Loading activity…
@jotyshafiq
Sr. Research Director@Salesforce AI, Assoc. Prof@NTU (on leave) Work: SFR-RL, SFR-DeepResearch, SFR-RAG, SFR-Judge, XGen, CodeT5, ALBEF, ChartQA
AI
The authors introducing EvoHarnessBench say even today’s self-evolving methods cannot reliably adapt to new capabilities while retaining earlier competence.