5 papers
Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understanding
Zhiyun Jiang, Hanyong Wang, Binbin Liang +4
Scene safety understanding plays a life-or-death role in situational awareness in various critical domains. Traditional methods that rely on learning direct mappings between scenes…
Absence is Presence: Understanding Visual Scene Negative Events Under Safety Cognitive Constraint
Zhiyun Jiang, Hanyong Wang, Binbin Liang +3
Traditional scene understanding focuses on affirmative information objectively present in images. However, in safety-critical domains, comprehending key information that should exi…
Benchmarking MLLMs via Cognitive Expected Scene Graph for Safety-Critical Visual Negation Understanding
Zhiyun Jiang, Hanyong Wang, Binbin Liang +3
True machine intelligence requires transcending passive pixel registration to master top-down functional reasoning over absent information via visual negation understanding. Howeve…
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…
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…