Gabriel P. Andrade
Researcher
Works at the intersection of multi-agent reinforcement learning, game theory, and algorithmic economics.
Gabriel P. Andrade’s research & writing
All Gensyn research
- ResearchThe Role of Feedback Alignment in Self-Distillation
- ResearchLook Beyond One-Size-Fits-All LLMs with IR3DE
- ResearchStop Multitask Training. Just DUME.
- ResearchSAPO, Efficient LM Post-Training with Collective RL
- ResearchCheckFree: fault tolerant training without checkpoints