{"total":27,"rows":[{"id":"2307.07982","title":"A Survey of Techniques for Optimizing Transformer Inference","created":"2023-07-16","cited_by_count":35,"area":null},{"id":"2301.00131","title":"Guided Hybrid Quantization for Object detection in Multimodal Remote Sensing Imagery via One-to-one Self-teaching","created":"2022-12-31","cited_by_count":12,"area":null},{"id":"2303.09977","title":"Semantic Scene Completion with Cleaner Self","created":"2023-03-17","cited_by_count":12,"area":null},{"id":"2303.08983","title":"Reinforce Data, Multiply Impact: Improved Model Accuracy and Robustness with Dataset Reinforcement","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2306.14662","title":"Cross Architecture Distillation for Face Recognition","created":"2023-06-26","cited_by_count":9,"area":null},{"id":"2403.09195","title":"SAM-Lightening: A Lightweight Segment Anything Model with Dilated Flash Attention to Achieve 30 times Acceleration","created":"2024-03-14","cited_by_count":7,"area":null},{"id":"2406.07337","title":"Transferring Knowledge from Large Foundation Models to Small Downstream Models","created":"2024-06-11","cited_by_count":7,"area":null},{"id":"2312.03286","title":"Indirect Gradient Matching for Adversarial Robust Distillation","created":"2023-12-06","cited_by_count":6,"area":null},{"id":"2503.02154","title":"AugFL: Augmenting Federated Learning with Pretrained Models","created":"2025-03-04","cited_by_count":6,"area":null},{"id":"2211.04256","title":"Bridging Fairness and Environmental Sustainability in Natural Language Processing","created":"2022-11-08","cited_by_count":5,"area":null},{"id":"2304.02263","title":"Towards Efficient Task-Driven Model Reprogramming with Foundation Models","created":"2023-04-05","cited_by_count":5,"area":null},{"id":"2510.27432","title":"Mitigating Semantic Collapse in Partially Relevant Video Retrieval","created":"2025-10-31","cited_by_count":5,"area":null},{"id":"2202.01011","title":"Auto-Transfer: Learning to Route Transferrable Representations","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2209.13858","title":"Variance Tolerance Factors For Interpreting ALL Neural Networks","created":"2022-09-28","cited_by_count":2,"area":null},{"id":"2211.04031","title":"Hilbert Distillation for Cross-Dimensionality Networks","created":"2022-11-08","cited_by_count":2,"area":null},{"id":"2307.00198","title":"Filter Pruning for Efficient CNNs via Knowledge-driven Differential Filter Sampler","created":"2023-07-01","cited_by_count":2,"area":null},{"id":"2405.06038","title":"From Algorithm to Hardware: A Survey on Efficient and Safe Deployment of Deep Neural Networks","created":"2024-05-09","cited_by_count":2,"area":null},{"id":"2505.03113","title":"Image Recognition with Online Lightweight Vision Transformer: A Survey","created":"2025-05-06","cited_by_count":2,"area":null},{"id":"2305.16484","title":"Batch Model Consolidation: A Multi-Task Model Consolidation Framework","created":"2023-05-25","cited_by_count":1,"area":null},{"id":"2408.08250","title":"Computer Vision Model Compression Techniques for Embedded Systems: A Survey","created":"2024-08-15","cited_by_count":1,"area":null},{"id":"2605.13859","title":"BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation","created":"2026-04-14","cited_by_count":1,"area":null},{"id":"2205.03602","title":"Automatic Block-wise Pruning with Auxiliary Gating Structures for Deep Convolutional Neural Networks","created":"2022-05-07","cited_by_count":0,"area":null},{"id":"2211.13852","title":"Adaptive Attention Link-based Regularization for Vision Transformers","created":"2022-11-25","cited_by_count":0,"area":null},{"id":"2311.01571","title":"On Preserving the Knowledge of Long Clinical Texts","created":"2023-11-02","cited_by_count":0,"area":null},{"id":"2411.10077","title":"Hierarchical mutual distillation for multi-view fusion: Learning from all possible view combinations","created":"2024-11-15","cited_by_count":0,"area":null},{"id":"2503.21272","title":"Reinforced Model Merging","created":"2025-03-27","cited_by_count":0,"area":null},{"id":"2509.22319","title":"Progressive Weight Loading: Accelerating Initial Inference and Gradually Boosting Performance on Resource-Constrained Environments","created":"2025-09-26","cited_by_count":0,"area":null}],"next_cursor":null}