{"list":"other","total":63,"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":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2407.21783","title":"The Llama 3 Herd of Models","created":"2024-07-31","cited_by_count":14715},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","created":"2022-04-05","cited_by_count":5326},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"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":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2403.08295","title":"Gemma: Open Models Based on Gemini Research and Technology","created":"2024-03-13","cited_by_count":916},{"id":"2306.15595","title":"Extending Context Window of Large Language Models via Positional Interpolation","created":"2023-06-27","cited_by_count":740},{"id":"2204.06745","title":"GPT-NeoX-20B: An Open-Source Autoregressive Language Model","created":"2022-04-14","cited_by_count":713},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2309.00071","title":"YaRN: Efficient Context Window Extension of Large Language Models","created":"2023-08-31","cited_by_count":601},{"id":"2501.00103","title":"LTX-Video: Realtime Video Latent Diffusion","created":"2024-12-30","cited_by_count":581},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2412.07772","title":"From Slow Bidirectional to Fast Autoregressive Video Diffusion Models","created":"2024-12-10","cited_by_count":433},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2211.04894","title":"Exploring Video Quality Assessment on User Generated Contents from Aesthetic and Technical Perspectives","created":"2022-11-09","cited_by_count":320},{"id":"2402.13753","title":"LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens","created":"2024-02-21","cited_by_count":313},{"id":"2405.08748","title":"Hunyuan-DiT: A Powerful Multi-Resolution Diffusion Transformer with Fine-Grained Chinese Understanding","created":"2024-05-14","cited_by_count":298},{"id":"2411.19108","title":"Timestep Embedding Tells: It's Time to Cache for Video Diffusion Model","created":"2024-11-28","cited_by_count":269},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"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":"2212.10554","title":"A Length-Extrapolatable Transformer","created":"2022-12-20","cited_by_count":127},{"id":"2410.19355","title":"FasterCache: Training-Free Video Diffusion Model Acceleration with High Quality","created":"2024-10-25","cited_by_count":122},{"id":"2411.02397","title":"Adaptive Caching for Faster Video Generation with Diffusion Transformers","created":"2024-11-04","cited_by_count":108},{"id":"1611.09571","title":"Predicting Human Eye Fixations via an LSTM-based Saliency Attentive Model","created":"2016-11-29","cited_by_count":91},{"id":"2003.05477","title":"Unified Image and Video Saliency Modeling","created":"2020-03-11","cited_by_count":75},{"id":"1705.02544","title":"Deep Visual Attention Prediction","created":"2017-05-07","cited_by_count":70},{"id":"2502.15894","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","created":"2025-02-21","cited_by_count":66},{"id":"1411.1045","title":"Deep Gaze I: Boosting Saliency Prediction with Feature Maps Trained on ImageNet","created":"2014-11-04","cited_by_count":60},{"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":"1609.01064","title":"A Deep Multi-Level Network for Saliency Prediction","created":"2016-09-05","cited_by_count":54},{"id":"1805.01047","title":"EML-NET:An Expandable Multi-Layer NETwork for Saliency Prediction","created":"2018-05-02","cited_by_count":51},{"id":"1510.02927","title":"DeepFix: A Fully Convolutional Neural Network for predicting Human Eye Fixations","created":"2015-10-10","cited_by_count":48},{"id":"2110.03593","title":"TranSalNet: Towards perceptually relevant visual saliency prediction","created":"2021-10-07","cited_by_count":44},{"id":"2506.09045","title":"MagCache: Fast Video Generation with Magnitude-Aware Cache","created":"2025-06-10","cited_by_count":41},{"id":"2412.07776","title":"Video Motion Transfer with Diffusion Transformers","created":"2024-12-10","cited_by_count":39},{"id":"2304.00287","title":"Vision Transformers with Mixed-Resolution Tokenization","created":"2023-04-01","cited_by_count":36},{"id":"2506.03065","title":"Sparse-vDiT: Unleashing the Power of Sparse Attention to Accelerate Video Diffusion Transformers","created":"2025-06-03","cited_by_count":34},{"id":"2411.18810","title":"All Seeds Are Not Equal: Enhancing Compositional Text-to-Image Generation with Reliable Random Seeds","created":"2024-11-27","cited_by_count":31},{"id":"2503.18446","title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","created":"2025-03-24","cited_by_count":25},{"id":"1610.01708","title":"A Deep Spatial Contextual Long-term Recurrent Convolutional Network for Saliency Detection","created":"2016-10-06","cited_by_count":23},{"id":"2503.19011","title":"RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis","created":"2025-03-24","cited_by_count":20},{"id":"2506.03737","title":"ComRoPE: Scalable and Robust Rotary Position Embedding Parameterized by Trainable Commuting Angle Matrices","created":"2025-06-04","cited_by_count":18},{"id":"2411.19824","title":"SAT-HMR: Real-Time Multi-Person 3D Mesh Estimation via Scale-Adaptive Tokens","created":"2024-11-29","cited_by_count":16},{"id":"2505.10046","title":"Exploring the Deep Fusion of Large Language Models and Diffusion Transformers for Text-to-Image Synthesis","created":"2025-05-15","cited_by_count":16},{"id":"2406.12042","title":"Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Models","created":"2024-06-17","cited_by_count":13},{"id":"2510.18091","title":"Accelerating Vision Transformers with Adaptive Patch Sizes","created":"2025-10-20","cited_by_count":13},{"id":"2412.10783","title":"Video Diffusion Transformers are In-Context Learners","created":"2024-12-14","cited_by_count":12},{"id":"2407.15171","title":"Assessing Sample Quality via the Latent Space of Generative Models","created":"2024-07-21","cited_by_count":8},{"id":"2502.08690","title":"Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation","created":"2025-02-12","cited_by_count":4},{"id":"2409.19501","title":"Learning Frame-Wise Emotion Intensity for Audio-Driven Talking-Head Generation","created":"2024-09-29","cited_by_count":3}],"next_cursor":null}