{"total":169,"rows":[{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718,"area":"ssm"},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336,"area":"ssm"},{"id":"2106.12423","title":"Alias-Free Generative Adversarial Networks","created":"2021-06-23","cited_by_count":1184,"area":null},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864,"area":"wm"},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815,"area":null},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613,"area":null},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514,"area":"ssm"},{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197,"area":"diffusion"},{"id":"2209.10655","title":"Mega: Moving Average Equipped Gated Attention","created":"2022-09-21","cited_by_count":179,"area":null},{"id":"2209.15594","title":"Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability","created":"2022-09-30","cited_by_count":155,"area":null},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132,"area":"diffusion"},{"id":"2205.09745","title":"Understanding Gradient Descent on Edge of Stability in Deep Learning","created":"2022-05-19","cited_by_count":128,"area":null},{"id":"2304.08577","title":"Avatars Grow Legs: Generating Smooth Human Motion from Sparse Tracking Inputs with Diffusion Model","created":"2023-04-17","cited_by_count":107,"area":"diffusion"},{"id":"2112.03530","title":"A Conditional Point Diffusion-Refinement Paradigm for 3D Point Cloud Completion","created":"2021-12-07","cited_by_count":100,"area":"diffusion"},{"id":"2105.13493","title":"Efficient and Accurate Gradients for Neural SDEs","created":"2021-05-27","cited_by_count":71,"area":null},{"id":"2312.07511","title":"A Hitchhiker's Guide to Geometric GNNs for 3D Atomic Systems","created":"2023-12-12","cited_by_count":68,"area":null},{"id":"2112.10809","title":"Lite Vision Transformer with Enhanced Self-Attention","created":"2021-12-20","cited_by_count":64,"area":null},{"id":"2103.01436","title":"ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations","created":"2021-03-02","cited_by_count":58,"area":null},{"id":"2304.03400","title":"RoSteALS: Robust Steganography using Autoencoder Latent Space","created":"2023-04-06","cited_by_count":57,"area":"safety"},{"id":"2110.01765","title":"Rapid training of deep neural networks without skip connections or normalization layers using Deep Kernel Shaping","created":"2021-10-05","cited_by_count":52,"area":null},{"id":"2404.15956","title":"A Survey on Visual Mamba","created":"2024-04-24","cited_by_count":50,"area":"ssm"},{"id":"2404.08801","title":"Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length","created":"2024-04-12","cited_by_count":46,"area":null},{"id":"2306.04321","title":"Generative Semantic Communication: Diffusion Models Beyond Bit Recovery","created":"2023-06-07","cited_by_count":41,"area":"diffusion"},{"id":"1810.11043","title":"One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks","created":"2018-10-25","cited_by_count":33,"area":"offlinerl"},{"id":"2503.14337","title":"PENCIL: Long Thoughts with Short Memory","created":"2025-03-18","cited_by_count":33,"area":"lr"},{"id":"2201.11279","title":"Revisiting RCAN: Improved Training for Image Super-Resolution","created":"2022-01-27","cited_by_count":32,"area":null},{"id":"2205.11775","title":"Constrained Monotonic Neural Networks","created":"2022-05-24","cited_by_count":32,"area":null},{"id":"2203.12338","title":"Real-time Object Detection for Streaming Perception","created":"2022-03-23","cited_by_count":30,"area":null},{"id":"2303.01215","title":"Why (and When) does Local SGD Generalize Better than SGD?","created":"2023-03-02","cited_by_count":26,"area":null},{"id":"2303.11828","title":"The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector","created":"2023-03-21","cited_by_count":25,"area":null},{"id":"2102.01670","title":"Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization","created":"2021-02-02","cited_by_count":22,"area":null},{"id":"2211.13613","title":"Ham2Pose: Animating Sign Language Notation into Pose Sequences","created":"2022-11-24","cited_by_count":21,"area":null},{"id":"2402.07245","title":"Semi-Mamba-UNet: Pixel-Level Contrastive and Pixel-Level Cross-Supervised Visual Mamba-based UNet for Semi-Supervised Medical Image Segmentation","created":"2024-02-11","cited_by_count":20,"area":"ssm"},{"id":"2110.15238","title":"Bolt: Bridging the Gap between Auto-tuners and Hardware-native Performance","created":"2021-10-25","cited_by_count":18,"area":null},{"id":"2402.05889","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","created":"2024-02-08","cited_by_count":17,"area":"lr"},{"id":"2304.14994","title":"A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks","created":"2023-04-28","cited_by_count":16,"area":null},{"id":"1909.12971","title":"Zero-shot Imitation Learning from Demonstrations for Legged Robot Visual Navigation","created":"2019-09-27","cited_by_count":13,"area":"offlinerl"},{"id":"2108.12943","title":"Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks","created":"2021-08-30","cited_by_count":13,"area":null},{"id":"2210.02093","title":"Centralized Feature Pyramid for Object Detection","created":"2022-10-05","cited_by_count":13,"area":null},{"id":"2410.05258","title":"Differential Transformer","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2503.10065","title":"Do We Always Need the Simplicity Bias? Looking for Optimal Inductive Biases in the Wild","created":"2025-03-13","cited_by_count":13,"area":null},{"id":"2204.08624","title":"Topology and geometry of data manifold in deep learning","created":"2022-04-19","cited_by_count":12,"area":null},{"id":"2204.00106","title":"A Survey of Robust 3D Object Detection Methods in Point Clouds","created":"2022-03-31","cited_by_count":10,"area":null},{"id":"2206.09379","title":"0/1 Deep Neural Networks via Block Coordinate Descent","created":"2022-06-19","cited_by_count":10,"area":null},{"id":"2109.09151","title":"Locally-symplectic neural networks for learning volume-preserving dynamics","created":"2021-09-19","cited_by_count":9,"area":null},{"id":"2111.10489","title":"Modeling Design and Control Problems Involving Neural Network Surrogates","created":"2021-11-20","cited_by_count":9,"area":null},{"id":"2405.02154","title":"Neural Context Flows for Meta-Learning of Dynamical Systems","created":"2024-05-03","cited_by_count":9,"area":null},{"id":"2506.15980","title":"Advanced Sign Language Video Generation with Compressed and Quantized Multi-Condition Tokenization","created":"2025-06-19","cited_by_count":9,"area":"diffusion"},{"id":"2108.13368","title":"Robust Interactive Semantic Segmentation of Pathology Images with Minimal User Input","created":"2021-08-30","cited_by_count":8,"area":null},{"id":"2112.09822","title":"Multimeasurement Generative Models","created":"2021-12-18","cited_by_count":8,"area":null},{"id":"2309.08208","title":"HM-Conformer: A Conformer-based audio deepfake detection system with hierarchical pooling and multi-level classification token aggregation methods","created":"2023-09-15","cited_by_count":8,"area":null},{"id":"2104.13101","title":"Initializing LSTM internal states via manifold learning","created":"2021-04-27","cited_by_count":7,"area":null},{"id":"2207.10433","title":"StreamYOLO: Real-time Object Detection for Streaming Perception","created":"2022-07-21","cited_by_count":7,"area":null},{"id":"2403.10858","title":"RetMIL: Retentive Multiple Instance Learning for Histopathological Whole Slide Image Classification","created":"2024-03-16","cited_by_count":7,"area":null},{"id":"2502.06996","title":"A view on learning robust goal-conditioned value functions: Interplay between RL and MPC","created":"2025-02-10","cited_by_count":7,"area":"deeprl"},{"id":"2107.06862","title":"Differentiable Programming of Reaction-Diffusion Patterns","created":"2021-06-22","cited_by_count":6,"area":null},{"id":"2208.12587","title":"Mitosis Detection, Fast and Slow: Robust and Efficient Detection of Mitotic Figures","created":"2022-08-26","cited_by_count":6,"area":null},{"id":"2210.05782","title":"Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models","created":"2022-10-11","cited_by_count":6,"area":null},{"id":"2501.06167","title":"Meta-Learning for Physically-Constrained Neural System Identification","created":"2025-01-10","cited_by_count":6,"area":null},{"id":"2505.00630","title":"Vision Mamba in Remote Sensing: A Comprehensive Survey of Techniques, Applications and Outlook","created":"2025-05-01","cited_by_count":6,"area":"ssm"},{"id":"2507.12933","title":"DMQ: Dissecting Outliers of Diffusion Models for Post-Training Quantization","created":"2025-07-17","cited_by_count":6,"area":"diffusion"},{"id":"2510.22777","title":"SeeDNorm: Self-Rescaled Dynamic Normalization","created":"2025-10-26","cited_by_count":6,"area":null},{"id":"2111.05986","title":"SyMetric: Measuring the Quality of Learnt Hamiltonian Dynamics Inferred from Vision","created":"2021-11-10","cited_by_count":5,"area":null},{"id":"2207.03954","title":"Black and Gray Box Learning of Amplitude Equations: Application to Phase Field Systems","created":"2022-07-08","cited_by_count":5,"area":null},{"id":"2209.13933","title":"DPNet: Dual-Path Network for Real-time Object Detection with Lightweight Attention","created":"2022-09-28","cited_by_count":5,"area":null},{"id":"2302.10913","title":"From paintbrush to pixel: A review of deep neural networks in AI-generated art","created":"2023-02-14","cited_by_count":5,"area":"diffusion"},{"id":"2306.03406","title":"Deep neural networks architectures from the perspective of manifold learning","created":"2023-06-06","cited_by_count":5,"area":null},{"id":"2407.04212","title":"Smart Vision-Language Reasoners","created":"2024-07-05","cited_by_count":5,"area":"lr"},{"id":"2502.20411","title":"Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2506.01153","title":"Weight-Space Linear Recurrent Neural Networks","created":"2025-06-01","cited_by_count":5,"area":null},{"id":"2104.11532","title":"3D Convolutional Neural Networks for Ultrasound-Based Silent Speech Interfaces","created":"2021-04-23","cited_by_count":4,"area":null},{"id":"2412.10338","title":"XYScanNet: A State Space Model for Single Image Deblurring","created":"2024-12-13","cited_by_count":4,"area":"ssm"},{"id":"2509.13240","title":"Don't Forget the Nonlinearity: Unlocking Activation Functions in Efficient Fine-Tuning","created":"2025-09-16","cited_by_count":4,"area":null},{"id":"2601.12791","title":"SKANet: A Cognitive Dual-Stream Framework with Adaptive Modality Fusion for Robust Compound GNSS Interference Classification","created":"2026-01-19","cited_by_count":4,"area":null},{"id":"2105.14933","title":"The use of Generative Adversarial Networks to characterise new physics in multi-lepton final states at the LHC","created":"2021-05-31","cited_by_count":3,"area":null},{"id":"2106.13445","title":"A Picture May Be Worth a Hundred Words for Visual Question Answering","created":"2021-06-25","cited_by_count":3,"area":null},{"id":"2204.05983","title":"Comparison Analysis of Traditional Machine Learning and Deep Learning Techniques for Data and Image Classification","created":"2022-04-11","cited_by_count":3,"area":null},{"id":"2210.04042","title":"Computing non-equilibrium trajectories by a deep learning approach","created":"2022-10-08","cited_by_count":3,"area":null},{"id":"2301.11783","title":"Certified Invertibility in Neural Networks via Mixed-Integer Programming","created":"2023-01-27","cited_by_count":3,"area":null},{"id":"2304.08498","title":"Ranking Loss and Sequestering Learning for Reducing Image Search Bias in Histopathology","created":"2023-04-15","cited_by_count":3,"area":null},{"id":"2305.18164","title":"Generative Adversarial Networks based Skin Lesion Segmentation","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2310.17658","title":"Is Channel Independent strategy optimal for Time Series Forecasting?","created":"2023-10-18","cited_by_count":3,"area":null},{"id":"2405.09052","title":"Dielectric Tensor Prediction for Inorganic Materials Using Latent Information from Preferred Potential","created":"2024-05-15","cited_by_count":3,"area":null},{"id":"2407.11074","title":"ST-RetNet: A Long-term Spatial-Temporal Traffic Flow Prediction Method","created":"2024-07-13","cited_by_count":3,"area":null},{"id":"2410.15678","title":"Revealing and Mitigating the Local Pattern Shortcuts of Mamba","created":"2024-10-21","cited_by_count":3,"area":"ssm"},{"id":"2412.17350","title":"DiffFormer: a Differential Spatial-Spectral Transformer for Hyperspectral Image Classification","created":"2024-12-23","cited_by_count":3,"area":null},{"id":"2501.08837","title":"MANTA: Diffusion Mamba for Efficient and Effective Stochastic Long-Term Dense Anticipation","created":"2025-01-15","cited_by_count":3,"area":"ssm"},{"id":"2501.17486","title":"DINT Transformer","created":"2025-01-29","cited_by_count":3,"area":null},{"id":"2511.06833","title":"ConsistTalk: Intensity Controllable Temporally Consistent Talking Head Generation with Diffusion Noise Search","created":"2025-11-10","cited_by_count":3,"area":"diffusion"},{"id":"2511.14348","title":"Enforcing hidden physics in physics-informed neural networks","created":"2025-11-18","cited_by_count":3,"area":null},{"id":"2605.24386","title":"Fermi-Dirac machines as quantizations of neurons","created":"2026-05-23","cited_by_count":3,"area":null},{"id":"2203.16973","title":"Analyzing the factors affecting usefulness of Self-Supervised Pre-trained Representations for Speech Recognition","created":"2022-03-31","cited_by_count":2,"area":null},{"id":"2209.06119","title":"APTx: better activation function than MISH, SWISH, and ReLU's variants used in deep learning","created":"2022-09-10","cited_by_count":2,"area":null},{"id":"2302.05433","title":"Unified Functional Hashing in Automatic Machine Learning","created":"2023-02-10","cited_by_count":2,"area":null},{"id":"2304.04058","title":"Learning Energy-Based Representations of Quantum Many-Body States","created":"2023-04-08","cited_by_count":2,"area":null},{"id":"2401.05596","title":"POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation","created":"2024-01-11","cited_by_count":2,"area":null},{"id":"2405.01943","title":"Dependency-Aware Semi-Structured Sparsity of GLU Variants in Large Language Models","created":"2024-05-03","cited_by_count":2,"area":null},{"id":"2406.10556","title":"Multi-User Semantic Fusion for Semantic Communications over Degraded Broadcast Channels","created":"2024-06-15","cited_by_count":2,"area":null},{"id":"2410.01655","title":"Reevaluating Meta-Learning Optimization Algorithms Through Contextual Self-Modulation","created":"2024-10-02","cited_by_count":2,"area":null},{"id":"2412.02399","title":"OMENN: One Matrix to Explain Neural Networks","created":"2024-12-03","cited_by_count":2,"area":null}],"next_cursor":"100"}