{"total":16,"rows":[{"id":"2403.07420","title":"DragAnything: Motion Control for Anything using Entity Representation","created":"2024-03-12","cited_by_count":159,"area":null},{"id":"2602.10825","title":"Flow caching for autoregressive video generation","created":"2026-02-11","cited_by_count":25,"area":null},{"id":"2405.00314","title":"Model Quantization and Hardware Acceleration for Vision Transformers: A Comprehensive Survey","created":"2024-05-01","cited_by_count":13,"area":null},{"id":"2403.07134","title":"COMQ: A Backpropagation-Free Algorithm for Post-Training Quantization","created":"2024-03-11","cited_by_count":12,"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":"2407.09111","title":"Inference Optimization of Foundation Models on AI Accelerators","created":"2024-07-12","cited_by_count":9,"area":null},{"id":"2412.07268","title":"PTSBench: A Comprehensive Post-Training Sparsity Benchmark Towards Algorithms and Models","created":"2024-12-10","cited_by_count":5,"area":null},{"id":"2409.11650","title":"Art and Science of Quantizing Large-Scale Models: A Comprehensive Overview","created":"2024-09-18","cited_by_count":2,"area":null},{"id":"2503.11159","title":"Stabilizing Quantization-Aware Training by Implicit-Regularization on Hessian Matrix","created":"2025-03-14","cited_by_count":2,"area":null},{"id":"2506.22771","title":"FF-INT8: Efficient Forward-Forward DNN Training on Edge Devices with INT8 Precision","created":"2025-06-28","cited_by_count":2,"area":null},{"id":"2511.06724","title":"Argus: Quality-Aware High-Throughput Text-to-Image Inference Serving System","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2608.28205","title":"Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency","created":"2026-08-28","cited_by_count":1,"area":null},{"id":"2506.09066","title":"ReStNet: A Reusable & Stitchable Network for Dynamic Adaptation on IoT Devices","created":"2025-06-08","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":"2609.33601","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},{"id":"2610.09877","title":"Layerwise Error Attribution for Fast and Robust Mixed-Precision Post-Training Quantization","created":"2026-10-07","cited_by_count":0,"area":null}],"next_cursor":null}