YY

yy0514

·

AI & ML interests

None yet

Recent Activity

upvoted an article 28 days ago

Gaia2 and ARE: Empowering the community to study agents

upvoted a paper about 1 month ago

RepSelect: Robust LLM Unlearning via Representation Selectivity

submitted a paper about 1 month ago

RepSelect: Robust LLM Unlearning via Representation Selectivity

View all activity

Organizations

None yet

upvoted an article 28 days ago

Article

Gaia2 and ARE: Empowering the community to study agents

+9

clefourrier, gregmialz, mlcu, mortimerp9, XciD, tfrere, evijit, RomainFroger, dheeraj7596, CarolinePascal, upiter

•

Sep 22, 2025

• 136

upvoted 2 papers about 1 month ago

RepSelect: Robust LLM Unlearning via Representation Selectivity

Paper • 2606.17168 • Published Jun 15 • 5

Agents' Last Exam

Paper • 2606.05405 • Published Jun 3 • 383

upvoted a collection 5 months ago

Search-R1-v0.3

RL with outcome reward + format reward. https://arxiv.org/abs/2505.15117 • 12 items • Updated Aug 12, 2025 • 5

upvoted a paper 9 months ago

Agentic Reinforcement Learning for Search is Unsafe

Paper • 2510.17431 • Published Oct 20, 2025 • 5

upvoted a paper about 1 year ago

Clinical knowledge in LLMs does not translate to human interactions

Paper • 2504.18919 • Published Apr 26, 2025 • 26

upvoted a paper over 1 year ago

Ablation is Not Enough to Emulate DPO: How Neuron Dynamics Drive Toxicity Reduction

Paper • 2411.06424 • Published Nov 10, 2024 • 5