6 papers
EKT-Router: Expert-Evidence Alignment for Embodied Vision-Language Models
Weilin Ruan, Yingjie Xu, Yangkai Wei +7
Embodied vision-language models must answer questions from partial, evolving observations. Their success depends on both the reasoning capability selected and the evidence availabl…
Anvil: Scaling Embodied Spatial Intelligence through Knowledge Recirculation
Weilin Ruan, Bohan Zhou, Jinghao Li +12
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant form…
In-Context Learning for Robots: Methods and Applications
Haojian Huang, Zexi Li, Junhao Guo +36
General-purpose robots must infer what a new task requires and translate that understanding into appropriate physical action. In-context learning (ICL) for robots supports this pro…
WorldLines: Benchmarking and Modeling Long-Horizon Stateful Embodied Agents
Yehang Zhang, Jianchong Su, Haojian Huang +7
To assist humans over extended periods in real homes, embodied agents must remember user routines, world states, and past interactions. Existing long-term memory benchmarks mainly…
MC-Risk: Multi-Component Risk Fields for Risk Identification and Motion Planning
Maximilian Link, Yingjie Xu, Yingbai Hu +1
We present MC-Risk, a planner-aligned, multi-component risk field on a bird's-eye-view grid that yields early, calibrated, and class-aware risk localization. MC-Risk linearly compo…
PyraVid: Hierarchical Multimodal Memory for Long-Horizon Video Reasoning
Sikuan Yan, Sicheng Dong, Haotong Wang +8
Memory has become an increasingly important component of agentic systems, as these systems are expected to reason over long-term experience. However, prior work has largely focused…