Sergio Hernandez

sergio-hernandez

3 1

·

https://sergiohg.com/

AI & ML interests

Data-centric post-training: environments & signals.

Recent Activity

authored a paper about 5 hours ago

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

upvoted a paper about 6 hours ago

QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents

liked a dataset about 6 hours ago

View all activity

Organizations

sergio-hernandez 's models 2

sergio-hernandez/learning-to-ask_logprob-sampling_round-penalty_step-60

2B • Updated Jul 11, 2025 • 2

sergio-hernandez/learning-to-ask_logprob-sampling_round-penalty_step-12

2B • Updated Jul 11, 2025 • 2