{"total":23,"rows":[{"id":"2504.02508","title":"APHQ-ViT: Post-Training Quantization with Average Perturbation Hessian Based Reconstruction for Vision Transformers","created":"2025-04-03","cited_by_count":19,"area":null},{"id":"2410.04960","title":"On Efficient Variants of Segment Anything Model: A Survey","created":"2024-10-07","cited_by_count":16,"area":null},{"id":"2410.21352","title":"LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment","created":"2024-10-28","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":"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":"2405.06525","title":"SSA-Seg: Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation","created":"2024-05-10","cited_by_count":4,"area":null},{"id":"2410.01813","title":"Privacy-Preserving SAM Quantization for Efficient Edge Intelligence in Healthcare","created":"2024-09-14","cited_by_count":4,"area":null},{"id":"2505.04861","title":"Mix-QSAM: Mixed-Precision Quantization of the Segment Anything Model","created":"2025-05-08","cited_by_count":4,"area":null},{"id":"2503.03088","title":"AHCQ-SAM: Toward Accurate and Hardware-Compatible Post-Training Segment Anything Model Quantization","created":"2025-03-05","cited_by_count":3,"area":null},{"id":"2503.06515","title":"SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model","created":"2025-03-09","cited_by_count":3,"area":null},{"id":"2507.08765","title":"Compress Any Segment Anything Model (SAM)","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2511.13023","title":"SLMQuant:Benchmarking Small Language Model Quantization for Practical Deployment","created":"2025-11-17","cited_by_count":2,"area":null},{"id":"2602.08224","title":"Efficient-SAM2: Accelerating SAM2 with Object-Aware Visual Encoding and Memory Retrieval","created":"2026-02-09","cited_by_count":2,"area":null},{"id":"2505.14638","title":"Dual Precision Quantization for Efficient and Accurate Deep Neural Networks Inference","created":"2025-05-20","cited_by_count":1,"area":null},{"id":"2506.09782","title":"Q-SAM2: Accurate Quantization for Segment Anything Model 2","created":"2025-06-11","cited_by_count":1,"area":null},{"id":"2603.11917","title":"PicoSAM3: Real-Time In-Sensor Region-of-Interest Segmentation","created":"2026-03-12","cited_by_count":1,"area":null},{"id":"2605.16901","title":"CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model","created":"2026-05-16","cited_by_count":1,"area":null},{"id":"2603.13804","title":"Memory-efficient Continual Learning with Prototypical Exemplar Condensation","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2604.16855","title":"When W4A4 Breaks Camouflaged Object Detection: Token-Group Dual-Constraint Activation Quantization","created":"2026-04-18","cited_by_count":0,"area":null},{"id":"2607.19811","title":"Lean-SAM2: Target-Anchored Memory and Encoder Acceleration for SAM2","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.28589","title":"MixFrag: Fragility-Guided Mixed-Precision Post-Training Quantization for Vision Transformers","created":"2026-07-30","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":"2609.38811","title":"DCM-SAM: Defect-Conditioned Mixture of LoRA Experts for NPU-Deployed AM Defect Segmentation","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}