With the rapid growth of space activities, near-Earth space is becoming increasingly congested, leading to a higher risk of spacecraft collisions and space debris generation. Recent close-proximity encounters and collision incidents necessitate efficient and cost-effective onboard systems for space object detection (SOD) and collision avoidance. While deep learning (DL) enabled Edge AI using low-cost vision sensors on single or multiple satellites has shown promises for SOD, significant challenges remain, including limited datasets, small SOD, and the lack of comprehensive performance assessments. This paper presents a collaborative Edge AI framework for multiview SOD and systematically benchmarks DL models and fusion strategies. Results show that higher image resolution significantly improves small SOD. For multiple views, image-level fusion reduces the combined communication and inference latency by 30.13% and 32.80% on average compared with feature-level and attention-based fusion across the evaluated inter-satellite link (ISL) bandwidth. For larger view sets, feature-level and attention-based fusion achieve better detection accuracy at the cost of analysis in the sensing-communication pipeline, revealing that multiview collaboration introduces minimal latency overhead under ISL constraints when reception capacity is not exceeded. Our work provides valuable design insights for future collaborative satellite network design, supporting the emerging space situational awareness and space traffic management requirements.
Xingyu Qu, Siyuan Lu, Zhiyu Chen, Sheng Wang, Tao Lin
原文摘要
Multi-model LLM serving uses routers, cascades and agent workflows to move requests across models with different costs and capabilities. Existing serving systems reuse KV caches only within one model, so every switch forces the target to re-prefill history the source already processed, adding time to first token (TTFT) that grows with history length and target size. Cross-model KV transfer can replace this prefill, yet prior methods are slower than re-prefill end to end. We present CacheBridge, the first serving system to accelerate heterogeneous multi-model workloads through cross-model KV transfer. It co-designs a compact, attention-calibrated KV mapper with systematic optimization for online multi-model serving, which makes model switch efficient on latency and memory cost. In Qwen3 14B$\rightarrow$32B agent serving on $τ$-bench, it reduces mean TTFT by $30$ to $98\%$ versus re-prefill at $1$ to $24$ QPS with comparable task success. Across five model pairs from three families, it uses $8$ to $12\times$ less mapper memory than Closed-Form Mapper and retains on average $97.94\%$ and $102.94\%$ of re-prefill task quality on chat/reasoning and RAG workloads, respectively. The promising results have opened new opportunities for efficient multi-model LLM serving through cross-model KV reuse.