Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
Paper • 2510.08525 • Published • 23 •
2
wenjiedu
Kurt232
AI & ML interests
None yet
Recent Activity
upvoted a paper 20 days ago
The Trinity of Consistency as a Defining Principle for General World Models upvoted a paper 3 months ago
OmniAgent: Audio-Guided Active Perception Agent for Omnimodal Audio-Video UnderstandingOrganizations
None yet
commented a
paper 5 months ago
Does Phi-4-mini equal to Phi-4-mini-instruct?
1
#31 opened 9 months ago
by Kurt232