{"list":"other","total":77,"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2505.09388","title":"Qwen3 Technical Report","created":"2025-05-14","cited_by_count":8820},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2001.08361","title":"Scaling Laws for Neural Language Models","created":"2020-01-23","cited_by_count":6586},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"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":"2409.12191","title":"Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution","created":"2024-09-18","cited_by_count":4234},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"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":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2101.03961","title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","created":"2021-01-11","cited_by_count":3073},{"id":"2203.15556","title":"Training Compute-Optimal Large Language Models","created":"2022-03-29","cited_by_count":3019},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2006.16236","title":"Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention","created":"2020-06-29","cited_by_count":2022},{"id":"2002.05202","title":"GLU Variants Improve Transformer","created":"2020-02-12","cited_by_count":1804},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2006.16668","title":"GShard: Scaling Giant Models with Conditional Computation and Automatic Sharding","created":"2020-06-30","cited_by_count":1631},{"id":"1904.10509","title":"Generating Long Sequences with Sparse Transformers","created":"2019-04-23","cited_by_count":1546},{"id":"2305.13245","title":"GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints","created":"2023-05-22","cited_by_count":1346},{"id":"2405.04434","title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","created":"2024-05-07","cited_by_count":1135},{"id":"2108.12409","title":"Train Short, Test Long: Attention with Linear Biases Enables Input Length Extrapolation","created":"2021-08-27","cited_by_count":1103},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"id":"2310.11513","title":"GenEval: An Object-Focused Framework for Evaluating Text-to-Image Alignment","created":"2023-10-17","cited_by_count":972},{"id":"2401.10166","title":"VMamba: Visual State Space Model","created":"2024-01-18","cited_by_count":969},{"id":"2209.11895","title":"In-context Learning and Induction Heads","created":"2022-09-24","cited_by_count":964},{"id":"2401.06066","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","created":"2024-01-11","cited_by_count":867},{"id":"2512.02556","title":"DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models","created":"2025-12-02","cited_by_count":815},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2304.11277","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","created":"2023-04-21","cited_by_count":660},{"id":"2307.08621","title":"Retentive Network: A Successor to Transformer for Large Language Models","created":"2023-07-17","cited_by_count":613},{"id":"1712.00409","title":"Deep Learning Scaling is Predictable, Empirically","created":"2017-12-01","cited_by_count":582},{"id":"2010.14701","title":"Scaling Laws for Autoregressive Generative Modeling","created":"2020-10-28","cited_by_count":522},{"id":"2403.05135","title":"ELLA: Equip Diffusion Models with LLM for Enhanced Semantic Alignment","created":"2024-03-08","cited_by_count":475},{"id":"2502.11089","title":"Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention","created":"2025-02-16","cited_by_count":407},{"id":"2102.10882","title":"Conditional Positional Encodings for Vision Transformers","created":"2021-02-22","cited_by_count":406},{"id":"2406.06484","title":"Parallelizing Linear Transformers with the Delta Rule over Sequence Length","created":"2024-06-10","cited_by_count":396},{"id":"2305.19466","title":"The Impact of Positional Encoding on Length Generalization in Transformers","created":"2023-05-31","cited_by_count":327},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2203.03466","title":"Tensor Programs V: Tuning Large Neural Networks via Zero-Shot Hyperparameter Transfer","created":"2022-03-07","cited_by_count":288},{"id":"2511.22699","title":"Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer","created":"2025-11-27","cited_by_count":277},{"id":"2408.15664","title":"Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts","created":"2024-08-28","cited_by_count":205},{"id":"2510.26692","title":"Kimi Linear: An Expressive, Efficient Attention Architecture","created":"2025-10-30","cited_by_count":196},{"id":"2604.15804","title":"Qwen3.5-Omni Technical Report","created":"2026-04-17","cited_by_count":174},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2304.09151","title":"UniMax: Fairer and more Effective Language Sampling for Large-Scale Multilingual Pretraining","created":"2023-04-18","cited_by_count":151},{"id":"2410.06205","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","created":"2024-10-08","cited_by_count":115},{"id":"2512.04040","title":"RELIC: Interactive Video World Model with Long-Horizon Memory","created":"2025-12-03","cited_by_count":96},{"id":"2512.24880","title":"mHC: Manifold-Constrained Hyper-Connections","created":"2025-12-31","cited_by_count":88},{"id":"2403.13802","title":"ZigMa: A DiT-style Zigzag Mamba Diffusion Model","created":"2024-03-20","cited_by_count":84},{"id":"2409.19606","title":"Hyper-Connections","created":"2024-09-29","cited_by_count":84},{"id":"2511.20645","title":"PixelDiT: Pixel Diffusion Transformers for Image Generation","created":"2025-11-25","cited_by_count":83},{"id":"2505.01618","title":"Don't be lazy: CompleteP enables compute-efficient deep transformers","created":"2025-05-02","cited_by_count":78},{"id":"2407.11633","title":"Scaling Diffusion Transformers to 16 Billion Parameters","created":"2024-07-16","cited_by_count":66},{"id":"2509.20360","title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","created":"2025-09-24","cited_by_count":54},{"id":"2410.08184","title":"Scaling Laws For Diffusion Transformers","created":"2024-10-10","cited_by_count":44},{"id":"2505.21829","title":"In Search of Adam's Secret Sauce","created":"2025-05-27","cited_by_count":40},{"id":"2509.25162","title":"AlignTok: Aligning Visual Foundation Encoders to Tokenizers for Diffusion Models","created":"2025-09-29","cited_by_count":36},{"id":"2512.17351","title":"Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers","created":"2025-12-19","cited_by_count":33},{"id":"2512.22382","title":"Completed Hyperparameter Transfer across Modules, Width, Depth, Batch and Duration","created":"2025-12-26","cited_by_count":27},{"id":"2604.03444","title":"Olmo Hybrid: From Theory to Practice and Back","created":"2026-04-03","cited_by_count":22},{"id":"2505.15270","title":"Scaling Diffusion Transformers Efficiently via $\\mu$P","created":"2025-05-21","cited_by_count":6},{"id":"2606.01774","title":"FLARE: Diffusion for Hybrid Language Model","created":"2026-06-01","cited_by_count":6},{"id":"2602.01642","title":"The Effect of Mini-Batch Noise on the Implicit Bias of Adam","created":"2026-02-02","cited_by_count":4},{"id":"2508.06001","title":"KnapFormer: An Online Load Balancer for Efficient Diffusion Transformers Training","created":"2025-08-08","cited_by_count":3},{"id":"2502.00972","title":"Pushing the Boundaries of State Space Models for Image and Video Generation","created":"2025-02-03","cited_by_count":2}],"next_cursor":null}