§00 · APOD
The Path of Artemis II
Why doesn't Artemis II land on the Moon? The main reason is that Artemis II is primarily a test mission designed to make a future Artemis missions -- which will land humans on the Moon -- better prepared. Similarly, NASA's Apollo 8 and Apollo 10 went right near the Moon as tests before Apollo 11 -- which landed. As the trajectory in the featured animated video shows, Artemis II will loop around both the Earth and the Moon before returning to the Earth about 10 days after launch. The Artemis II mission will take humans outside the Earth's magnetosphere for the first time since the Apollo miss...
2026-04-06 ·
NASA APOD ↗
§06 · arXiv Dispatch
Research Filed Today
Preprints submitted to arXiv on April 6, 2026. Science before peer review.
01
Recent vision-language models (VLMs) typically rely on a single vision encoder trained with contrastive image-text objectives, such as CLIP-style pretraining. While contrastive encoders are effective for cross-modal alignment and retrieval, self-supervised visual encoders often c...
Ankan Deria, Komal Kumar, Xilin He et al. (+4)
02
This paper explores the use of server learning for enhancing the robustness of federated learning against malicious attacks even when clients' training data are not independent and identically distributed. We propose a heuristic algorithm that uses server learning and client upda...
Van Sy Mai, Kushal Chakrabarti, Richard J. La et al. (+1)
03
Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator, despite that SR is fundamentally a low-resolu...
Rongyuan Wu, Lingchen Sun, Zhengqiang Zhang et al. (+4)
04
Non-contrast chest CTs offer a rich opportunity for both conventional pulmonary and opportunistic extra-pulmonary screening. While Multi-Task Learning (MTL) can unify these diverse tasks, standard hard-parameter sharing approaches are often suboptimal for modeling distinct pathol...
Fengbei Liu, Sunwoo Kwak, Hao Phung et al. (+6)
05
Large language models (LLMs) often produce confident but incorrect answers in settings where abstention would be safer. Standard evaluation protocols, however, require a response and do not account for how confidence should guide decisions under different risk preferences. To add...
Sean Wu, Fredrik K. Gustafsson, Edward Phillips et al. (+3)
06
Remote sensing segmentation in real deployment is inherently continual: new semantic categories emerge, and acquisition conditions shift across seasons, cities, and sensors. Despite recent progress, many incremental approaches still treat training steps as isolated updates, which...
Jiekai Wu, Rong Fu, Chuangqi Li et al. (+10)
07
Model predictive control (MPC) with learned world models has emerged as a promising paradigm for embodied control, particularly for its ability to generalize zero-shot when deployed in new environments. However, learned world models often struggle with long-horizon control due to...
Wancong Zhang, Basile Terver, Artem Zholus et al. (+8)
08
The rapid adoption of the Internet of Medical Things (IoMT) is transforming healthcare by enabling seamless connectivity among medical devices, systems, and services. However, it also introduces serious cybersecurity and patient safety concerns as attackers increasingly exploit n...
Rahul Jaiswal, Per-Arne Andersen, Linga Reddy Cenkeramaddi et al. (+2)
Source: arXiv.org · Cornell University