Pose: Exploiting Self-Occlusion for Direct 6D Pose Estimation","created":"2021-08-18","cited_by_count":88,"area":null},{"id":"2206.07136","title":"Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger","created":"2022-06-14","cited_by_count":88,"area":null},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86,"area":null},{"id":"2112.00719","title":"HyperInverter: Improving StyleGAN Inversion via Hypernetwork","created":"2021-12-01","cited_by_count":85,"area":null},{"id":"2209.07556","title":"ZeroEGGS: Zero-shot Example-based Gesture Generation from Speech","created":"2022-09-15","cited_by_count":84,"area":null},{"id":"2103.02631","title":"RotoGrad: Gradient Homogenization in Multitask Learning","created":"2021-03-03","cited_by_count":83,"area":null},{"id":"2203.10016","title":"ESS: Learning Event-based Semantic Segmentation from Still Images","created":"2022-03-18","cited_by_count":82,"area":null},{"id":"2212.14034","title":"Cramming: Training a Language Model on a Single GPU in One Day","created":"2022-12-28","cited_by_count":81,"area":null},{"id":"2106.14343","title":"High-probability Bounds for Non-Convex Stochastic Optimization with Heavy Tails","created":"2021-06-28","cited_by_count":80,"area":null},{"id":"2107.10253","title":"Demonstration-Guided Reinforcement Learning with Learned Skills","created":"2021-07-21","cited_by_count":76,"area":null},{"id":"2410.15629","title":"Fully Explicit Dynamic Gaussian Splatting","created":"2024-10-21","cited_by_count":76,"area":null},{"id":"2104.00783","title":"Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems","created":"2021-04-01","cited_by_count":75,"area":null},{"id":"2103.14636","title":"A Practical Survey on Faster and Lighter Transformers","created":"2021-03-26","cited_by_count":73,"area":null},{"id":"2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","created":"2025-12-31","cited_by_count":72,"area":null},{"id":"2204.14244","title":"CLIP-Art: Contrastive Pre-training for Fine-Grained Art Classification","created":"2022-04-29","cited_by_count":65,"area":null},{"id":"2202.05274","title":"Motion Puzzle: Arbitrary Motion Style Transfer by Body Part","created":"2022-02-10","cited_by_count":64,"area":null},{"id":"2104.07302","title":"TransferNet: An Effective and Transparent Framework for Multi-hop Question Answering over Relation Graph","created":"2021-04-15","cited_by_count":60,"area":null},{"id":"2310.10198","title":"MoConVQ: Unified Physics-Based Motion Control via Scalable Discrete Representations","created":"2023-10-16","cited_by_count":60,"area":null},{"id":"2306.04406","title":"Generalized Teacher Forcing for Learning Chaotic Dynamics","created":"2023-06-07","cited_by_count":58,"area":null},{"id":"2102.07448","title":"OmniDet: Surround View Cameras based Multi-task Visual Perception Network for Autonomous Driving","created":"2021-02-15","cited_by_count":57,"area":null},{"id":"2211.09760","title":"VeLO: Training Versatile Learned Optimizers by Scaling Up","created":"2022-11-17","cited_by_count":57,"area":null},{"id":"2303.03108","title":"Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization","created":"2023-03-03","cited_by_count":57,"area":null},{"id":"2304.09987","title":"Tetra-NeRF: Representing Neural Radiance Fields Using Tetrahedra","created":"2023-04-19","cited_by_count":57,"area":null},{"id":"2401.00496","title":"SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge","created":"2023-12-31","cited_by_count":56,"area":null},{"id":"2211.12145","title":"Uncertainty-aware Vision-based Metric Cross-view Geolocalization","created":"2022-11-22","cited_by_count":54,"area":null},{"id":"2106.09017","title":"Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptation","created":"2021-06-16","cited_by_count":50,"area":null},{"id":"2110.03677","title":"Large Learning Rate Tames Homogeneity: Convergence and Balancing Effect","created":"2021-10-07","cited_by_count":50,"area":null},{"id":"2112.03459","title":"A Novel Convergence Analysis for Algorithms of the Adam Family","created":"2021-12-07","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":"2303.15743","title":"HS-Pose: Hybrid Scope Feature Extraction for Category-level Object Pose Estimation","created":"2023-03-28","cited_by_count":49,"area":null},{"id":"2204.00367","title":"Learning to Deblur using Light Field Generated and Real Defocus Images","created":"2022-04-01","cited_by_count":46,"area":null},{"id":"2406.09405","title":"Why Warmup the Learning Rate? Underlying Mechanisms and Improvements","created":"2024-06-13","cited_by_count":46,"area":null},{"id":"2105.02467","title":"Body Meshes as Points","created":"2021-05-06","cited_by_count":45,"area":null},{"id":"2211.07394","title":"Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization","created":"2022-11-14","cited_by_count":45,"area":null},{"id":"2102.08098","title":"GradInit: Learning to Initialize Neural Networks for Stable and Efficient Training","created":"2021-02-16","cited_by_count":44,"area":null},{"id":"2206.02338","title":"OrdinalCLIP: Learning Rank Prompts for Language-Guided Ordinal Regression","created":"2022-06-06","cited_by_count":44,"area":null},{"id":"2206.04656","title":"Simple Cues Lead to a Strong Multi-Object Tracker","created":"2022-06-09","cited_by_count":44,"area":null},{"id":"2208.00237","title":"RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation","created":"2022-07-30","cited_by_count":43,"area":null},{"id":"2410.01623","title":"Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?","created":"2024-10-02","cited_by_count":43,"area":null},{"id":"2501.16371","title":"Optimizing the Optimizer for Physics-Informed Neural Networks and Kolmogorov-Arnold Networks","created":"2025-01-22","cited_by_count":42,"area":null},{"id":"2107.02397","title":"Deep Network Approximation: Achieving Arbitrary Accuracy with Fixed Number of Neurons","created":"2021-07-06","cited_by_count":41,"area":null},{"id":"2206.06614","title":"Transformers are Meta-Reinforcement Learners","created":"2022-06-14","cited_by_count":41,"area":null},{"id":"2208.06661","title":"SSP-Pose: Symmetry-Aware Shape Prior Deformation for Direct Category-Level Object Pose Estimation","created":"2022-08-13","cited_by_count":41,"area":null},{"id":"2303.13497","title":"TriPlaneNet: An Encoder for EG3D Inversion","created":"2023-03-23","cited_by_count":41,"area":null},{"id":"2106.08208","title":"SUPER-ADAM: Faster and Universal Framework of Adaptive Gradients","created":"2021-06-15","cited_by_count":40,"area":null},{"id":"2112.02732","title":"JointLK: Joint Reasoning with Language Models and Knowledge Graphs for Commonsense Question Answering","created":"2021-12-06","cited_by_count":40,"area":null},{"id":"2105.01848","title":"PingAn-VCGroup's Solution for ICDAR 2021 Competition on Scientific Literature Parsing Task B: Table Recognition to HTML","created":"2021-05-05","cited_by_count":39,"area":null},{"id":"2108.12841","title":"Rethinking Deep Image Prior for Denoising","created":"2021-08-29","cited_by_count":38,"area":null},{"id":"2203.07932","title":"Style Transformer for Image Inversion and Editing","created":"2022-03-15","cited_by_count":37,"area":null},{"id":"2301.12832","title":"Deep networks for system identification: a Survey","created":"2023-01-30","cited_by_count":37,"area":null},{"id":"2601.14430","title":"Meta Flow Maps enable scalable reward alignment","created":"2026-01-20","cited_by_count":37,"area":null},{"id":"2303.12326","title":"Make Encoder Great Again in 3D GAN Inversion through Geometry and Occlusion-Aware Encoding","created":"2023-03-22","cited_by_count":35,"area":null},{"id":"2502.15938","title":"Straight to Zero: Why Linearly Decaying the Learning Rate to Zero Works Best for LLMs","created":"2025-02-21","cited_by_count":35,"area":null},{"id":"2510.17845","title":"MAT-Agent: Adaptive Multi-Agent Training Optimization","created":"2025-10-10","cited_by_count":35,"area":null},{"id":"2102.07753","title":"Learning Intra-Batch Connections for Deep Metric Learning","created":"2021-02-15","cited_by_count":34,"area":null},{"id":"2102.12459","title":"When Attention Meets Fast Recurrence: Training Language Models with Reduced Compute","created":"2021-02-24","cited_by_count":34,"area":null},{"id":"2203.10339","title":"Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation","created":"2022-03-19","cited_by_count":34,"area":null},{"id":"2303.11162","title":"Picture that Sketch: Photorealistic Image Generation from Abstract Sketches","created":"2023-03-20","cited_by_count":34,"area":null},{"id":"2104.07661","title":"E2Style: Improve the Efficiency and Effectiveness of StyleGAN Inversion","created":"2021-04-15","cited_by_count":33,"area":null},{"id":"2402.18377","title":"Out-of-Domain Generalization in Dynamical Systems Reconstruction","created":"2024-02-28","cited_by_count":33,"area":null},{"id":"2107.13741","title":"Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels","created":"2021-07-29","cited_by_count":32,"area":null},{"id":"2203.11860","title":"Practical tradeoffs between memory, compute, and performance in learned optimizers","created":"2022-03-22","cited_by_count":32,"area":null},{"id":"2210.02689","title":"Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence","created":"2022-10-06","cited_by_count":32,"area":null},{"id":"2410.08257","title":"Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics","created":"2024-10-10","cited_by_count":32,"area":null},{"id":"2502.09571","title":"DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra","created":"2025-02-13","cited_by_count":32,"area":null},{"id":"2304.08612","title":"Bridging Discrete and Backpropagation: Straight-Through and Beyond","created":"2023-04-17","cited_by_count":31,"area":null},{"id":"2509.15816","title":"On the Convergence of Muon and Beyond","created":"2025-09-19","cited_by_count":31,"area":null},{"id":"2106.03090","title":"Deep Matching Prior: Test-Time Optimization for Dense Correspondence","created":"2021-06-06","cited_by_count":30,"area":null},{"id":"2404.15272","title":"CT-GLIP: 3D Grounded Language-Image Pretraining with CT Scans and Radiology Reports for Full-Body Scenarios","created":"2024-04-23","cited_by_count":30,"area":null},{"id":"2207.08082","title":"CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement","created":"2022-07-17","cited_by_count":29,"area":null},{"id":"2208.01957","title":"PolarMOT: How Far Can Geometric Relations Take Us in 3D Multi-Object Tracking?","created":"2022-08-03","cited_by_count":29,"area":null},{"id":"2408.11029","title":"Scaling Law with Learning Rate Annealing","created":"2024-08-20","cited_by_count":29,"area":null},{"id":"2103.17182","title":"Positive-Negative Momentum: Manipulating Stochastic Gradient Noise to Improve Generalization","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2306.03009","title":"Using Sequences of Life-events to Predict Human Lives","created":"2023-06-05","cited_by_count":27,"area":null},{"id":"2307.11108","title":"Flatness-Aware Minimization for Domain Generalization","created":"2023-07-20","cited_by_count":27,"area":null},{"id":"2304.13615","title":"Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentation","created":"2023-04-26","cited_by_count":26,"area":null},{"id":"2306.17833","title":"Resetting the Optimizer in Deep RL: An Empirical Study","created":"2023-06-30","cited_by_count":26,"area":null},{"id":"2102.05320","title":"An Adaptive Stochastic Sequential Quadratic Programming with Differentiable Exact Augmented Lagrangians","created":"2021-02-10","cited_by_count":25,"area":null}],"next_cursor":"100"}