2 papers
cs.RO2026
DEFLECT: Temporal Counterfactual Preference Learning for Delay-Robust Asynchronous VLAs
Yixiang Zhu, Yonghao Chen, Zijie Yang +3
Vision-Language-Action (VLA) policies increasingly rely on asynchronous inference to hide model latency behind ongoing robot motion. During inference, the robot continues executing…
cs.AR2026
MixFP4: Enhancing NVFP4 with Adaptive FP4/INT4 Block Representations
Jiaxiang Zou, Yonghao Chen, Ruilong Wu +1
As large language models continue to scale, fine-grained block-scaled low-precision formats such as NVFP4 are increasingly adopted for their substantial throughput and memory benef…