2 papers
cs.CL2026
The Illusion of Control: Why Bare Classifier Inversion Silently Fails in Concept-Bottleneck Text Generation
Qi Bing, Xiaowei Shao
Concept-bottleneck controllable generation routes multi-attribute control through a low-dimensional concept code that, at deployment, must be synthesised from a target attribute co…
cs.AI2025
Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimization
Shiyang Duan, Yuan Tian, Qi Bing +1
The exponential growth of scientific knowledge has made the automated generation of scientific hypotheses that combine novelty, feasibility, and research value a core challenge. Ex…