Preprint
Aug 2026
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Experiments on Qwen3-VL-4B and Qwen3-VL-8B show that incorporating pattern-specific penalties into reinforcement learning can mitigate cross-mode misalignment while incurring a marginal task performance trade-off.
Xin-Ming Wang, Wei-Nong Wang, Hong-Ming Yang et al.
· 2 citations
· ⚡1