arXiv AI October 23, 2026 By Xiaolong Huang, Yinyuan Zhang, Daliang Xu, Yun Ma, Qing Li, Mengwei Xu, Shangguang Wang, Gang Huang, Xuanzhe Liu

Resuming Vision-Language Inference across Onboard Interruptions

Read the original on arXiv AI →

OrbitWeaver is a framework that enables vision‑language models to resume inference after onboard interruptions on low‑Earth orbit satellites. It uses phase‑aware checkpointing and dependency‑aware dynamic recovery to preserve progress across power, thermal, and fault‑induced shutdowns, reducing restart latency and SSD write volume. Experiments on satellite payload hardware show up to a 4.07‑fold speedup and a 3.56‑fold reduction in write traffic, and a 72‑hour deployment confirmed its ability to maintain inference progress across repeated bus‑enforced shutdowns.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Hugging Face Trending Papers

Oct 21

Resuming Vision-Language Inference across Onboard Interruptions

Executing vision-language models (VLMs) aboard low-Earth orbit satellites enables flexible processing of observation data without first downlinking it to the ground. On commercial off-the-shelf payloa...

llms multimodal

arXiv Machine Learning

Jun 19

Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.

By Liang Su

llms agents robotics efficiency benchmarks data-engineering

Hugging Face Trending Papers

Jul 5

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation. Their bidirectional attention prevents exact autoregressive-style KV caching, since committing one position shifts the KV activations of all others.

llms diffusion

arXiv AI

Oct 5

Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines

Zephon is a data loader designed for foundation model training that ensures deterministic ordering of training data batches even when GPU resources change, checkpoints are resumed, or different processing backends are used. It handles online, stateful pipelines—where tokenization, packing, and mixing of samples create complex n‑to‑m transformations—by partitioning the data stream into topology‑independent lanes, serializing ordering decisions, and checkpointing only bounded in‑flight state. Experiments on text and vision‑language tasks show Zephon delivers competitive throughput while offering guarantees that existing loaders lack for such pipelines.

By Maximilian B\"other, Josh Wills, Ties Robroek, Sonnet Xu, Paul Burstein, Daniel Zayas, Cody Blakeney, Siddharth Joshi, Haoli Yin, Rishabh Adiga, Haakon Mongstad, Luke Merrick, Pratyush Maini, Ari Morcos, Matthew Leavitt, Ana Klimovic, Bogdan Gaza

efficiency multimodal

arXiv Machine Learning

Jul 7

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

arXiv:2607. 04206v1 Announce Type: cross Abstract: Diffusion language models (dLLMs) generate text by iteratively denoising a masked response and can commit multiple output positions per model invocation.

By Nitin Kedia, Saurabh Agarwal, Myungjin Lee, Aditya Akella

llms diffusion

arXiv Machine Learning

Jul 8

PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint

arXiv:2607. 01646v2 Announce Type: replace Abstract: State-of-the-art large language model (LLM) training takes tens of thousands of graphics processing units (GPUs) for months and encounters failures across the software and hardware stack.

By Haotian Xie, Junlin Chen, Mingkai Zheng, Lishan Yang, Zhao Zhang

llms benchmarks

One email a morning, machine-written

Related stories

Resuming Vision-Language Inference across Onboard Interruptions

Execution-State Capsules: Graph-Bound Execution-State Checkpoint and Restore for Low-Latency, Small-Batch, On-Device Physical-AI Serving

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

Zephon: Elastic Determinism for Online, Stateful Foundation Model Data Loading Pipelines

Sangam: Efficiently Serving Diffusion LLMs with the AR Stack

PHOENIX: Resilient LLM Training with Hot-Swapping via Zero-Overhead Checkpoint