← Flipkart questions
Reported in a candidate post, May 2025

Fine-tuning LLMs and VLMs, DPO and PPO reward policies

Filed under Flipkart

Discussion centred on generative AI topics the team works on: fine-tuning LLMs, vision-language models (VLMs), and reward and preference methods such as DPO and PPO, plus behavioural and values…

You've read your 3 free write-ups

Sign up free to keep reading. Your account opens the first 10 questions of every company.

Related Flipkart questions

Collected from public candidate posts and coding forums. Updated Nov 2026.