{"total":66,"rows":[{"id":"2506.19852","title":"Radial Attention: $O(n\\log n)$ Sparse Attention with Energy Decay for Long Video Generation","created":"2025-06-24","cited_by_count":69,"area":"diffusion"},{"id":"2509.24006","title":"SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse-Linear Attention","created":"2025-09-28","cited_by_count":58,"area":"diffusion"},{"id":"2512.16093","title":"TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times","created":"2025-12-18","cited_by_count":33,"area":"diffusion"},{"id":"2605.18739","title":"LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation","created":"2026-05-18","cited_by_count":30,"area":"diffusion"},{"id":"2505.21600","title":"R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing","created":"2025-05-27","cited_by_count":29,"area":"lr"},{"id":"2505.21136","title":"SageAttention2++: A More Efficient Implementation of SageAttention2","created":"2025-05-27","cited_by_count":22,"area":null},{"id":"2602.12675","title":"SLA2: Sparse-Linear Attention with Learnable Routing and QAT","created":"2026-02-13","cited_by_count":22,"area":"diffusion"},{"id":"2509.01085","title":"Bidirectional Sparse Attention for Faster Video Diffusion Training","created":"2025-09-01","cited_by_count":19,"area":"diffusion"},{"id":"2602.13515","title":"SpargeAttention2: Trainable Sparse Attention via Hybrid Top-k+Top-p Masking and Distillation Fine-Tuning","created":"2026-02-13","cited_by_count":18,"area":"diffusion"},{"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,"area":null},{"id":"2510.11696","title":"QeRL: Beyond Efficiency -- Quantization-enhanced Reinforcement Learning for LLMs","created":"2025-10-13","cited_by_count":16,"area":null},{"id":"2605.04956","title":"KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels","created":"2026-05-06","cited_by_count":12,"area":null},{"id":"2603.08982","title":"SVG-EAR: Parameter-Free Linear Compensation for Sparse Video Generation via Error-aware Routing","created":"2026-03-09","cited_by_count":10,"area":"diffusion"},{"id":"2601.19026","title":"Is Finer Better? The Limits of Microscaling Formats in Large Language Models","created":"2026-01-26","cited_by_count":8,"area":null},{"id":"2601.19213","title":"M2XFP: A Metadata-Augmented Microscaling Data Format for Efficient Low-bit Quantization","created":"2026-01-27","cited_by_count":8,"area":null},{"id":"2603.00040","title":"Attn-QAT: 4-Bit Attention With Quantization-Aware Training","created":"2026-02-09","cited_by_count":8,"area":null},{"id":"2603.02170","title":"SageBwd: A Trainable Low-bit Attention","created":"2026-03-02","cited_by_count":8,"area":null},{"id":"2606.23743","title":"Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation","created":"2026-06-21","cited_by_count":8,"area":"diffusion"},{"id":"2607.04422","title":"Full-Stack FP4: Stable LLM Pretraining with Quantized Projections, Optimizers, and Attention","created":"2026-07-05","cited_by_count":8,"area":null},{"id":"2508.18224","title":"FSA: An Alternative Efficient Implementation of Native Sparse Attention Kernel","created":"2025-08-25","cited_by_count":7,"area":null},{"id":"2509.23681","title":"QuantSparse: Comprehensively Compressing Video Diffusion Transformer with Model Quantization and Attention Sparsification","created":"2025-09-28","cited_by_count":7,"area":"diffusion"},{"id":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"id":"2603.16590","title":"BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization","created":"2026-03-17","cited_by_count":6,"area":null},{"id":"2603.28489","title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","created":"2026-03-30","cited_by_count":5,"area":"wm"},{"id":"2608.26794","title":"Ring Forcing: Towards Precise Long-Term Memory for Autoregressive Video Diffusion","created":"2026-08-27","cited_by_count":5,"area":"diffusion"},{"id":"2609.11638","title":"Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation","created":"2026-09-10","cited_by_count":5,"area":null},{"id":"2509.16518","title":"FG-Attn: Leveraging Fine-Grained Sparse Attention in Video Diffusion Models","created":"2025-09-20","cited_by_count":4,"area":"diffusion"},{"id":"2510.06175","title":"VecInfer: Efficient LLM Inference with Low-Bit KV Cache via Outlier-Suppressed Vector Quantization","created":"2025-10-07","cited_by_count":4,"area":"inference"},{"id":"2510.13602","title":"NOSA: Native and Offloadable Sparse Attention","created":"2025-10-15","cited_by_count":4,"area":"inference"},{"id":"2601.21824","title":"DASH: Deterministic Attention Scheduling for High-throughput Reproducible LLM Training","created":"2026-01-29","cited_by_count":4,"area":null},{"id":"2605.23081","title":"ThriftAttention: Selective Mixed Precision for Long-Context FP4 Attention","created":"2026-05-21","cited_by_count":4,"area":null},{"id":"2607.03118","title":"Vidu S1: A Real-Time Interactive Video Generation Model","created":"2026-07-03","cited_by_count":4,"area":null},{"id":"2511.21513","title":"IntAttention: A Fully Integer Attention Pipeline for Efficient Edge Inference","created":"2025-11-26","cited_by_count":3,"area":null},{"id":"2512.13492","title":"Transform Trained Transformer for Accelerating Native 4K Video Generation","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2512.13495","title":"Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation","created":"2025-12-15","cited_by_count":3,"area":null},{"id":"2601.22275","title":"VMonarch: Efficient Video Diffusion Transformers with Structured Attention","created":"2026-01-29","cited_by_count":3,"area":"diffusion"},{"id":"2605.12464","title":"Search Your Block Floating Point Scales!","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2602.01410","title":"SNIP: An Adaptive Mixed Precision Framework for Subbyte Large Language Model Training","created":"2026-02-01","cited_by_count":2,"area":null},{"id":"2603.07815","title":"HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration","created":"2026-03-08","cited_by_count":2,"area":"diffusion"},{"id":"2603.08747","title":"Diagnosing FP4 inference: a layer-wise and block-wise sensitivity analysis of NVFP4 and MXFP4","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.12056","title":"LoSA: Locality Aware Sparse Attention for Block-Wise Diffusion Language Models","created":"2026-04-13","cited_by_count":2,"area":"diffusion"},{"id":"2604.17397","title":"Speculative Decoding for Autoregressive Video Generation","created":"2026-04-19","cited_by_count":2,"area":"diffusion"},{"id":"2607.24377","title":"MXAttention: Data-Free Optimal Scaling and Pre-Normalization Quantization for MXFP4 Attention","created":"2026-07-27","cited_by_count":2,"area":"diffusion"},{"id":"2609.04105","title":"Hardware-Aware FP4 FlashAttention-4","created":"2026-09-03","cited_by_count":2,"area":null},{"id":"2609.15810","title":"VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention","created":"2026-09-14","cited_by_count":2,"area":"diffusion"},{"id":"2512.09202","title":"Tensor-Compressed and Fully-Quantized Training of Neural PDE Solvers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2603.09582","title":"BinaryAttention: One-Bit QK-Attention for Vision and Diffusion Transformers","created":"2026-03-10","cited_by_count":1,"area":"diffusion"},{"id":"2604.03950","title":"Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference","created":"2026-04-05","cited_by_count":1,"area":null},{"id":"2607.03012","title":"HyperVAttention: Efficient Sparse Attention with Spatio-Temporal Clustering for Video Diffusion","created":"2026-07-03","cited_by_count":1,"area":"diffusion"},{"id":"2609.20744","title":"Video DeltaNet: A Video-Native Hybrid Attention for Livestream Video Generation","created":"2026-09-17","cited_by_count":1,"area":"diffusion"},{"id":"2603.18742","title":"6Bit-Diffusion: Inference-Time Mixed-Precision Quantization for Video Diffusion Models","created":"2026-03-19","cited_by_count":0,"area":"diffusion"},{"id":"2604.08329","title":"DiV-INR: Extreme Low-Bitrate Diffusion Video Compression with INR Conditioning","created":"2026-04-09","cited_by_count":0,"area":"diffusion"},{"id":"2604.09742","title":"Efficient Matrix Implementation for Rotary Position Embedding","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.17353","title":"Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling","created":"2026-04-19","cited_by_count":0,"area":"agents"},{"id":"2605.16649","title":"AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling","created":"2026-05-15","cited_by_count":0,"area":"diffusion"},{"id":"2606.05981","title":"Inverting the Streaming-Diffusion Bottleneck: Video-Rate MLLM-Conditioned Edit Diffusion on a Consumer GPU","created":"2026-06-04","cited_by_count":0,"area":"distill"},{"id":"2607.02584","title":"RotateAttention: RoPE-Aware Rotation and Range Rectification for INT4 Quantized Attention in Video Generation","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2608.03867","title":"Heterogeneity-Aware Microscaling for Efficient Low-Bit LLM Inference","created":"2026-08-04","cited_by_count":0,"area":null},{"id":"2608.26965","title":"ClusterAttention: A training-free speedup of bidirectional attention","created":"2026-08-27","cited_by_count":0,"area":null},{"id":"2609.09721","title":"EFQ-Softmax: Exp-Free Quantization for Softmax","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.31306","title":"Benchmarking Attention for Tabular Foundation Models","created":"2026-09-25","cited_by_count":0,"area":null},{"id":"2609.32628","title":"DraftAttention2: Fast Video Diffusion with Low-Resolution-Guided Mixed-Precision Attention","created":"2026-09-26","cited_by_count":0,"area":"diffusion"},{"id":"2609.32882","title":"Improving Video Sparse Attention with Fine-grained Router and Sparse Rebasing","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33586","title":"Approximating Softmax in Pretrained LLMs: Model Sensitivity and Kernel Acceleration","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.35110","title":"Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge","created":"2026-09-28","cited_by_count":0,"area":"diffusion"},{"id":"2609.39813","title":"Backward-State Policy Is Part of the Learning Algorithm","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}