collaborators

5 papers

cs.LG2025

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

Ye Li, Jiahe Feng, Yuan Meng +6

Diffusion Policy (DP) excels in embodied control but suffers from high inference latency and computational cost due to multiple iterative denoising steps. The temporal complexity o…

cs.CV2025

FREE: Uncertainty-Aware Autoregression for Parallel Diffusion Transformers

Xinwan Wen, Bowen Li, Jiajun Luo +2

Diffusion Transformers (DiTs) achieve state-of-the-art generation quality but require long sequential denoising trajectories, leading to high inference latency. Recent speculative…

cs.RO2025

Spatial Policy: Guiding Visuomotor Robotic Manipulation with Spatial-Aware Modeling and Reasoning

Yijun Liu, Yuwei Liu, Yuan Meng +8

Vision-centric hierarchical embodied models have demonstrated strong potential. However, existing methods lack spatial awareness capabilities, limiting their effectiveness in bridg…

cs.CV2025

SP-VLA: A Joint Model Scheduling and Token Pruning Approach for VLA Model Acceleration

Ye Li, Yuan Meng, Zewen Sun +7

Vision-Language-Action (VLA) models have attracted increasing attention for their strong control capabilities. However, their high computational cost and low execution frequency hi…

cs.CL2024

EMS: Adaptive Evict-then-Merge Strategy for Head-wise KV Cache Compression Based on Global-Local Importance

Yingxin Li, Ye Li, Yuan Meng +4

As large language models (LLMs) continue to advance, the demand for higher quality and faster processing of long contexts across various applications is growing. KV cache is widely…