Lize Pirenne
Inversta
AI & ML interests
LLMs, RL
Recent Activity
upvoted
a
paper
about 1 month ago
Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective
Reinforcement Learning for LLM Reasoning
upvoted
a
paper
about 1 month ago
Time Blindness: Why Video-Language Models Can't See What Humans Can?
upvoted
a
paper
about 1 month ago
ATLAS: Learning to Optimally Memorize the Context at Test Time
Organizations
None yet