computation reduction
Computation reduction involves techniques aimed at decreasing the computational complexity of algorithms or models, improving efficiency and making them feasible for real-time applications.
- D2SA: Dual-Stage Distribution and Slice Adaptation for Efficient Test-Time Adaptation in MRI Reconstruction
- Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay
- Improving the Straight-Through Estimator with Zeroth-Order Information
- Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework
- Plug-and-Play Context Feature Reuse for Efficient Masked Generation
- TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation