{"total":114,"rows":[{"id":"2502.01776","title":"Sparse VideoGen: Accelerating Video Diffusion Transformers with Spatial-Temporal Sparsity","created":"2025-02-03","cited_by_count":217,"area":"diffusion"},{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160,"area":null},{"id":"2504.12626","title":"Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models","created":"2025-04-17","cited_by_count":143,"area":"diffusion"},{"id":"2502.04507","title":"Fast Video Generation with Sliding Tile Attention","created":"2025-02-06","cited_by_count":128,"area":"diffusion"},{"id":"2502.18137","title":"SpargeAttention: Accurate and Training-free Sparse Attention Accelerating Any Model Inference","created":"2025-02-25","cited_by_count":120,"area":null},{"id":"2508.21058","title":"Mixture of Contexts for Long Video Generation","created":"2025-08-28","cited_by_count":95,"area":null},{"id":"2502.21079","title":"Training-free and Adaptive Sparse Attention for Efficient Long Video Generation","created":"2025-02-28","cited_by_count":69,"area":"diffusion"},{"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":"2502.15894","title":"RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers","created":"2025-02-21","cited_by_count":66,"area":"diffusion"},{"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,"area":null},{"id":"2603.05451","title":"FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling","created":"2026-03-05","cited_by_count":66,"area":null},{"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":"2512.07826","title":"OpenVE-3M: A Large-Scale High-Quality Dataset for Instruction-Guided Video Editing","created":"2025-12-08","cited_by_count":53,"area":null},{"id":"2502.02770","title":"Twilight: Adaptive Attention Sparsity with Hierarchical Top-$p$ Pruning","created":"2025-02-04","cited_by_count":49,"area":null},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44,"area":"wm"},{"id":"2505.09343","title":"Insights into DeepSeek-V3: Scaling Challenges and Reflections on Hardware for AI Architectures","created":"2025-05-14","cited_by_count":39,"area":"moe"},{"id":"2512.16093","title":"TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times","created":"2025-12-18","cited_by_count":33,"area":"diffusion"},{"id":"2511.07399","title":"StreamDiffusionV2: A Streaming System for Dynamic and Interactive Video Generation","created":"2025-11-10","cited_by_count":30,"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":"2412.18911","title":"Rethinking Token-wise Feature Caching: Accelerating Diffusion Transformers with Dual Feature Caching","created":"2024-12-25","cited_by_count":28,"area":"diffusion"},{"id":"2503.16302","title":"Unleashing Vecset Diffusion Model for Fast Shape Generation","created":"2025-03-20","cited_by_count":26,"area":"diffusion"},{"id":"2502.09334","title":"ThunderServe: High-performance and Cost-efficient LLM Serving in Cloud Environments","created":"2025-02-13","cited_by_count":23,"area":"inference"},{"id":"2503.01103","title":"Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator","created":"2025-03-03","cited_by_count":23,"area":null},{"id":"2502.00722","title":"Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs","created":"2025-02-02","cited_by_count":22,"area":"inference"},{"id":"2505.14708","title":"DraftAttention: Fast Video Diffusion via Low-Resolution Attention Guidance","created":"2025-05-17","cited_by_count":22,"area":"diffusion"},{"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":"2503.22796","title":"DiTFastAttnV2: Head-wise Attention Compression for Multi-Modality Diffusion Transformers","created":"2025-03-28","cited_by_count":20,"area":"diffusion"},{"id":"2506.04648","title":"FPSAttention: Training-Aware FP8 and Sparsity Co-Design for Fast Video Diffusion","created":"2025-06-05","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":"2509.25182","title":"DC-VideoGen: Efficient Video Generation with Deep Compression Video Autoencoder","created":"2025-09-29","cited_by_count":16,"area":null},{"id":"2607.19191","title":"ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU","created":"2026-07-21","cited_by_count":16,"area":"wm"},{"id":"2510.15264","title":"DriveGen3D: Boosting Feed-Forward Driving Scene Generation with Efficient Video Diffusion","created":"2025-10-17","cited_by_count":15,"area":"diffusion"},{"id":"2605.09681","title":"Forcing-KV: Hybrid KV Cache Compression for Efficient Autoregressive Video Diffusion Models","created":"2026-05-10","cited_by_count":15,"area":"diffusion"},{"id":"2503.08040","title":"Accurate INT8 Training Through Dynamic Block-Level Fallback","created":"2025-03-11","cited_by_count":14,"area":null},{"id":"2504.14470","title":"Turbo2K: Towards Ultra-Efficient and High-Quality 2K Video Synthesis","created":"2025-04-20","cited_by_count":13,"area":null},{"id":"2503.16400","title":"ScalingNoise: Scaling Inference-Time Search for Generating Infinite Videos","created":"2025-03-20","cited_by_count":12,"area":"diffusion"},{"id":"2511.20123","title":"UltraViCo: Breaking Extrapolation Limits in Video Diffusion Transformers","created":"2025-11-25","cited_by_count":12,"area":"diffusion"},{"id":"2602.04789","title":"Light Forcing: Accelerating Autoregressive Video Diffusion via Sparse Attention","created":"2026-02-04","cited_by_count":12,"area":"diffusion"},{"id":"2602.24289","title":"Mode Seeking meets Mean Seeking for Fast Long Video Generation","created":"2026-02-27","cited_by_count":12,"area":"diffusion"},{"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":"2503.01901","title":"Identifying Sensitive Weights via Post-quantization Integral","created":"2025-02-28","cited_by_count":11,"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":"2503.01713","title":"SAGE: A Framework of Precise Retrieval for RAG","created":"2025-03-03","cited_by_count":8,"area":"rag"},{"id":"2509.25180","title":"DC-Gen: Post-Training Diffusion Acceleration with Deeply Compressed Latent Space","created":"2025-09-29","cited_by_count":8,"area":"diffusion"},{"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":"2602.02159","title":"Focus-dLLM: Accelerating Long-Context Diffusion LLM Inference via Confidence-Guided Context Focusing","created":"2026-02-02","cited_by_count":7,"area":null},{"id":"2604.15911","title":"Efficient Video Diffusion Models: Advancements and Challenges","created":"2026-04-17","cited_by_count":7,"area":"diffusion"},{"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":"2510.26843","title":"CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs","created":"2025-10-30","cited_by_count":4,"area":"inference"},{"id":"2601.07396","title":"Forecast the Principal, Stabilize the Residual: Subspace-Aware Feature Caching for Efficient Diffusion Transformers","created":"2026-01-12","cited_by_count":4,"area":"diffusion"},{"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":"2510.16325","title":"UltraImageGen: Efficient Ultra-High-Resolution Image Generation with Hierarchical Local Attention","created":"2025-10-18","cited_by_count":3,"area":"diffusion"},{"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":"2511.23113","title":"db-SP: Accelerating Sparse Attention for Visual Generative Models with Dual-Balanced Sequence Parallelism","created":"2025-11-28","cited_by_count":3,"area":"diffusion"},{"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":"2603.07815","title":"HybridStitch: Pixel and Timestep Level Model Stitching for Diffusion Acceleration","created":"2026-03-08","cited_by_count":2,"area":"diffusion"},{"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":"2604.18117","title":"LoRaQ: Optimized Low Rank Approximation for 4-bit Quantization","created":"2026-04-20","cited_by_count":2,"area":"diffusion"},{"id":"2604.22575","title":"SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference","created":"2026-04-24","cited_by_count":2,"area":null},{"id":"2605.26266","title":"Quantized Keys Steal Attention: Bias Correction for KV-Cache Compression in Video Diffusion","created":"2026-05-25","cited_by_count":2,"area":"diffusion"},{"id":"2607.00712","title":"Towards Memory-Efficient Autoregressive Video Generation via Instance-Specific Parametric Absorption","created":"2026-07-01","cited_by_count":2,"area":"inference"},{"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":"2609.15810","title":"VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention","created":"2026-09-14","cited_by_count":2,"area":"diffusion"},{"id":"2502.02922","title":"Elucidating the Preconditioning in Consistency Distillation","created":"2025-02-05","cited_by_count":1,"area":"diffusion"},{"id":"2511.10909","title":"Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy","created":"2025-11-14","cited_by_count":1,"area":null},{"id":"2602.06072","title":"PackInfer: Compute- and I/O-Efficient Attention for Batched LLM Inference","created":"2026-02-03","cited_by_count":1,"area":"inference"},{"id":"2603.05503","title":"Accelerating Text-to-Video Generation with Calibrated Sparse Attention","created":"2026-03-05","cited_by_count":1,"area":"diffusion"},{"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":"2603.12038","title":"Slow-Fast Inference: Training-Free Inference Acceleration via Within-Sentence Support Stability","created":"2026-03-12","cited_by_count":1,"area":"inference"},{"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":"2604.21231","title":"SparKV: Overhead-Aware KV Cache Loading for Efficient On-Device LLM Inference","created":"2026-04-23","cited_by_count":1,"area":"inference"},{"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":"2607.04302","title":"HiFA4: Training-Free 4-bit FlashAttention on Ascend HIF4 NPUs for LLM Inference","created":"2026-07-05","cited_by_count":1,"area":null},{"id":"2607.25291","title":"CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention","created":"2026-07-28","cited_by_count":1,"area":null},{"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":"2609.33384","title":"PulseQuant: Propagation-Guided Subspace Correction for 4-Bit Video Diffusion Transformers","created":"2026-09-27","cited_by_count":1,"area":"diffusion"},{"id":"2508.09602","title":"A Lightweight Learned Cardinality Estimation Model","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2510.22909","title":"Rethinking Inference Placement for Deep Learning across Edge and Cloud Platforms: A Multi-Objective Optimization Perspective and Future Directions","created":"2025-10-27","cited_by_count":0,"area":"lr"},{"id":"2601.21444","title":"APB-V: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention","created":"2026-01-29","cited_by_count":0,"area":"mllm"},{"id":"2603.09657","title":"When to Lock Attention: Training-Free KV Control in Video Diffusion","created":"2026-03-10","cited_by_count":0,"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":"2604.09742","title":"Efficient Matrix Implementation for Rotary Position Embedding","created":"2026-04-10","cited_by_count":0,"area":null},{"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":"2605.17294","title":"HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing","created":"2026-05-17","cited_by_count":0,"area":null}],"next_cursor":"100"}