3 papers
cs.RO2026
Fast and Accurate: An Adaptive VLA Inference Framework through Environment-aware Model Selection
Yuewei Sun, Lang Qin, Zechuan Tian +11
Embodied intelligence demands both long-horizon reasoning and real-time closed-loop responsiveness. Recent dual-system Vision-Language-Action (VLA) architectures combine fast react…
cs.CL2026
Adaptive Depth Sparse Framework: Similarity-Driven Resource Allocation for Pre-Trained LLMs
Yidu Wu, Xiang Wang, Kejie Zhao +3
Large language models (LLMs) achieve strong generation and reasoning performance, but the Transformer architecture incurs high inference cost. Existing acceleration methods often r…
cs.AI2026
MAR: Efficient Large Language Models via Module-aware Architecture Refinement
Junhong Cai, Guiqin Wang, Kejie Zhao +6
Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address t…