{"total":167,"rows":[{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255,"area":"diffusion"},{"id":"2102.04906","title":"Dynamic Neural Networks: A Survey","created":"2021-02-09","cited_by_count":408,"area":null},{"id":"2210.08823","title":"Scaling & Shifting Your Features: A New Baseline for Efficient Model Tuning","created":"2022-10-17","cited_by_count":294,"area":null},{"id":"2103.16874","title":"VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization","created":"2021-03-31","cited_by_count":287,"area":null},{"id":"2106.04489","title":"Parameter-efficient Multi-task Fine-tuning for Transformers via Shared Hypernetworks","created":"2021-06-08","cited_by_count":284,"area":null},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174,"area":"driving"},{"id":"2104.06849","title":"LEAP: Learning Articulated Occupancy of People","created":"2021-04-14","cited_by_count":107,"area":null},{"id":"2102.04432","title":"Colorization Transformer","created":"2021-02-08","cited_by_count":89,"area":null},{"id":"2109.06061","title":"Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting","created":"2021-09-13","cited_by_count":83,"area":null},{"id":"2302.11529","title":"Modular Deep Learning","created":"2023-02-22","cited_by_count":83,"area":null},{"id":"2212.00235","title":"VIDM: Video Implicit Diffusion Models","created":"2022-12-01","cited_by_count":78,"area":"diffusion"},{"id":"2203.07706","title":"ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation","created":"2022-03-15","cited_by_count":77,"area":null},{"id":"2106.02853","title":"Region-aware Adaptive Instance Normalization for Image Harmonization","created":"2021-06-05","cited_by_count":71,"area":null},{"id":"2105.07029","title":"Learning a Universal Template for Few-shot Dataset Generalization","created":"2021-05-14","cited_by_count":61,"area":null},{"id":"2111.01118","title":"Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training","created":"2021-11-01","cited_by_count":57,"area":null},{"id":"2203.15442","title":"Shifting More Attention to Visual Backbone: Query-modulated Refinement Networks for End-to-End Visual Grounding","created":"2022-03-29","cited_by_count":53,"area":"lr"},{"id":"2405.13998","title":"CViT: Continuous Vision Transformer for Operator Learning","created":"2024-05-22","cited_by_count":51,"area":null},{"id":"2206.00388","title":"Transfer without Forgetting","created":"2022-06-01","cited_by_count":44,"area":null},{"id":"2406.01210","title":"GeminiFusion: Efficient Pixel-wise Multimodal Fusion for Vision Transformer","created":"2024-06-03","cited_by_count":44,"area":null},{"id":"2211.11277","title":"DrapeNet: Garment Generation and Self-Supervised Draping","created":"2022-11-21","cited_by_count":41,"area":null},{"id":"2111.02625","title":"Qimera: Data-free Quantization with Synthetic Boundary Supporting Samples","created":"2021-11-04","cited_by_count":40,"area":null},{"id":"2206.09479","title":"StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis","created":"2022-06-19","cited_by_count":38,"area":null},{"id":"2301.08227","title":"Diffusion-based Conditional ECG Generation with Structured State Space Models","created":"2023-01-19","cited_by_count":36,"area":null},{"id":"2303.09554","title":"PartNeRF: Generating Part-Aware Editable 3D Shapes without 3D Supervision","created":"2023-03-16","cited_by_count":36,"area":null},{"id":"2111.06399","title":"Selective Synthetic Augmentation with HistoGAN for Improved Histopathology Image Classification","created":"2021-11-10","cited_by_count":35,"area":null},{"id":"2403.12952","title":"Just Shift It: Test-Time Prototype Shifting for Zero-Shot Generalization with Vision-Language Models","created":"2024-03-19","cited_by_count":32,"area":"mllm"},{"id":"2103.16341","title":"Learning Parallel Dense Correspondence from Spatio-Temporal Descriptors for Efficient and Robust 4D Reconstruction","created":"2021-03-30","cited_by_count":31,"area":null},{"id":"2106.09835","title":"Dual-Teacher Class-Incremental Learning With Data-Free Generative Replay","created":"2021-06-17","cited_by_count":31,"area":null},{"id":"2106.03620","title":"PcDGAN: A Continuous Conditional Diverse Generative Adversarial Network For Inverse Design","created":"2021-06-07","cited_by_count":30,"area":null},{"id":"2304.06600","title":"Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation","created":"2023-04-13","cited_by_count":29,"area":null},{"id":"2209.10304","title":"I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification","created":"2022-09-21","cited_by_count":27,"area":null},{"id":"2311.11178","title":"Active Prompt Learning in Vision Language Models","created":"2023-11-18","cited_by_count":25,"area":"mllm"},{"id":"2206.00050","title":"FiLM-Ensemble: Probabilistic Deep Learning via Feature-wise Linear Modulation","created":"2022-05-31","cited_by_count":24,"area":null},{"id":"2103.17267","title":"Bit-Mixer: Mixed-precision networks with runtime bit-width selection","created":"2021-03-31","cited_by_count":22,"area":null},{"id":"2208.00446","title":"Out-of-Distribution Detection with Semantic Mismatch under Masking","created":"2022-07-31","cited_by_count":22,"area":null},{"id":"2110.08525","title":"The Power of Prompt Tuning for Low-Resource Semantic Parsing","created":"2021-10-16","cited_by_count":21,"area":null},{"id":"2107.10060","title":"Conditional GANs with Auxiliary Discriminative Classifier","created":"2021-07-21","cited_by_count":20,"area":null},{"id":"2405.12420","title":"GarmentDreamer: 3DGS Guided Garment Synthesis with Diverse Geometry and Texture Details","created":"2024-05-20","cited_by_count":19,"area":null},{"id":"2310.03718","title":"Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning","created":"2023-10-05","cited_by_count":18,"area":null},{"id":"2106.09402","title":"Class Balancing GAN with a Classifier in the Loop","created":"2021-06-17","cited_by_count":17,"area":null},{"id":"2107.02638","title":"DocSynth: A Layout Guided Approach for Controllable Document Image Synthesis","created":"2021-07-06","cited_by_count":17,"area":null},{"id":"2110.08797","title":"Towards Language-guided Visual Recognition via Dynamic Convolutions","created":"2021-10-17","cited_by_count":17,"area":null},{"id":"2107.12815","title":"Adaptive Denoising via GainTuning","created":"2021-07-27","cited_by_count":16,"area":null},{"id":"2111.15207","title":"NeeDrop: Self-supervised Shape Representation from Sparse Point Clouds using Needle Dropping","created":"2021-11-30","cited_by_count":16,"area":null},{"id":"2312.05385","title":"Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving","created":"2023-12-08","cited_by_count":15,"area":"inference"},{"id":"2106.01629","title":"Semantic Palette: Guiding Scene Generation with Class Proportions","created":"2021-06-03","cited_by_count":14,"area":null},{"id":"2106.13409","title":"Generative Modeling for Multi-task Visual Learning","created":"2021-06-25","cited_by_count":14,"area":null},{"id":"2208.09932","title":"Improving GANs for Long-Tailed Data through Group Spectral Regularization","created":"2022-08-21","cited_by_count":14,"area":null},{"id":"2102.06696","title":"Efficient Conditional GAN Transfer with Knowledge Propagation across Classes","created":"2021-02-12","cited_by_count":13,"area":null},{"id":"2210.09297","title":"Neural Contact Fields: Tracking Extrinsic Contact with Tactile Sensing","created":"2022-10-17","cited_by_count":13,"area":null},{"id":"2102.03984","title":"One-shot Face Reenactment Using Appearance Adaptive Normalization","created":"2021-02-08","cited_by_count":12,"area":null},{"id":"2104.05077","title":"CoPE: Conditional image generation using Polynomial Expansions","created":"2021-04-11","cited_by_count":12,"area":null},{"id":"2106.03743","title":"Proxy-Normalizing Activations to Match Batch Normalization while Removing Batch Dependence","created":"2021-06-07","cited_by_count":12,"area":null},{"id":"2209.11173","title":"U-Sleep's resilience to AASM guidelines","created":"2022-09-19","cited_by_count":12,"area":null},{"id":"2211.03165","title":"Motion Style Transfer: Modular Low-Rank Adaptation for Deep Motion Forecasting","created":"2022-11-06","cited_by_count":12,"area":null},{"id":"2303.12368","title":"MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation","created":"2023-03-22","cited_by_count":12,"area":null},{"id":"2103.07470","title":"Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers","created":"2021-03-15","cited_by_count":11,"area":null},{"id":"2112.02252","title":"Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction","created":"2021-12-04","cited_by_count":11,"area":null},{"id":"2201.09650","title":"What You See is Not What the Network Infers: Detecting Adversarial Examples Based on Semantic Contradiction","created":"2022-01-24","cited_by_count":11,"area":null},{"id":"2104.10631","title":"MetricOpt: Learning to Optimize Black-Box Evaluation Metrics","created":"2021-04-21","cited_by_count":9,"area":null},{"id":"2106.08601","title":"Self-Supervised GANs with Label Augmentation","created":"2021-06-16","cited_by_count":9,"area":null},{"id":"2108.07886","title":"Modulating Language Models with Emotions","created":"2021-08-17","cited_by_count":9,"area":null},{"id":"2110.10640","title":"OSS-Net: Memory Efficient High Resolution Semantic Segmentation of 3D Medical Data","created":"2021-10-20","cited_by_count":9,"area":null},{"id":"2112.01073","title":"Controllable Video Captioning with an Exemplar Sentence","created":"2021-12-02","cited_by_count":9,"area":null},{"id":"2504.13112","title":"Hadamard product in deep learning: Introduction, Advances and Challenges","created":"2025-04-17","cited_by_count":9,"area":null},{"id":"2104.10857","title":"Attribute-Modulated Generative Meta Learning for Zero-Shot Classification","created":"2021-04-22","cited_by_count":8,"area":null},{"id":"2105.00020","title":"Continuous Face Aging via Self-estimated Residual Age Embedding","created":"2021-04-30","cited_by_count":8,"area":null},{"id":"2107.04240","title":"Deep Image Synthesis from Intuitive User Input: A Review and Perspectives","created":"2021-07-09","cited_by_count":8,"area":null},{"id":"2311.17050","title":"Surf-D: Generating High-Quality Surfaces of Arbitrary Topologies Using Diffusion Models","created":"2023-11-28","cited_by_count":8,"area":"diffusion"},{"id":"2102.11382","title":"Sandwich Batch Normalization: A Drop-In Replacement for Feature Distribution Heterogeneity","created":"2021-02-22","cited_by_count":7,"area":null},{"id":"2106.06736","title":"Multi-level Attention Fusion Network for Audio-visual Event Recognition","created":"2021-06-12","cited_by_count":7,"area":null},{"id":"2409.10419","title":"HiFi-CS: Towards Open Vocabulary Visual Grounding For Robotic Grasping Using Vision-Language Models","created":"2024-09-16","cited_by_count":7,"area":"mllm"},{"id":"2102.09582","title":"Benefits of Linear Conditioning with Metadata for Image Segmentation","created":"2021-02-18","cited_by_count":6,"area":null},{"id":"2302.08706","title":"Fine-grained Cross-modal Fusion based Refinement for Text-to-Image Synthesis","created":"2023-02-17","cited_by_count":6,"area":null},{"id":"2303.16412","title":"A Comprehensive and Versatile Multimodal Deep Learning Approach for Predicting Diverse Properties of Advanced Materials","created":"2023-03-29","cited_by_count":6,"area":null},{"id":"2311.16524","title":"3D Teeth Reconstruction from Panoramic Radiographs using Neural Implicit Functions","created":"2023-11-28","cited_by_count":6,"area":null},{"id":"2103.06230","title":"Range-GAN: Range-Constrained Generative Adversarial Network for Conditioned Design Synthesis","created":"2021-03-10","cited_by_count":5,"area":null},{"id":"2106.14274","title":"Learning Mesh Representations via Binary Space Partitioning Tree Networks","created":"2021-06-27","cited_by_count":5,"area":null},{"id":"2108.02104","title":"Point Discriminative Learning for Data-efficient 3D Point Cloud Analysis","created":"2021-08-04","cited_by_count":5,"area":null},{"id":"2203.16482","title":"RFNet-4D++: Joint Object Reconstruction and Flow Estimation from 4D Point Clouds with Cross-Attention Spatio-Temporal Features","created":"2022-03-30","cited_by_count":5,"area":null},{"id":"2210.11467","title":"Multi-View Guided Multi-View Stereo","created":"2022-10-20","cited_by_count":5,"area":null},{"id":"2101.03710","title":"ArrowGAN : Learning to Generate Videos by Learning Arrow of Time","created":"2021-01-11","cited_by_count":4,"area":null},{"id":"2109.15321","title":"Sensor-Guided Optical Flow","created":"2021-09-30","cited_by_count":4,"area":null},{"id":"2305.10309","title":"MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks","created":"2023-05-17","cited_by_count":4,"area":null},{"id":"2102.00696","title":"Numerical Weather Forecasting using Convolutional-LSTM with Attention and Context Matcher Mechanisms","created":"2021-02-01","cited_by_count":3,"area":null},{"id":"2106.02257","title":"Visual Question Rewriting for Increasing Response Rate","created":"2021-06-04","cited_by_count":3,"area":null},{"id":"2204.03703","title":"Physics-assisted Generative Adversarial Network for X-Ray Tomography","created":"2022-04-07","cited_by_count":3,"area":null},{"id":"2204.10689","title":"Reinforcing Generated Images via Meta-learning for One-Shot Fine-Grained Visual Recognition","created":"2022-04-22","cited_by_count":3,"area":null},{"id":"2205.03027","title":"A Highly Adaptive Acoustic Model for Accurate Multi-Dialect Speech Recognition","created":"2022-05-06","cited_by_count":3,"area":null},{"id":"2208.04226","title":"SKDCGN: Source-free Knowledge Distillation of Counterfactual Generative Networks using cGANs","created":"2022-08-08","cited_by_count":3,"area":"distill"},{"id":"2212.03836","title":"PaDPaF: Partial Disentanglement with Partially-Federated GANs","created":"2022-12-07","cited_by_count":3,"area":null},{"id":"2408.15640","title":"GANs Conditioning Methods: A Survey","created":"2024-08-28","cited_by_count":3,"area":null},{"id":"2410.16945","title":"IdenBAT: Disentangled Representation Learning for Identity-Preserved Brain Age Transformation","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2412.16777","title":"HyperCLIP: Adapting Vision-Language models with Hypernetworks","created":"2024-12-21","cited_by_count":3,"area":"mllm"},{"id":"2504.12588","title":"Plain Transformers Can be Powerful Graph Learners","created":"2025-04-17","cited_by_count":3,"area":null},{"id":"2101.12690","title":"Towards Generalising Neural Implicit Representations","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2106.15011","title":"Are conditional GANs explicitly conditional?","created":"2021-06-28","cited_by_count":2,"area":null},{"id":"2203.09639","title":"Generating unrepresented proportions of geological facies using Generative Adversarial Networks","created":"2022-03-17","cited_by_count":2,"area":null},{"id":"2208.01382","title":"A New Probabilistic V-Net Model with Hierarchical Spatial Feature Transform for Efficient Abdominal Multi-Organ Segmentation","created":"2022-08-02","cited_by_count":2,"area":null},{"id":"2301.07266","title":"ACQ: Improving Generative Data-free Quantization Via Attention Correction","created":"2023-01-18","cited_by_count":2,"area":null}],"next_cursor":"100"}