{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2309.06180","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","created":"2023-09-12","cited_by_count":5944},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2004.05150","title":"Longformer: The Long-Document Transformer","created":"2020-04-10","cited_by_count":3413},{"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":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2009.14794","title":"Rethinking Attention with Performers","created":"2020-09-30","cited_by_count":1601},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2210.09461","title":"Token Merging: Your ViT But Faster","created":"2022-10-17","cited_by_count":1021},{"id":"1906.02691","title":"An Introduction to Variational Autoencoders","created":"2019-06-06","cited_by_count":1000},{"id":"1904.06991","title":"Improved Precision and Recall Metric for Assessing Generative Models","created":"2019-04-15","cited_by_count":944},{"id":"2306.09341","title":"Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis","created":"2023-06-15","cited_by_count":890},{"id":"2402.15391","title":"Genie: Generative Interactive Environments","created":"2024-02-23","cited_by_count":747},{"id":"1911.02150","title":"Fast Transformer Decoding: One Write-Head is All You Need","created":"2019-11-06","cited_by_count":717},{"id":"2405.12399","title":"Diffusion for World Modeling: Visual Details Matter in Atari","created":"2024-05-20","cited_by_count":300},{"id":"2303.17604","title":"Token Merging for Fast Stable Diffusion","created":"2023-03-30","cited_by_count":224},{"id":"2502.06764","title":"History-Guided Video Diffusion","created":"2025-02-10","cited_by_count":171},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2501.08325","title":"GameFactory: Creating New Games with Generative Interactive Videos","created":"2025-01-14","cited_by_count":130},{"id":"2312.01026","title":"Token Fusion: Bridging the Gap between Token Pruning and Token Merging","created":"2023-12-02","cited_by_count":125},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120},{"id":"2412.03568","title":"The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control","created":"2024-12-04","cited_by_count":80},{"id":"2103.16365","title":"FoV-NeRF: Foveated Neural Radiance Fields for Virtual Reality","created":"2021-03-30","cited_by_count":79},{"id":"2503.18352","title":"Diffusion-4K: Ultra-High-Resolution Image Synthesis with Latent Diffusion Models","created":"2025-03-24","cited_by_count":65},{"id":"2105.12441","title":"DeepGaze IIE: Calibrated prediction in and out-of-domain for state-of-the-art saliency modeling","created":"2021-05-26","cited_by_count":56},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36},{"id":"2410.17932","title":"VR-Splatting: Foveated Radiance Field Rendering via 3D Gaussian Splatting and Neural Points","created":"2024-10-23","cited_by_count":29},{"id":"2105.14173","title":"FoveaTer: Foveated Transformer for Image Classification","created":"2021-05-29","cited_by_count":28},{"id":"2503.18940","title":"Training-free Diffusion Acceleration with Bottleneck Sampling","created":"2025-03-24","cited_by_count":25},{"id":"2506.10968","title":"Eye, Robot: Learning to Look to Act with a BC-RL Perception-Action Loop","created":"2025-06-12","cited_by_count":25},{"id":"2411.16720","title":"Importance-Based Token Merging for Efficient Image and Video Generation","created":"2024-11-23","cited_by_count":22},{"id":"2307.02321","title":"MSViT: Dynamic Mixed-Scale Tokenization for Vision Transformers","created":"2023-07-05","cited_by_count":20},{"id":"2509.10918","title":"ToMA: Token Merge with Attention for Diffusion Models","created":"2025-09-13","cited_by_count":18},{"id":"2505.11707","title":"Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration","created":"2025-05-16","cited_by_count":17},{"id":"2409.11923","title":"Agglomerative Token Clustering","created":"2024-09-18","cited_by_count":13},{"id":"2507.15833","title":"Look, Focus, Act: Efficient and Robust Robot Learning via Human Gaze and Foveated Vision Transformers","created":"2025-07-21","cited_by_count":11},{"id":"2511.14751","title":"Co-Me: Confidence-Guided Token Merging for Visual Geometric Transformers","created":"2025-11-18","cited_by_count":10},{"id":"2312.01450","title":"Foveation in the Era of Deep Learning","created":"2023-12-03","cited_by_count":8},{"id":"2204.04455","title":"Noise-based Enhancement for Foveated Rendering","created":"2022-04-09","cited_by_count":5},{"id":"2302.01368","title":"Towards Attention-aware Foveated Rendering","created":"2023-02-02","cited_by_count":5},{"id":"2506.11131","title":"Segment This Thing: Foveated Tokenization for Efficient Point-Prompted Segmentation","created":"2025-06-10","cited_by_count":5},{"id":"2507.12771","title":"Local Representative Token Guided Merging for Text-to-Image Generation","created":"2025-07-17","cited_by_count":2}],"next_cursor":null}