Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces
Paper • 2605.29288 • Published • 9
mantou
mantou-cloud
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Diagnosing Harmful Continuation in Answer-Correct Long-CoT Training Traces upvoted a paper 12 months ago
Truth in the Few: High-Value Data Selection for Efficient Multi-Modal
ReasoningOrganizations
None yet
upvoted a paper 1 day ago