Da Yu

Jellyfish0538

·

https://dayu11.github.io/

dayu11

AI & ML interests

Differentially private deep learning

Recent Activity

upvoted a paper 27 days ago

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

upvoted a paper about 2 months ago

Orchard: An Open-Source Agentic Modeling Framework

upvoted a paper 4 months ago

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

View all activity

Organizations

None yet

liked a model 10 months ago

google/vaultgemma-1b

Text Generation • 1B • Updated Sep 12, 2025 • 3.03k • 411

liked a model about 1 year ago

microsoft/GUI-Actor-7B-Qwen2-VL

Image-Text-to-Text • 8B • Updated Aug 9, 2025 • 234 • 39

liked 2 datasets over 2 years ago

ncbi/pubmed

Updated Jan 26, 2024 • 1.22k • 164

tatsu-lab/alpaca_eval

Updated Aug 16, 2024 • 15.7k • 66

liked a dataset almost 3 years ago

lmsys/lmsys-chat-1m

Viewer • Updated Jul 27, 2024 • 1M • 6.11k • 933

liked a model almost 3 years ago

yahma/llama-7b-hf

Text Generation • Updated Apr 8, 2023 • 5.05k • • 89

liked 2 datasets almost 3 years ago

lmsys/chatbot_arena_conversations

Viewer • Updated Sep 30, 2023 • 33k • 2.5k • 466

stanfordnlp/SHP

Viewer • Updated Oct 10, 2023 • 386k • 3.47k • 322