Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

18 June 2025

Ankan Deria

Adinath Madhavrao Dukre

Feilong Tang

Sara Atito

Sudipta Roy

Muhammad Awais

Muhammad Haris Khan

Imran Razzak

ArXiv (abs)PDF HTML

Papers citing "Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning"

Title
No papers