§00 · APOD
Robert Goddard and Nell
Robert H. Goddard, considered the father of modern rocketry, was born in Worcester Massachusetts in 1882. As a 16 year old, Goddard read H.G. Wells' science fiction classic "War Of The Worlds" and dreamed of space flight. By 1926 he had designed, built, and flown the world's first liquid fuel rocket. Launched 100 years ago, on March 16, 1926 from his aunt Effie's farm in Auburn Massachusetts, the rocket dubbed "Nell", rose to an altitude of 41 feet in a flight that lasted about 2 1/2 seconds. In this posed photo Goddard stands next to the 10 foot tall rocket, holding the launch stand frame. To...
2026-03-28 ·
NASA APOD ↗
§06 · arXiv Dispatch
Research Filed Today
Preprints submitted to arXiv on March 28, 2026. Science before peer review.
01
Multi-shot video generation is crucial for long narrative storytelling, yet current bidirectional architectures suffer from limited interactivity and high latency. We propose ShotStream, a novel causal multi-shot architecture that enables interactive storytelling and efficient on...
Yawen Luo, Xiaoyu Shi, Junhao Zhuang et al. (+5)
02
Existing feed-forward 3D Gaussian Splatting methods predict pixel-aligned primitives, leading to a quadratic growth in primitive count as resolution increases. This fundamentally limits their scalability, making high-resolution synthesis such as 4K intractable. We introduce LGTM ...
Yixing Lao, Xuyang Bai, Xiaoyang Wu et al. (+7)
03
Vision Foundation Models (VFMs) have become the cornerstone of modern computer vision, offering robust representations across a wide array of tasks. While recent advances allow these models to handle varying input sizes during training, inference typically remains restricted to a...
Bocheng Zou, Mu Cai, Mark Stanley et al. (+2)
04
Reference-to-video (R2V) generation is a controllable video synthesis paradigm that constrains the generation process using both text prompts and reference images, enabling applications such as personalized advertising and virtual try-on. In practice, existing R2V methods typical...
Lei Wang, YuXin Song, Ge Wu et al. (+5)
05
Vision-language-action models have reshaped autonomous driving to incorporate languages into the decision-making process. However, most existing pipelines only utilize the language modality for scene descriptions or reasoning and lack the flexibility to follow diverse user instru...
Sicheng Zuo, Yuxuan Li, Wenzhao Zheng et al. (+3)
06
Human driving behavior is inherently personal, which is shaped by long-term habits and influenced by short-term intentions. Individuals differ in how they accelerate, brake, merge, yield, and overtake across diverse situations. However, existing end-to-end autonomous driving syst...
Zehao Wang, Huaide Jiang, Shuaiwu Dong et al. (+3)
07
Graphic design is a creative and innovative process that plays a crucial role in applications such as e-commerce and advertising. However, developing an automated design system that can faithfully translate user intentions into editable design files remains an open challenge. Alt...
Xincheng Shuai, Song Tang, Yutong Huang et al. (+2)
08
Accurate estimation of large displacement optical flow remains a critical challenge. Existing methods typically rely on iterative local search or/and domain-specific fine-tuning, which severely limits their performance in large displacement and zero-shot generalization scenarios....
Dingxi Zhang, Fangjinhua Wang, Marc Pollefeys 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:
ListAssemblyCollegeStateShemonSabbaeWomenEngineering