arxiv:2505.14827
Yufan Zhuang PRO
yzhuang
AI & ML interests
research scientist @ google, phd @ uc san diego, large language models
Recent Activity
upvoted a paper 3 days ago
RRSI: Regularized Recursive Self-Improvement of Agent Harnesses upvoted a paper about 2 months ago
EnvHarness: Awakening Static Worlds for Agent Learning liked a model 3 months ago
thinkingmachines/InklingOrganizations
models 239
yzhuang/Llama-3.1-8B-Instruct-attn
8B • Updated • 7
yzhuang/Llama-3.1-8B-Instruct-AgenticLU
8B • Updated • 87 • 1
yzhuang/linear_icl_projector_sentiment_analysis_gtr-t5-base_Mistral-7B-Instruct-v0.3
3.15M • Updated • 5
yzhuang/linear_icl_projector_sentiment_analysis_stella_en_1.5B_v5_Mistral-7B-Instruct-v0.3
4.19M • Updated • 4
yzhuang/linear_icl_projector_sentiment_analysis_SFR-Embedding-2_R_Mistral-7B-Instruct-v0.3
16.8M • Updated • 8
yzhuang/linear_icl_projector_sentiment_analysis_NV-Embed-v1_Mistral-7B-Instruct-v0.3
16.8M • Updated • 5
yzhuang/linear_icl_projector_sentiment_analysis_gtr-t5-base_Meta-Llama-3.1-8B-Instruct
3.15M • Updated • 9
yzhuang/linear_icl_projector_summarization_gtr-t5-base_Meta-Llama-3.1-8B-Instruct
3.15M • Updated • 6
yzhuang/linear_projector_distclm2_wikitext_gtr-t5-base_Meta-Llama-3.1-8B-Instruct
3.15M • Updated • 7
yzhuang/linear_icl_projector_sentiment_analysis_gtr-t5-base_Qwen2-7B-Instruct
2.75M • Updated • 7
datasets 306
yzhuang/Agentic-Long-Context-Understanding-QA
Viewer • Updated • 114k • 369 • 24
yzhuang/aimo-validation-aime
Viewer • Updated • 90 • 18
yzhuang/useragent_gpt-4o-2024-11-20_hq
Viewer • Updated • 64.9k • 69
yzhuang/user_agent_megadataset
Viewer • Updated • 84.9k • 33
yzhuang/repobench_python_131072
Viewer • Updated • 23.6k • 194
yzhuang/tinyzero-Countdown-Tasks-7
Viewer • Updated • 329k • 6
yzhuang/tinyzero-Countdown-Tasks-3
Viewer • Updated • 329k • 8
yzhuang/tinyzero-Countdown-Tasks-4
Viewer • Updated • 329k • 23
yzhuang/tinyzero-Countdown-Tasks-5
Viewer • Updated • 329k • 15
yzhuang/tinyzero-Countdown-Tasks-6
Viewer • Updated • 329k • 8