SeongWan Kim
idgmatrix
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM Inference upvoted a paper about 7 hours ago
Speculative Forcing for Efficient Autoregressive Video Generation upvoted a paper about 7 hours ago
Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP TrimmingOrganizations
None yet