4 papers
Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution
Weichen Xu, Zhenhua Liu, Lin Luo +8
Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.e., execution horizon) before replanning, turning replanning into a task-agnostic peri…
TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
ZhiYuan Feng, Yu Deng, Ruichuan An +11
In real home deployments, household agents must often operate from a complete household scene and a situated household request, rather than from a clean task specification. Such re…
Aladdin: Joint Placement and Scaling for SLO-Aware LLM Serving
Chengyi Nie, Rodrigo Fonseca, Zhenhua Liu
The demand for large language model (LLM) inference is gradually dominating the artificial intelligence workloads. Therefore, there is an urgent need for cost-efficient inference s…
Training DNN Models over Heterogeneous Clusters with Optimal Performance
Chengyi Nie, Jessica Maghakian, Zhenhua Liu
Adjusting batch sizes and adaptively tuning other hyperparameters can significantly speed up deep neural network (DNN) training. Despite the ubiquity of heterogeneous clusters, exi…