Similar Items: SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
- Make Your LVLM KV Cache More Lightweight
- What Matters in Practical Learned Image Compression
- Zero-Shot Imagined Speech Decoding via Imagined-to-Listened MEG Mapping
- Adaptive Policy Selection and Fine-Tuning under Interaction Budgets for Offline-to-Online Reinforcement Learning
- Auto-FlexSwitch: Efficient Dynamic Model Merging via Learnable Task Vector Compression
- On Adaptivity in Zeroth-Order Optimization