Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 35
WANGBORAN
wangbr
AI & ML interests
None yet
Recent Activity
upvoted a paper about 1 month ago
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs upvoted a paper 2 months ago
ReflectWorld-MM: An Entity-Oriented Multimodal Memory System for Open-Ended Video Streams upvoted a paper 11 months ago
MR-Align: Meta-Reasoning Informed Factuality Alignment for Large
Reasoning ModelsOrganizations
None yet