{"list":"other","total":66,"rows":[{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"1912.01703","title":"PyTorch: An Imperative Style, High-Performance Deep Learning Library","created":"2019-12-03","cited_by_count":20305},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2307.09288","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","created":"2023-07-18","cited_by_count":13028},{"id":"1503.02531","title":"Distilling the Knowledge in a Neural Network","created":"2015-03-09","cited_by_count":10324},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"2401.14196","title":"DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence","created":"2024-01-25","cited_by_count":1181},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2311.18828","title":"One-step Diffusion with Distribution Matching Distillation","created":"2023-11-30","cited_by_count":1019},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"2310.04378","title":"Latent Consistency Models: Synthesizing High-Resolution Images with Few-Step Inference","created":"2023-10-06","cited_by_count":846},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759},{"id":"2408.12528","title":"Show-o: One Single Transformer to Unify Multimodal Understanding and Generation","created":"2024-08-22","cited_by_count":752},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"2012.12556","title":"A Survey on Visual Transformer","created":"2020-12-23","cited_by_count":654},{"id":"2406.11838","title":"Autoregressive Image Generation without Vector Quantization","created":"2024-06-17","cited_by_count":651},{"id":"2204.13902","title":"Fast Sampling of Diffusion Models with Exponential Integrator","created":"2022-04-29","cited_by_count":532},{"id":"2408.11039","title":"Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Model","created":"2024-08-20","cited_by_count":483},{"id":"2307.12348","title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","created":"2023-07-23","cited_by_count":365},{"id":"2312.00858","title":"DeepCache: Accelerating Diffusion Models for Free","created":"2023-12-01","cited_by_count":359},{"id":"2201.06503","title":"Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models","created":"2022-01-17","cited_by_count":334},{"id":"2302.04304","title":"Q-Diffusion: Quantizing Diffusion Models","created":"2023-02-08","cited_by_count":273},{"id":"2211.15736","title":"Post-training Quantization on Diffusion Models","created":"2022-11-28","cited_by_count":267},{"id":"2306.00980","title":"SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds","created":"2023-06-01","cited_by_count":227},{"id":"2301.12900","title":"DepGraph: Towards Any Structural Pruning","created":"2023-01-30","cited_by_count":203},{"id":"2305.10924","title":"Structural Pruning for Diffusion Models","created":"2023-05-18","cited_by_count":195},{"id":"2411.05007","title":"SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","created":"2024-11-07","cited_by_count":170},{"id":"2310.13268","title":"DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics","created":"2023-10-20","cited_by_count":161},{"id":"2409.04410","title":"Open-MAGVIT2: An Open-Source Project Toward Democratizing Auto-regressive Visual Generation","created":"2024-09-06","cited_by_count":155},{"id":"2312.03209","title":"Cache Me if You Can: Accelerating Diffusion Models through Block Caching","created":"2023-12-06","cited_by_count":151},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150},{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2211.17106","title":"Diffusion Probabilistic Model Made Slim","created":"2022-11-27","cited_by_count":121},{"id":"2205.12524","title":"Accelerating Diffusion Models via Early Stop of the Diffusion Process","created":"2022-05-25","cited_by_count":100},{"id":"2402.19481","title":"DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models","created":"2024-02-29","cited_by_count":98},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94},{"id":"2410.01699","title":"Accelerating Auto-regressive Text-to-Image Generation with Training-free Speculative Jacobi Decoding","created":"2024-10-02","cited_by_count":66},{"id":"2406.09750","title":"ControlVAR: Exploring Controllable Visual Autoregressive Modeling","created":"2024-06-14","cited_by_count":58},{"id":"2411.01738","title":"xDiT: an Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism","created":"2024-11-04","cited_by_count":56},{"id":"2404.11098","title":"LAPTOP-Diff: Layer Pruning and Normalized Distillation for Compressing Diffusion Models","created":"2024-04-17","cited_by_count":53},{"id":"2410.02705","title":"ControlAR: Controllable Image Generation with Autoregressive Models","created":"2024-10-03","cited_by_count":48},{"id":"2410.03355","title":"LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding","created":"2024-10-04","cited_by_count":47},{"id":"2407.07614","title":"MARS: Mixture of Auto-Regressive Models for Fine-grained Text-to-image Synthesis","created":"2024-07-10","cited_by_count":44},{"id":"2408.01181","title":"VAR-CLIP: Text-to-Image Generator with Visual Auto-Regressive Modeling","created":"2024-08-02","cited_by_count":42},{"id":"2410.08159","title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation","created":"2024-10-10","cited_by_count":32},{"id":"2410.04671","title":"CAR: Controllable Autoregressive Modeling for Visual Generation","created":"2024-10-07","cited_by_count":30},{"id":"2406.10797","title":"STAR: Scale-wise Text-conditioned AutoRegressive image generation","created":"2024-06-16","cited_by_count":28},{"id":"2408.12245","title":"Scalable Autoregressive Image Generation with Mamba","created":"2024-08-22","cited_by_count":26},{"id":"2406.06911","title":"AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising","created":"2024-06-11","cited_by_count":22},{"id":"2312.05284","title":"SlimSAM: 0.1% Data Makes Segment Anything Slim","created":"2023-12-08","cited_by_count":20},{"id":"2404.06091","title":"Hash3D: Training-free Acceleration for 3D Generation","created":"2024-04-09","cited_by_count":19},{"id":"2409.06322","title":"G3PT: Unleash the power of Autoregressive Modeling in 3D Generation via Cross-scale Querying Transformer","created":"2024-09-10","cited_by_count":16},{"id":"2408.09027","title":"Efficient Autoregressive Audio Modeling via Next-Scale Prediction","created":"2024-08-16","cited_by_count":11}],"next_cursor":null}