computational overhead

An Adaptive Orthogonal Convolution Scheme for Efficient and Flexible CNN Architectures ICML 2025 Compute or Load KV Cache? Why Not Both? ICML 2025 Exploiting Similarity for Computation and Communication-Efficient Decentralized Optimization ICML 2025 FedSSI: Rehearsal-Free Continual Federated Learning with Synergistic Synaptic Intelligence ICML 2025 Metadata Conditioning Accelerates Language Model Pre-training ICML 2025 METEOR: Multi-Encoder Collaborative Token Pruning for Efficient Vision Language Models ICCV 2025 Predicting High-precision Depth on Low-Precision Devices Using 2D Hilbert Curves ICML 2025 T2: An Adaptive Test-Time Scaling Strategy for Contextual Question Answering EMNLP 2025 Video-Panda: Parameter-efficient Alignment for Encoder-free Video-Language Models CVPR 2025 When to Continue Thinking: Adaptive Thinking Mode Switching for Efficient Reasoning EMNLP 2025 Efficient Non-stationary Online Learning by Wavelets with Applications to Online Distribution Shift Adaptation ICML 2024 Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance CVPR 2024 Low-Cost High-Power Membership Inference Attacks ICML 2024 Memory Optimization for Deep Networks ICLR 2021