arxiv:2504.00927
Jason Weston
spermwhale
AI & ML interests
None yet
Recent Activity
authored
a paper
about 14 hours ago
Multi-Token Attention
authored
a paper
13 days ago
SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning
Tasks
authored
a paper
2 months ago
Step-KTO: Optimizing Mathematical Reasoning through Stepwise Binary
Feedback
Organizations
None yet
Papers
23
models
None public yet
datasets
None public yet