Spatial understanding is essential for embodied agents navigating and interacting with the physical world. As observations arrive incrementally, agents must reason in a streaming manner. Yet streaming understanding must also be closed-loop: task-relevant evidence may require both recalling past observations and activel...
Yu-Xi Wei, Wei Huang, Qi-Rui Chen et al.· 0 citations
D$^2$-VLA is presented, which combines dual memory and dual-frequency control at the KV-cache interface of a pretrained VLA, which uses block-wise causal KV caching to encode observations incrementally and constructs separate historical KV read views for the VLM and action expert.
Zi-Jian Ye, Chen Wei, Wei Huang et al.· 0 citations
This work introduces LayerRecall, a current-conditioned, layer-selective memory router that retrieves relevant historical K/V states and injects them only into backbone-specific memory-sensitive layers while preserving local attention elsewhere, and proposes Cross-Horizon Prediction Matching (CHPM), which uses a privil...