Liang Zeng PRO

zengliangcs

·

AI & ML interests

None yet

Recent Activity

upvoted a paper about 4 hours ago

Your Transformer Can Hold Two Thoughts at Once: Evidence of Linear Superposition in LLMs

upvoted a paper 4 months ago

π-Bench: Evaluating Proactive Personal Assistant Agents in Long-Horizon Workflows

upvoted a paper 6 months ago

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability

View all activity

Organizations

zengliangcs 's papers 9

arxiv:2602.21818

arxiv:2507.01352

arxiv:2506.19290

arxiv:2506.12508

arxiv:2505.22312

arxiv:2410.18451

arxiv:2407.08348

arxiv:2406.06563

arxiv:2406.00605