activity
20242026
most citedEMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

1 citations · 1 across the 15 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2025

TS-DP: Reinforcement Speculative Decoding For Temporal Adaptive Diffusion Policy Acceleration

Ye Li, Jiahe Feng, Yuan Meng +10

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. Existing diffusion model…