arxiv:2601.11061
Ruizhe Li
rzdiversity
ยท
AI & ML interests
Mechanistic Interpretability, Multimodal LLMs
Recent Activity
authored
a paper
about 8 hours ago
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
upvoted
a
paper
about 8 hours ago
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
submitted
a paper
about 8 hours ago
Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs
Organizations
None yet
models
0
None public yet
datasets
0
None public yet