{"list":"other","total":70,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"1510.00149","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","created":"2015-10-01","cited_by_count":2329},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2305.13048","title":"RWKV: Reinventing RNNs for the Transformer Era","created":"2023-05-22","cited_by_count":827},{"id":"2409.18869","title":"Emu3: Next-Token Prediction is All You Need","created":"2024-09-27","cited_by_count":781},{"id":"2406.06525","title":"Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation","created":"2024-06-10","cited_by_count":777},{"id":"1711.09078","title":"Video Enhancement with Task-Oriented Flow","created":"2017-11-24","cited_by_count":619},{"id":"2312.06635","title":"Gated Linear Attention Transformers with Hardware-Efficient Training","created":"2023-12-11","cited_by_count":514},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2208.09392","title":"Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise","created":"2022-08-19","cited_by_count":276},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233},{"id":"2309.10668","title":"Language Modeling Is Compression","created":"2023-09-19","cited_by_count":225},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2206.13397","title":"Generative Modelling With Inverse Heat Dissipation","created":"2022-06-21","cited_by_count":167},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"2404.07904","title":"HGRN2: Gated Linear RNNs with State Expansion","created":"2024-04-11","cited_by_count":127},{"id":"2402.17414","title":"Neural Video Compression with Feature Modulation","created":"2024-02-27","cited_by_count":123},{"id":"2209.05442","title":"Soft Diffusion: Score Matching for General Corruptions","created":"2022-09-12","cited_by_count":102},{"id":"2304.02633","title":"HNeRV: A Hybrid Neural Representation for Videos","created":"2023-04-05","cited_by_count":100},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"2303.09508","title":"LDMVFI: Video Frame Interpolation with Latent Diffusion Models","created":"2023-03-16","cited_by_count":89},{"id":"2309.03350","title":"Relay Diffusion: Unifying diffusion process across resolutions for image synthesis","created":"2023-09-04","cited_by_count":79},{"id":"2206.07307","title":"VCT: A Video Compression Transformer","created":"2022-06-15","cited_by_count":74},{"id":"2306.09818","title":"HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation","created":"2023-06-16","cited_by_count":71},{"id":"2006.09952","title":"Universally Quantized Neural Compression","created":"2020-06-17","cited_by_count":64},{"id":"2404.09937","title":"Compression Represents Intelligence Linearly","created":"2024-04-15","cited_by_count":56},{"id":"2312.02753","title":"C3: High-performance and low-complexity neural compression from a single image or video","created":"2023-12-05","cited_by_count":55},{"id":"2008.06091","title":"A Technical Overview of AV1","created":"2020-08-13","cited_by_count":47},{"id":"2207.05315","title":"CANF-VC: Conditional Augmented Normalizing Flows for Video Compression","created":"2022-07-12","cited_by_count":46},{"id":"2210.08772","title":"Signal Processing for Implicit Neural Representations","created":"2022-10-17","cited_by_count":46},{"id":"2212.12294","title":"FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos","created":"2022-12-23","cited_by_count":46},{"id":"2304.06544","title":"DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos","created":"2023-04-13","cited_by_count":42},{"id":"2403.14148","title":"Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition","created":"2024-03-21","cited_by_count":42},{"id":"2101.08687","title":"Overfitting for Fun and Profit: Instance-Adaptive Data Compression","created":"2021-01-21","cited_by_count":38},{"id":"2303.14124","title":"Towards Scalable Neural Representation for Diverse Videos","created":"2023-03-24","cited_by_count":37},{"id":"2404.08580","title":"Lossy Image Compression with Foundation Diffusion Models","created":"2024-04-12","cited_by_count":36},{"id":"2208.13056","title":"Lossy Image Compression with Quantized Hierarchical VAEs","created":"2022-08-27","cited_by_count":35},{"id":"2212.07372","title":"Image Compression with Product Quantized Masked Image Modeling","created":"2022-12-14","cited_by_count":33},{"id":"2208.03742","title":"PS-NeRV: Patch-wise Stylized Neural Representations for Videos","created":"2022-08-07","cited_by_count":32},{"id":"2210.04955","title":"f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation","created":"2022-10-10","cited_by_count":32},{"id":"2402.18152","title":"Boosting Neural Representations for Videos with a Conditional Decoder","created":"2024-02-28","cited_by_count":29},{"id":"2409.07414","title":"NVRC: Neural Video Representation Compression","created":"2024-09-11","cited_by_count":29},{"id":"2405.15413","title":"MambaVC: Learned Visual Compression with Selective State Spaces","created":"2024-05-24","cited_by_count":28},{"id":"2403.15679","title":"DS-NeRV: Implicit Neural Video Representation with Decomposed Static and Dynamic Codes","created":"2024-03-23","cited_by_count":25},{"id":"2502.05741","title":"Linear Attention Modeling for Learned Image Compression","created":"2025-02-09","cited_by_count":23},{"id":"2410.09706","title":"ECVC: Exploiting Non-Local Correlations in Multiple Frames for Contextual Video Compression","created":"2024-10-13","cited_by_count":20},{"id":"2409.00953","title":"PNVC: Towards Practical INR-based Video Compression","created":"2024-09-02","cited_by_count":19},{"id":"2412.03748","title":"HIIF: Hierarchical Encoding based Implicit Image Function for Continuous Super-resolution","created":"2024-12-04","cited_by_count":17},{"id":"2408.08093","title":"When Video Coding Meets Multimodal Large Language Models: A Unified Paradigm for Video Coding","created":"2024-08-15","cited_by_count":11},{"id":"2209.09422","title":"Bit Allocation using Optimization","created":"2022-09-20","cited_by_count":9},{"id":"2009.07583","title":"Video Compression with CNN-based Post Processing","created":"2020-09-16","cited_by_count":8},{"id":"2408.05042","title":"Benchmarking Conventional and Learned Video Codecs with a Low-Delay Configuration","created":"2024-08-09","cited_by_count":6},{"id":"2412.11379","title":"Controllable Distortion-Perception Tradeoff Through Latent Diffusion for Neural Image Compression","created":"2024-12-16","cited_by_count":6},{"id":"2312.02605","title":"Accelerating Learnt Video Codecs with Gradient Decay and Layer-wise Distillation","created":"2023-12-05","cited_by_count":4},{"id":"2405.08530","title":"Parameter-Efficient Instance-Adaptive Neural Video Compression","created":"2024-05-14","cited_by_count":4}],"next_cursor":null}