arxiv:2406.16758
Taehyeon Kim
Kthyeon
AI & ML interests
LLM Inference: Parallel, Speculative, Instructive Decoding
Recent Activity
upvoted
a
paper
about 1 month ago
Flex-Judge: Think Once, Judge Anywhere
upvoted
a
paper
2 months ago
Learning Adaptive Parallel Reasoning with Language Models
Organizations
models
0
None public yet
datasets
0
None public yet