efficiency improvement
Efficiency improvement in AI contexts often refers to optimizing algorithms or models to reduce computational resource usage, memory consumption, or time taken for training and inference, allowing for faster and more cost-effective AI systems.
- Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
- KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
- LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
- Reinforced Active Learning for Large-Scale Virtual Screening with Learnable Policy Model
- Revolutionizing Training-Free NAS: Towards Efficient Automatic Proxy Discovery via Large Language Models
- Think Only When You Need with Large Hybrid-Reasoning Models
- Thinkless: LLM Learns When to Think