arxiv:2608.08722
Victor Gallego
vicgalle
AI & ML interests
Preference fine-tuning, alignment & synthetic data.
Building LLMs in general!
Recent Activity
authored a paper 5 days ago
Opponent Aware Reinforcement Learning upvoted a paper 5 days ago
Opponent Aware Reinforcement Learning authored a paper 8 days ago
Gaming Without an Attacker: Benchmark Fingerprinting in LLM-Driven Search Under Selection PressureOrganizations
