The paper-to-video task converts a research paper into a structured video abstract, distilling key concepts, methods, and conclusions into an accessible, well-organized format. While state-of-the-art video generation models demonstrate potential, they are constrained by limited context windows, rigid video duration constraints, limited stylistic diversity, and an inability to represent domain-specific knowledge. To address these limitations, we introduce Preacher, the first paper-to-video agentic system. Preacher employs a topdown approach to decompose, summarize, and reformulate the paper, followed by bottom-up video generation, synthesizing diverse video segments into a coherent abstract. To align cross-modal representations, we define key scenes and introduce a Progressive Chain of Thought (P-CoT) for granular, iterative planning. Preacher successfully generates high-quality video abstracts across five research fields, demonstrating expertise beyond current video generation models. Code will be released at: https://github.com/Gen-Verse/Paper2Video

Breakthroughs, discoveries, and DIY tips sent every weekday. Scholars believe they have solved a medieval manuscript mystery that's plagued scholars for nearly 130 years. Based on a handful of grammatical reevaluations, experts believe that they can reconcile a famously odd portion in Geoffrey Chaucer's The Canterbury Tales. In doing so, they also traced the text back to a priest from the Middle Ages who employed "memes" of the day as a way to relate to his parishioners. Their findings were published in The Review of English Studies on July 15.

Large Language Models, despite their significant capabilities, are known to fail in surprising and unpredictable ways. Evaluating their true `understanding' of language is particularly challenging due to the extensive web-scale data they are trained on. Therefore, we construct an evaluation to systematically assess natural language understanding (NLU) in LLMs by leveraging Construction Grammar (CxG), which provides insights into the meaning captured by linguistic elements known as constructions (Cxns). CxG is well-suited for this purpose because provides a theoretical basis to construct targeted evaluation sets. These datasets are carefully constructed to include examples which are unlikely to appear in pre-training data, yet intuitive and easy for humans to understand, enabling a more targeted and reliable assessment. Our experiments focus on downstream natural language inference and reasoning tasks by comparing LLMs' understanding of the underlying meanings communicated through 8 unique Cxns with that of humans. The results show that while LLMs demonstrate some knowledge of constructional information, even the latest models including GPT-o1 struggle with abstract meanings conveyed by these Cxns, as demonstrated in cases where test sentences are dissimilar to their pre-training data. We argue that such cases provide a more accurate test of true language understanding, highlighting key limitations in LLMs' semantic capabilities. We make our novel dataset and associated experimental data including prompts and model responses publicly available.

A little girl asks when she'll be able to bury her father. The preacher, named David, says it'll have to wait till spring. David speaks to another follower named James outside, played by Troy Baker, who portrayed Joel Miller in the video games. David may seem like a run-of-the-mill preacher, but his interaction with James suggests an insidious side. When David asks James if he's still "with me," Baker's James barely nods his head, letting out a weak "yeah."

South by Southwest has unveiled its list of featured speakers for the upcoming fest, which includes the cast of Veep, Seth Rogen and exec producers of AMC's, Better Call Saul's Bob Odenkrik, John Cena, and more. The fest, which runs from March 10-19, will feature discussions from fields in tech, film, music, television, business, literature, government and journalism. Check out the list below. Jessica Shortall (Social Impact) – Jessica is the Managing Director of Texas Competes, a coalition of more than 1,200 Texas companies making the data-driven case for Texas to be welcoming to LGBTQ people. This business-oriented voice has become a national model.