§00 · APOD
The Guardians of Rapa Nui beneath the Milky Way
In the words of today's astrophotographer, Rositsa Dimitrova, "What have these silent sentinels watched pass across the sky?" The volcanic mo'ai (meaning statue) of Ahu Tongariki stand guard over Rapa Nui (Isla de Pascua, Easter Island), a Polynesian island (annexed by Chile in 1888) located thousands of kilometers off the coast of South America in the Pacific Ocean. Due to the island's remoteness, the mo'ai, with their backs to the dark ocean, are able to gaze upon a clear and vibrant night sky. Pictured, these larger-than-life statues stare at the bright band of the Milky Way, partly obscure...
2026-03-25 · © Rositsa Dimitrova
Text:
Keighley Rockcliffe
(NASA
GSFC,
UMBC CSST,
CRESST II) ·
NASA APOD ↗
§06 · arXiv Dispatch
Research Filed Today
Preprints submitted to arXiv on March 25, 2026. Science before peer review.
01
Relying on in-domain annotations and precise sensor-rig priors, existing 3D occupancy prediction methods are limited in both scalability and out-of-domain generalization. While recent visual geometry foundation models exhibit strong generalization capabilities, they were mainly d...
Anh-Quan Cao, Tuan-Hung Vu
02
Vision Language Models (VLMs) are increasingly used for tasks like medical report generation and visual question answering. However, fluent diagnostic text does not guarantee safe visual understanding. In clinical practice, interpretation begins with pre-diagnostic sanity checks:...
Ufaq Khan, Umair Nawaz, L D M S S Teja et al. (+5)
03
Unified models capable of interleaved generation have emerged as a promising paradigm, with the community increasingly converging on autoregressive modeling for text and flow matching for image generation. To advance this direction, we propose a unified reinforcement learning fra...
Jie Liu, Zilyu Ye, Linxiao Yuan et al. (+8)
04
Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this limitation, we formulate Degradation-Aware Optical Flow, a new task targeting accurate dense corres...
Jaewon Min, Jaeeun Lee, Yeji Choi et al. (+7)
05
Dynamical systems theory and reinforcement learning view world evolution as latent-state dynamics driven by actions, with visual observations providing partial information about the state. Recent video world models attempt to learn this action-conditioned dynamics from data. Howe...
Zhen Li, Zian Meng, Shuwei Shi et al. (+5)
06
Accurate estimation of aerodynamic state variables such as freestream velocity and angle of attack (AoA) is important for aerodynamic load prediction, flight control, and model validation. This work presents a non-intrusive method for estimating vehicle velocity and AoA from stru...
Chandler B. Smith, S. Hales Swift, Andrew Steyer et al. (+1)
07
Existing approaches for improving the efficiency of Large Vision-Language Models (LVLMs) are largely based on the concept of visual token reduction. This approach, however, creates an information bottleneck that impairs performance, especially on challenging tasks that require fi...
Adrian Bulat, Alberto Baldrati, Ioannis Maniadis Metaxas et al. (+2)
08
Diffusion and flow matching models have unlocked unprecedented capabilities for creative content creation, such as interactive image and streaming video generation. The growing demand for higher resolutions, frame rates, and context lengths, however, makes efficient generation in...
Brian Chao, Lior Yariv, Howard Xiao et al. (+1)
Source: arXiv.org · Cornell University
§03 · The Wire
Wikipedia in Motion
500
edits recorded in the most recent sample. Most-edited topics:
WalterListGriseargiolestesWayneWarrenJohnAssemblyUnited