Dani Balcells
danibalcells
AI & ML interests
Mechanistic interpretability
Cognitive science
Recent Activity
authored
a paper
about 1 month ago
SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via
Multi-Agent Multi-Turn Reinforcement Learning
liked
a model
4 months ago
Qwen/Qwen2.5-1.5B-Instruct
liked
a model
4 months ago
meta-llama/Llama-3.2-3B-Instruct
Organizations
