{"total":42,"rows":[{"id":"2511.18870","title":"HunyuanVideo 1.5 Technical Report","created":"2025-11-24","cited_by_count":160,"area":null},{"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":"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":"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":"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":"2505.21136","title":"SageAttention2++: A More Efficient Implementation of SageAttention2","created":"2025-05-27","cited_by_count":22,"area":null},{"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":"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":"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":"2603.00040","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":"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":"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":"2609.11638","title":"Vidu S2: Real-Time Interactive, Editable, and Spatial Video Generation","created":"2026-09-10","cited_by_count":5,"area":null},{"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":"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":"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":"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":"2607.04302","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":"2508.09602","title":"A Lightweight Learned Cardinality Estimation Model","created":"2025-08-13","cited_by_count":0,"area":null},{"id":"2604.09742","title":"Efficient Matrix Implementation for Rotary Position Embedding","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.17294","title":"HierEdit: Region-Aware Hierarchical Diffusion for Efficient High-Resolution Editing","created":"2026-05-17","cited_by_count":0,"area":null},{"id":"2606.06521","title":"P-Cast Precision in FP8 Attention: Sink-Induced Collapse and the Optimality of S=2^8","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2606.26587","title":"SharQ: Bridging Activation Sparsity and FP4 Quantization for LLM Inference","created":"2026-06-25","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":"2609.31306","title":"Benchmarking Attention for Tabular Foundation Models","created":"2026-09-25","cited_by_count":0,"area":null},{"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":"2609.34272","title":"Broken Symmetry in BF16 Attention: Why FlashAttention Gradients Blow Up Late in Training","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}