Attention Amnesia in Hybrid LLMs: When CoT Fine-Tuning Breaks Long-Range Recall, and How to Fix It
Paper • 2606.11052 • Published • 4
Zhu
Boyu123
AI & ML interests
None yet
Recent Activity
upvoted a paper 1 day ago
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short upvoted a paper 2 months ago
The Depth Ceiling: On the Limits of Large Language Models in Discovering Latent PlanningOrganizations
None yet