{"total":19,"rows":[{"id":"2408.12588","title":"Real-Time Video Generation with Pyramid Attention Broadcast","created":"2024-08-22","cited_by_count":149,"area":null},{"id":"2412.18653","title":"1.58-bit FLUX","created":"2024-12-24","cited_by_count":31,"area":null},{"id":"2411.13918","title":"Quantization without Tears","created":"2024-11-21","cited_by_count":25,"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":"2505.05530","title":"Low-bit Model Quantization for Deep Neural Networks: A Survey","created":"2025-05-08","cited_by_count":11,"area":null},{"id":"2505.20932","title":"QwT-v2: Practical, Effective and Efficient Post-Training Quantization","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2512.07834","title":"Voxify3D: Pixel Art Meets Volumetric Rendering","created":"2025-12-08","cited_by_count":3,"area":null},{"id":"2510.14823","title":"FraQAT: Quantization Aware Training with Fractional bits","created":"2025-10-16","cited_by_count":2,"area":null},{"id":"2605.26137","title":"AssetGen: Deployable 3D Asset Generation at Interactive Speed","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2505.16335","title":"FPQVAR: Floating Point Quantization for Visual Autoregressive Model with FPGA Hardware Co-design","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2605.16423","title":"Nonlinear Bipolar Compensation: Handling Outliers in Post-Training Quantization","created":"2026-05-14","cited_by_count":1,"area":null},{"id":"2607.15846","title":"DSTAR: Accelerating Diffusion Transformers via Spatial and Temporal Redundancy Reduction","created":"2026-07-17","cited_by_count":1,"area":null},{"id":"2608.29264","title":"EpaCache: Error-Propagation-Aware Caching for Accelerating Diffusion-Based Visual Generation","created":"2026-08-29","cited_by_count":1,"area":null},{"id":"2509.26277","title":"Cat: Post-Training Quantization Error Reduction via Cluster-based Affine Transformation","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2603.27665","title":"Test-Time Instance-Specific Parameter Composition: A New Paradigm for Adaptive Generative Modeling","created":"2026-03-29","cited_by_count":0,"area":null},{"id":"2605.26628","title":"Tail-Aware HiFloat4: W4A4 Post-Training Quantization for Wan2.2","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2608.25380","title":"APT: Accelerating Diffusion Transformers via Attention Probability-Guided Pruning and Quantization","created":"2026-08-26","cited_by_count":0,"area":null},{"id":"2609.32922","title":"Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.33601","title":"JustQuant: You Don't Need Smoothing, SVD, or Rotation for 4-Bit Activation Quantization","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}