Loading activity…
@duynguyen772
PhD Student @unccs @unc_ai_group, advised by @mohitban47 | Student Researcher @GoogleCloud | Prev: @AmazonScience
AI
Its creators say deployment feedback updates executable safety rules that enforce policies before agents act.
AI
A researcher behind AVSD says it combines multiple teacher views, including hints, solutions and execution outputs, to improve token-level learning signals for LLM math and code reasoning.