#Parameter Efficiency
2 articles with this tag
AI Research
Code2LoRA: Repository Context without Overhead
Code2LoRA generates dynamic LoRA adapters for code LLMs, offering repository context without inference overhead and adapting to evolving codebases.
26 days ago
AI Research
JACTUS AI Unifies Compression and Adaptation
JACTUS AI unifies parameter compression and task adaptation, outperforming sequential methods with fewer retained parameters across vision and language tasks.
about 2 months ago