Answer with Evidence: Consistency-Aware Grounded Visual Question Answering for Roadside Traffic Scenes
This work introduces Enumerate-then-Answer (EtA), which reverses the generation order so that answer-evidence agreement becomes a property of the output structure, and Enumeration-Consistent Policy Optimization (ECPO), a reinforcement learning stage that uses the union of multiple rollouts as a recall teacher without g...
Run-Wei Guan, Rong-Sheng Hu, Shang-Shu Chen et al.
· 0 citations