Compiler Infrastructure, Code Generation, Optimization Passes, Backend Development
LLM-Crowdsourced: A Benchmark-Free Paradigm for Mutual Evaluation of Large Language Models
arxiv.org·2d
LoRA-PAR: A Flexible Dual-System LoRA Partitioning Approach to Efficient LLM Fine-Tuning
arxiv.org·4d
CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs
arxiv.org·2d
Loading...Loading more...