Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs
Paper • 2608.12781 • Published • 33
fengyuanlu
straybird
·
AI & ML interests
None yet
Recent Activity
upvoted a paper about 18 hours ago
Beyond Correctness: Benchmarking and Aligning Response Behaviors in Hybrid-Thinking MLLMs updated a model about 3 years ago
RUCAIBox/Erya updated a model about 3 years ago
RUCAIBox/Erya4FTOrganizations
upvoted a paper about 18 hours ago