2 papers
cs.LG2026
SCAPE: Accurate and Efficient LLM Training with Extreme Sparse Communication
Mingkai Zheng, Junlin Chen, Haotian Xie +1
Communication increasingly dominates the cost of Large Language Model (LLM) pre-training, especially under data-parallel and sharded training schemes, where gradient synchronizatio…
cs.RO2026
The Speedup Paradox: Rethinking Inference Speed-Quality Trade-off in Embodied Tasks
Yujin Wang, Junli Chen, Yixuan Li +4
Embodied foundation models have recently been widely used to improve robot generalization and task success rates. Previous works apply lossy efficient-inference techniques such as…