Opportunistic and Delay-Tolerant Networks

Neueste Paper

• It Takes a MAESTRO To Prune Bad Experts

  Palaash Goel, Ayush Maheshwari, Tanmoy Chakraborty · 10. Juli 2026

  Sparsely-activated Mixture-of-Experts (MoE) language models achieve remarkable inference efficiency by activating only a small fraction of parameters per token, yet their full expert banks reside in memory at all times, creating a prohibitive deployment bottleneck. Existing structured pruning method…

• Memory-Native Non-Terrestrial Networks for Embodied Intelligence

  Chengyang Li, Yikun Wang, Jiahui He, Yujie Wan, Shuai Wang, Yuan Wu, Yik-Chung Wu, Chengzhong Xu, Huseyin Arslan · 2. Juli 2026

  Non-terrestrial networks (NTN) provide ubiquitous connectivity for embodied intelligence (EI), enabling robots in wilderness to leverage cloud resources or report critical information to remote centers. However, the synergy is nontrivial due to the highly-dynamic, resource-constrained, topology-vary…

• An Open-Source Framework to Emulate Delay and Disruption Tolerant Networks for International Space Station Communication

  Krit Grover, Marcelo Ponce · 22. Mai 2026

  Delay and Disruption Tolerant Networks (DTN) are critical for reliable communications in challenged network environments, particularly for space systems where end-to-end connectivity cannot be guaranteed. We present an open-source, full-stack implementation of the Bundle protocol for communicating w…

• Relay Buffer Independent Communication over Pooled HBM for Efficient MoE Inference on Ascend

  Tianlun Hu, Tiancheng Hu, Shengsheng Litang, Sheng Wang, Xiaoming Bao, Yuxing Li, Wei Wang, Zhongzhe Hu, Lijun Li, Hongwei Sun, Jingbin Zhou\\ · 8. Mai 2026

  Mixture-of-Experts (MoE) inference requires large-scale token exchange across devices, making dispatch and combine major bottlenecks in both prefill and decode. Beyond network transfer, routing-driven layout transformation, temporary relay, and output restoration can add substantial overhead. Existi…

• Latency-Aware Resource Allocation over Heterogeneous Networks: A Lorentz-Invariant Market Mechanism

  Saad Alqithami · 7. April 2026

  We present a telecom-native auction mechanism for allocating bandwidth and time slots across heterogeneous-delay networks, ranging from low-Earth-orbit (LEO) satellite constellations to delay-tolerant deep-space relays. The Lorentz-Invariant Auction (LIA) treats bids as spacetime events and reweight…

• Variational Routing: A Scalable Bayesian Framework for Calibrated Mixture-of-Experts Transformers

  Albus Yizhuo Li, Matthew Wicker · 11. März 2026

  Foundation models are increasingly being deployed in contexts where understanding the uncertainty of their outputs is critical to ensuring responsible deployment. While Bayesian methods offer a principled approach to uncertainty quantification, their computational overhead renders their use impracti…

• Three AI-agents walk into a bar . . . . `Lord of the Flies' tribalism emerges among smart AI-Agents

  Dhwanil M. Mori, Neil F. Johnson · 27. Februar 2026

  Near-future infrastructure systems may be controlled by autonomous AI agents that repeatedly request access to limited resources such as energy, bandwidth, or computing power. We study a simplified version of this setting using a framework where N AI-agents independently decide at each round whether…

• Prompt-Driven Low-Altitude Edge Intelligence: Modular Agents and Generative Reasoning

  Jiahao You, Ziye Jia, Chao Dong, Qihui Wu · 17. Februar 2026

  The large artificial intelligence models (LAMs) show strong capabilities in perception, reasoning, and multi-modal understanding, and can enable advanced capabilities in low-altitude edge intelligence. However, the deployment of LAMs at the edge remains constrained by some fundamental limitations. F…

• Towards Adaptive, Scalable, and Robust Coordination of LLM Agents: A Dynamic Ad-Hoc Networking Perspective

  Rui Li, Zeyu Zhang, Xiaohe Bo, Quanyu Dai, Chaozhuo Li, Feng Wen, Xu Chen · 10. Februar 2026

  Multi-agent architectures built on large language models (LLMs) have demonstrated the potential to realize swarm intelligence through well-crafted collaboration. However, the substantial burden of manual orchestration inherently raises an imperative to automate the design of agentic workflows. We fr…

• Deep Temporal Graph Clustering: A Comprehensive Benchmark and Datasets

  Meng Liu, Ke Liang, Siwei Wang, Xingchen Hu, Sihang Zhou, Xinwang Liu · 21. Januar 2026

  Temporal Graph Clustering (TGC) is a new task with little attention, focusing on node clustering in temporal graphs. Compared with existing static graph clustering, it can find the balance between time requirement and space requirement (Time-Space Balance) through the interaction sequence-based batc…

• Adaptive Science Operations in Deep Space Missions Using Offline Belief State Planning

  Grace Ra Kim, Hailey Warner, Duncan Eddy, Evan Astle, Zachary Booth, Edward Balaban, Mykel J. Kochenderfer · 13. Januar 2026

  Deep space missions face extreme communication delays and environmental uncertainty that prevent real-time ground operations. To support autonomous science operations in communication-constrained environments, we present a partially observable Markov decision process (POMDP) framework that adaptivel…

• Improving Reliability of Human Trafficking Alerts in Airports

  Nana Oye Akrofi Quarcoo, Milena Radenkovic · 1. Januar 2026

  This paper investigates the latter scenario of individual emergency alerts in airports by applying two existing benchmark delay tolerant network protocols and evaluating their performance of delivery ratio and latency. First, the paper provides a background on Mobile Ad Hoc Networks (MANETs) and Del…

• MoE Pathfinder: Trajectory-driven Expert Pruning

  Xican Yang, Yuanhe Tian, Yan Song · 23. Dezember 2025

  Mixture-of-experts (MoE) architectures used in large language models (LLMs) achieve state-of-the-art performance across diverse tasks yet face practical challenges such as deployment complexity and low activation efficiency. Expert pruning has thus emerged as a promising solution to reduce computati…

• Loss-Guided Auxiliary Agents for Overcoming Mode Collapse in GFlowNets

  Idriss Malek, Aya Laajil, Abhijith Sharma, Eric Moulines, Salem Lahlou · 11. November 2025

  Although Generative Flow Networks (GFlowNets) are designed to capture multiple modes of a reward function, they often suffer from mode collapse in practice, getting trapped in early-discovered modes and requiring prolonged training to find diverse solutions. Existing exploration techniques often rel…

• FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

  Yutong Feng, Xu Liu, Yutong Xia, Yuxuan Liang · 11. November 2025

  Accurately modeling complex dynamic spatio-temporal systems requires capturing flow-mediated interdependencies and context-sensitive interaction dynamics. Existing methods, predominantly graph-based or attention-driven, rely on similarity-driven connectivity assumptions, neglecting asymmetric flow e…