Knapsack RL: Unlocking Exploration of LLMs via Optimizing Budget Allocation
Paper
•
2509.25849
•
Published
•
47
•
2
Ziniu Li
ziniuli
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
about 8 hours ago
ReMax: A Simple, Effective, and Efficient Reinforcement Learning Method
for Aligning Large Language Models
upvoted
a
paper
about 8 hours ago
Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
upvoted
a
paper
7 days ago
How Far Are We from Genuinely Useful Deep Research Agents?
Organizations
commented
a
paper
2 months ago
Adding _set_gradient_checkpointing for compatibility
👍
2
6
#22 opened about 2 years ago
by
vriveras