{"total":703,"rows":[{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969,"area":null},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651,"area":null},{"id":"2110.02178","title":"MobileViT: Light-weight, General-purpose, and Mobile-friendly Vision Transformer","created":"2021-10-05","cited_by_count":642,"area":null},{"id":"2111.11418","title":"MetaFormer Is Actually What You Need for Vision","created":"2021-11-22","cited_by_count":524,"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":"2101.11605","title":"Bottleneck Transformers for Visual Recognition","created":"2021-01-27","cited_by_count":364,"area":null},{"id":"2106.08903","title":"GemNet: Universal Directional Graph Neural Networks for Molecules","created":"2021-06-02","cited_by_count":343,"area":null},{"id":"2104.14421","title":"What Are Bayesian Neural Network Posteriors Really Like?","created":"2021-04-29","cited_by_count":308,"area":null},{"id":"2209.02976","title":"YOLOv6: A Single-Stage Object Detection Framework for Industrial Applications","created":"2022-09-07","cited_by_count":275,"area":null},{"id":"2206.11990","title":"Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs","created":"2022-06-23","cited_by_count":264,"area":null},{"id":"2306.12873","title":"FuXi: A cascade machine learning forecasting system for 15-day global weather forecast","created":"2023-06-22","cited_by_count":241,"area":null},{"id":"2203.08195","title":"DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection","created":"2022-03-15","cited_by_count":224,"area":null},{"id":"2103.12731","title":"Scaling Local Self-Attention for Parameter Efficient Visual Backbones","created":"2021-03-23","cited_by_count":220,"area":null},{"id":"2306.12059","title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","created":"2023-06-21","cited_by_count":204,"area":null},{"id":"2202.10447","title":"Transformer Quality in Linear Time","created":"2022-02-21","cited_by_count":191,"area":null},{"id":"2402.17152","title":"Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendations","created":"2024-02-27","cited_by_count":188,"area":null},{"id":"2203.06904","title":"Delta Tuning: A Comprehensive Study of Parameter Efficient Methods for Pre-trained Language Models","created":"2022-03-14","cited_by_count":180,"area":null},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2206.02680","title":"Separable Self-attention for Mobile Vision Transformers","created":"2022-06-06","cited_by_count":163,"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":"2210.09782","title":"Decoupling Features in Hierarchical Propagation for Video Object Segmentation","created":"2022-10-18","cited_by_count":148,"area":null},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141,"area":null},{"id":"2103.11511","title":"MoViNets: Mobile Video Networks for Efficient Video Recognition","created":"2021-03-21","cited_by_count":135,"area":null},{"id":"2212.10650","title":"KronA: Parameter Efficient Tuning with Kronecker Adapter","created":"2022-12-20","cited_by_count":133,"area":null},{"id":"2307.03170","title":"Focused Transformer: Contrastive Training for Context Scaling","created":"2023-07-06","cited_by_count":133,"area":null},{"id":"2210.04123","title":"DIMES: A Differentiable Meta Solver for Combinatorial Optimization Problems","created":"2022-10-08","cited_by_count":129,"area":null},{"id":"2302.03655","title":"Reducing SO(3) Convolutions to SO(2) for Efficient Equivariant GNNs","created":"2023-02-07","cited_by_count":117,"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":"2206.04040","title":"MobileOne: An Improved One millisecond Mobile Backbone","created":"2022-06-08","cited_by_count":109,"area":null},{"id":"2105.00304","title":"SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects","created":"2021-05-01","cited_by_count":104,"area":null},{"id":"2205.06643","title":"The Design Space of E(3)-Equivariant Atom-Centered Interatomic Potentials","created":"2022-05-13","cited_by_count":101,"area":null},{"id":"2312.03701","title":"Return of Unconditional Generation: A Self-supervised Representation Generation Method","created":"2023-12-06","cited_by_count":98,"area":null},{"id":"2202.08450","title":"Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization","created":"2022-02-17","cited_by_count":97,"area":null},{"id":"2306.10574","title":"Score-based Data Assimilation","created":"2023-06-18","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":"2101.08692","title":"Characterizing signal propagation to close the performance gap in unnormalized ResNets","created":"2021-01-21","cited_by_count":88,"area":null},{"id":"2106.13195","title":"FitVid: Overfitting in Pixel-Level Video Prediction","created":"2021-06-24","cited_by_count":87,"area":null},{"id":"2205.11961","title":"ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts","created":"2022-05-24","cited_by_count":85,"area":null},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80,"area":null},{"id":"2502.20762","title":"Towards Practical Real-Time Neural Video Compression","created":"2025-02-28","cited_by_count":80,"area":null},{"id":"2309.14032","title":"DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization","created":"2023-09-25","cited_by_count":78,"area":null},{"id":"2105.13493","title":"Efficient and Accurate Gradients for Neural SDEs","created":"2021-05-27","cited_by_count":71,"area":null},{"id":"2204.06806","title":"YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss","created":"2022-04-14","cited_by_count":68,"area":null},{"id":"2106.02347","title":"SE(3)-equivariant prediction of molecular wavefunctions and electronic densities","created":"2021-06-04","cited_by_count":67,"area":null},{"id":"2402.03804","title":"ReLU$^2$ Wins: Discovering Efficient Activation Functions for Sparse LLMs","created":"2024-02-06","cited_by_count":67,"area":null},{"id":"2305.10862","title":"How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses","created":"2023-05-18","cited_by_count":66,"area":null},{"id":"2209.07399","title":"A Light Recipe to Train Robust Vision Transformers","created":"2022-09-15","cited_by_count":64,"area":null},{"id":"2307.02469","title":"What Matters in Training a GPT4-Style Language Model with Multimodal Inputs?","created":"2023-07-05","cited_by_count":64,"area":null},{"id":"2408.00712","title":"MotionFix: Text-Driven 3D Human Motion Editing","created":"2024-08-01","cited_by_count":64,"area":null},{"id":"2212.06347","title":"Reliable extrapolation of deep neural operators informed by physics or sparse observations","created":"2022-12-13","cited_by_count":62,"area":null},{"id":"2310.05573","title":"ODEFormer: Symbolic Regression of Dynamical Systems with Transformers","created":"2023-10-09","cited_by_count":62,"area":null},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2211.03295","title":"MogaNet: Multi-order Gated Aggregation Network","created":"2022-11-07","cited_by_count":59,"area":null},{"id":"2306.10619","title":"Towards Stability of Autoregressive Neural Operators","created":"2023-06-18","cited_by_count":59,"area":null},{"id":"2503.18860","title":"HunyuanPortrait: Implicit Condition Control for Enhanced Portrait Animation","created":"2025-03-24","cited_by_count":59,"area":null},{"id":"2104.04448","title":"Relating Adversarially Robust Generalization to Flat Minima","created":"2021-04-09","cited_by_count":57,"area":null},{"id":"2310.06434","title":"Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition","created":"2023-10-10","cited_by_count":56,"area":null},{"id":"2409.10594","title":"Kolmogorov-Arnold Transformer","created":"2024-09-16","cited_by_count":56,"area":null},{"id":"2312.08459","title":"FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models","created":"2023-12-13","cited_by_count":55,"area":null},{"id":"2406.15007","title":"RouteFinder: Towards Foundation Models for Vehicle Routing Problems","created":"2024-06-21","cited_by_count":55,"area":null},{"id":"2604.12946","title":"Parcae: Scaling Laws For Stable Looped Language Models","created":"2026-04-14","cited_by_count":55,"area":null},{"id":"2403.07041","title":"Ant Colony Sampling with GFlowNets for Combinatorial Optimization","created":"2024-03-11","cited_by_count":53,"area":null},{"id":"2404.13671","title":"FiLo: Zero-Shot Anomaly Detection by Fine-Grained Description and High-Quality Localization","created":"2024-04-21","cited_by_count":51,"area":null},{"id":"2203.09410","title":"A Framework and Benchmark for Deep Batch Active Learning for Regression","created":"2022-03-17","cited_by_count":49,"area":null},{"id":"2407.05551","title":"Read, Watch and Scream! Sound Generation from Text and Video","created":"2024-07-08","cited_by_count":48,"area":null},{"id":"2412.09492","title":"Video Seal: Open and Efficient Video Watermarking","created":"2024-12-12","cited_by_count":48,"area":null},{"id":"2209.09893","title":"Deep Generalized Schr\\\"odinger Bridge","created":"2022-09-20","cited_by_count":47,"area":null},{"id":"2209.13351","title":"SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery","created":"2022-09-27","cited_by_count":47,"area":null},{"id":"2305.17852","title":"Hierarchical Neural Memory Network for Low Latency Event Processing","created":"2023-05-29","cited_by_count":47,"area":null},{"id":"2308.16258","title":"Robust Principles: Architectural Design Principles for Adversarially Robust CNNs","created":"2023-08-30","cited_by_count":46,"area":null},{"id":"2310.05963","title":"CFDBench: A Large-Scale Benchmark for Machine Learning Methods in Fluid Dynamics","created":"2023-09-13","cited_by_count":46,"area":null},{"id":"2205.15175","title":"ShuffleMixer: An Efficient ConvNet for Image Super-Resolution","created":"2022-05-30","cited_by_count":45,"area":null},{"id":"2105.12931","title":"YOLO5Face: Why Reinventing a Face Detector","created":"2021-05-27","cited_by_count":44,"area":null},{"id":"2209.00530","title":"Holomorphic Equilibrium Propagation Computes Exact Gradients Through Finite Size Oscillations","created":"2022-09-01","cited_by_count":42,"area":null},{"id":"2206.14476","title":"Can Push-forward Generative Models Fit Multimodal Distributions?","created":"2022-06-29","cited_by_count":41,"area":null},{"id":"2406.07266","title":"SemlaFlow -- Efficient 3D Molecular Generation with Latent Attention and Equivariant Flow Matching","created":"2024-06-11","cited_by_count":41,"area":null},{"id":"2508.15884","title":"Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search","created":"2025-08-21","cited_by_count":41,"area":null},{"id":"2306.07473","title":"3D molecule generation by denoising voxel grids","created":"2023-06-13","cited_by_count":40,"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":"2401.08295","title":"SAPT: A Shared Attention Framework for Parameter-Efficient Continual Learning of Large Language Models","created":"2024-01-16","cited_by_count":38,"area":null},{"id":"2409.06202","title":"RealisDance: Equip controllable character animation with realistic hands","created":"2024-09-10","cited_by_count":37,"area":null},{"id":"2406.15333","title":"GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation","created":"2024-06-21","cited_by_count":36,"area":null},{"id":"2402.18512","title":"Log Neural Controlled Differential Equations: The Lie Brackets Make a Difference","created":"2024-02-28","cited_by_count":35,"area":null},{"id":"2405.17527","title":"Unisolver: PDE-Conditional Transformers Towards Universal Neural PDE Solvers","created":"2024-05-27","cited_by_count":35,"area":null},{"id":"2302.00456","title":"Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Maps","created":"2023-02-01","cited_by_count":33,"area":null},{"id":"2307.06555","title":"Deep Network Approximation: Beyond ReLU to Diverse Activation Functions","created":"2023-07-13","cited_by_count":33,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2502.06415","title":"Systematic Outliers in Large Language Models","created":"2025-02-10","cited_by_count":33,"area":null},{"id":"2110.03303","title":"Universal Approximation Under Constraints is Possible with Transformers","created":"2021-10-07","cited_by_count":32,"area":null},{"id":"2405.14567","title":"EHRMamba: Towards Generalizable and Scalable Foundation Models for Electronic Health Records","created":"2024-05-23","cited_by_count":32,"area":null},{"id":"2106.03180","title":"Vision Transformers with Hierarchical Attention","created":"2021-06-06","cited_by_count":31,"area":null},{"id":"2109.09721","title":"Machine-learning hidden symmetries","created":"2021-09-20","cited_by_count":31,"area":null},{"id":"2310.18846","title":"INCODE: Implicit Neural Conditioning with Prior Knowledge Embeddings","created":"2023-10-28","cited_by_count":31,"area":null},{"id":"2102.02340","title":"MUFASA: Multimodal Fusion Architecture Search for Electronic Health Records","created":"2021-02-03","cited_by_count":30,"area":null},{"id":"2208.07337","title":"SYN-MAD 2022: Competition on Face Morphing Attack Detection Based on Privacy-aware Synthetic Training Data","created":"2022-08-15","cited_by_count":30,"area":null},{"id":"2502.17410","title":"COSMOS: A Hybrid Adaptive Optimizer for Memory-Efficient Training of LLMs","created":"2025-02-24","cited_by_count":30,"area":null},{"id":"2404.06665","title":"Deep Generative Data Assimilation in Multimodal Setting","created":"2024-04-10","cited_by_count":29,"area":null},{"id":"2405.14747","title":"TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes","created":"2024-05-23","cited_by_count":29,"area":null},{"id":"2309.06262","title":"Modality Unifying Network for Visible-Infrared Person Re-Identification","created":"2023-09-12","cited_by_count":27,"area":null},{"id":"2309.16354","title":"Transformer-VQ: Linear-Time Transformers via Vector Quantization","created":"2023-09-28","cited_by_count":26,"area":null}],"next_cursor":"100"}