CATP prunes low-confidence tokens in COD Transformers and uses dual-path compensation to cut computation while preserving segmentation accuracy on boundary regions.
Sparse-tuning: Adapting vision transformers with efficient fine-tuning and inference
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
verdicts
UNVERDICTED 2representative citing papers
SFLAM is a quantized split federated fine-tuning framework for large AI models that reduces device memory, energy use, and latency via split learning, optimization strategies, and simulations showing gains over conventional methods.
citing papers explorer
-
CATP: Confidence-Aware Token Pruning for Camouflaged Object Detection
CATP prunes low-confidence tokens in COD Transformers and uses dual-path compensation to cut computation while preserving segmentation accuracy on boundary regions.
-
Deploying Large AI Models on Resource-Limited Devices with Split Federated Learning
SFLAM is a quantized split federated fine-tuning framework for large AI models that reduces device memory, energy use, and latency via split learning, optimization strategies, and simulations showing gains over conventional methods.