Edge-cloud collaboration for long-horizon LLM agents: benchmark data and paper (arXiv 2610.17816).
Pengcheng Huang
chengpingan
·
AI & ML interests
AI & Agent
Recent Activity
upvoted a paper about 2 hours ago
Skill-Decoupled On-Policy Expert Distillation for Unified Vision-Language Models upvoted a paper about 2 hours ago
Chaos in the Text: Revealing the Modality Preference in Mixed-Modality Retrievers submitted a paper 2 days ago
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent ExecutionOrganizations
None yet
datasets 8
chengpingan/CoFaithfulQA
Viewer • Updated • 8.53k • 109
chengpingan/EC2-Bench
Viewer • Updated • 128 • 112 • 1
chengpingan/wildclaw_trej
Updated • 4
chengpingan/ExpandR_retriever_training_data
Viewer • Updated • 709k • 6 • 1
chengpingan/ExpandR_llm_training_data
Viewer • Updated • 30k • 3 • 1
chengpingan/ParamMute-Training-Data
Viewer • Updated • 32.6k • 72 • 2
chengpingan/LLM-QE-Retriever-Training-Data
Viewer • Updated • 709k • 23
chengpingan/LLM-QE-DPO-Training-Data
Viewer • Updated • 30k • 9