2 papers
cs.LG2026
PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents
Ziyi Bai, Siqi Li, Tinglei Huang +1
Recent studies have shown that multimodal large language models (MLLMs) can serve as embodied agents, translating language instructions and visual observations into executable plan…
cs.CL2024
SplaXBERT: Leveraging Mixed Precision Training and Context Splitting for Question Answering
Zhu Yufan, Hao Zeyu, Li Siqi +1
SplaXBERT, built on ALBERT-xlarge with context-splitting and mixed precision training, achieves high efficiency in question-answering tasks on lengthy texts. Tested on SQuAD v1.1,…