{"list":"other","total":53,"rows":[{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2205.14135","title":"FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness","created":"2022-05-27","cited_by_count":3673},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2307.08691","title":"FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning","created":"2023-07-17","cited_by_count":2598},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2309.17453","title":"Efficient Streaming Language Models with Attention Sinks","created":"2023-09-29","cited_by_count":2186},{"id":"2210.17323","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","created":"2022-10-31","cited_by_count":1919},{"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":"2211.10438","title":"SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models","created":"2022-11-18","cited_by_count":1386},{"id":"2306.00978","title":"AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration","created":"2023-06-01","cited_by_count":1298},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2404.00456","title":"QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs","created":"2024-03-30","cited_by_count":634},{"id":"2401.09670","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","created":"2024-01-18","cited_by_count":617},{"id":"2104.13840","title":"Twins: Revisiting the Design of Spatial Attention in Vision Transformers","created":"2021-04-28","cited_by_count":565},{"id":"2311.18677","title":"Splitwise: Efficient generative LLM inference using phase splitting","created":"2023-11-30","cited_by_count":558},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2405.16406","title":"SpinQuant: LLM quantization with learned rotations","created":"2024-05-26","cited_by_count":471},{"id":"2407.02490","title":"MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention","created":"2024-07-02","cited_by_count":383},{"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":"2309.12307","title":"LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models","created":"2023-09-21","cited_by_count":244},{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217},{"id":"2402.04617","title":"InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory","created":"2024-02-07","cited_by_count":197},{"id":"2407.00079","title":"Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving","created":"2024-06-24","cited_by_count":196},{"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":"2406.01721","title":"DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs","created":"2024-06-03","cited_by_count":167},{"id":"2503.09642","title":"Open-Sora 2.0: Training a Commercial-Level Video Generation Model in $200k","created":"2025-03-12","cited_by_count":163},{"id":"2410.02367","title":"SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration","created":"2024-10-03","cited_by_count":160},{"id":"2410.09426","title":"FlatQuant: Flatness Matters for LLM Quantization","created":"2024-10-12","cited_by_count":131},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120},{"id":"2406.02540","title":"ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation","created":"2024-06-04","cited_by_count":115},{"id":"2406.08552","title":"DiTFastAttn: Attention Compression for Diffusion Transformer Models","created":"2024-06-12","cited_by_count":115},{"id":"2505.18875","title":"Sparse VideoGen2: Accelerate Video Generation with Sparse Attention via Semantic-Aware Permutation","created":"2025-05-24","cited_by_count":106},{"id":"2402.18158","title":"Evaluating Quantized Large Language Models","created":"2024-02-28","cited_by_count":77},{"id":"2505.11594","title":"SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training","created":"2025-05-16","cited_by_count":66},{"id":"2509.24006","title":"SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention","created":"2025-09-28","cited_by_count":58},{"id":"2412.19509","title":"MBQ: Modality-Balanced Quantization for Large Vision-Language Models","created":"2024-12-27","cited_by_count":45},{"id":"2405.17873","title":"MixDQ: Memory-Efficient Few-Step Text-to-Image Diffusion Models with Metric-Decoupled Mixed Precision Quantization","created":"2024-05-28","cited_by_count":43},{"id":"2504.17577","title":"TileLang: A Composable Tiled Programming Model for AI Systems","created":"2025-04-24","cited_by_count":43},{"id":"2406.04333","title":"BitsFusion: 1.99 bits Weight Quantization of Diffusion Model","created":"2024-06-06","cited_by_count":37},{"id":"2301.02240","title":"Skip-Attention: Improving Vision Transformers by Paying Less Attention","created":"2023-01-05","cited_by_count":24},{"id":"2510.27684","title":"Phased DMD: Few-step Distribution Matching Distillation via Score Matching within Subintervals","created":"2025-10-31","cited_by_count":24},{"id":"2401.04585","title":"EDA-DM: Enhanced Distribution Alignment for Post-Training Quantization of Diffusion Models","created":"2024-01-09","cited_by_count":23},{"id":"2505.11497","title":"QVGen: Pushing the Limit of Quantized Video Generative Models","created":"2025-05-16","cited_by_count":22},{"id":"2505.18610","title":"PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs","created":"2025-05-24","cited_by_count":22},{"id":"2311.06322","title":"Post-training Quantization for Text-to-Image Diffusion Models with Progressive Calibration and Activation Relaxing","created":"2023-11-10","cited_by_count":21},{"id":"2506.16054","title":"PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models","created":"2025-06-19","cited_by_count":17},{"id":"2506.04985","title":"FPTQuant: Function-Preserving Transforms for LLM Quantization","created":"2025-06-05","cited_by_count":16},{"id":"2503.16257","title":"Plug-and-Play 1.x-Bit KV Cache Quantization for Video Large Language Models","created":"2025-03-20","cited_by_count":13}],"next_cursor":null}