AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders
Paper
•
2510.19779
•
Published
•
60
Reward Reasoning Models
Reward-Reasoning
AI & ML interests
None yet
Recent Activity
upvoted
a
paper
3 months ago
AdaSPEC: Selective Knowledge Distillation for Efficient Speculative
Decoders
new activity
6 months ago
Reward-Reasoning/RRM-32B:Regarding the rewards in the knockout tournament
upvoted
a
paper
8 months ago
Reward Reasoning Model
Organizations
None yet
upvoted
a
paper
3 months ago
Regarding the rewards in the knockout tournament
3
#1 opened 7 months ago
by
droussis
upvoted
a
paper
8 months ago
updated
2
models
8 months ago
published
2
models
8 months ago