2 papers
cs.IR2026
UniHEAR: Unified Heterogeneous-Source Attentive Retrieval for Knowledge-Based Visual Question Answering
Ganzhong Luo, Yang Ren, Hanyong Wang +2
Knowledge-Based Visual Question Answering (KB-VQA) requires retrieving entity knowledge from external sources to answer visually grounded questions. Existing retrieval-augmented sy…
cs.LG2026
ExO-PPO: an Extended Off-policy Proximal Policy Optimization Algorithm
Hanyong Wang, Menglong Yang
Deep reinforcement learning has been able to solve various tasks successfully, however, due to the construction of policy gradient and training dynamics, tuning deep reinforcement…