Goto

Collaborating Authors

 Media


Textually Pretrained Speech Language Models

Neural Information Processing Systems

Speech language models (SpeechLMs) process and generate acoustic data only, without textual supervision. In this work, we propose TWIST, a method for training SpeechLMs using a warm-start from a pretrained textual language models. We show using both automatic and human evaluations that TWIST outperforms a cold-start SpeechLM across the board. We empirically analyze the effect of different model design choices such as the speech tokenizer, the pretrained textual model, and the dataset size. We find that model and dataset scale both play an important role in constructing better-performing SpeechLMs. Based on our observations, we present the largest (to the best of our knowledge) SpeechLM both in terms of number of parameters and training data. We additionally introduce two spoken versions of the StoryCloze textual benchmark to further improve model evaluation and advance future research in the field. We make speech samples, code and models publicly available.2


AMassive Scale Semantic Similarity Dataset of Historical English

Neural Information Processing Systems

A diversity of tasks use language models trained on semantic similarity data. While there are a variety of datasets that capture semantic similarity, they are either constructed from modern web data or are relatively small datasets created in the past decade by human annotators.



Ethical Considerations for Responsible Data Curation

Neural Information Processing Systems

HCCV datasets constructed through nonconsensual web scraping lack crucial metadata for comprehensive fairness and robustness evaluations. Current remedies are post hoc, lack persuasive justification for adoption, or fail to provide proper contextualization for appropriate application. Our research focuses on proactive, domain-specific recommendations, covering purpose, privacy and consent, and diversity, for curating HCCV evaluation datasets, addressing privacy and bias concerns. We adopt an ante hoc reflective perspective, drawing from current practices, guidelines, dataset withdrawals, and audits, to inform our considerations and recommendations.


Japan zoo staffer allegedly dumps wife's body inside incinerator

BBC News

Japan zoo staffer allegedly dumps wife's body inside incinerator A popular Japanese zoo has delayed its opening for the summer season after an employee told police he had disposed of his wife's body in the zoo's incinerator, local media reported. Asahiyama Zoo in the northern city of Asahikawa was supposed to welcome visitors on Wednesday in time for Japan's Golden Week holiday period, after completing a three-week maintenance break. But the city government says the zoo will now remain closed until Friday as investigations continue. Last week, police searched the zoo grounds after the employee told them he had disposed of his wife's body in the zoo's incinerator, local media reported. The incinerator was used to dispose of animal carcasses when they died.


18 silly finalists from the Comedy Wildlife People's Choice Awards

Popular Science

And your prestigious winner is...*drumroll please*...a bird with grass on its face. More information Adding us as a Preferred Source in Google by using this link indicates that you would like to see more of our content in Google News results. Now which direction is my nest? Breakthroughs, discoveries, and DIY tips sent six days a week. The people have spoken chuckled.


Runway-to-Space Challenge brings spaceflight closer

FOX News

Runway-to-Space Spaceplane Challenge lets teams fly payloads on Dawn Aerospace's reusable Aurora spaceplane from Oklahoma, with flights expected to begin in 2027.


DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

Neural Information Processing Systems

Generating controllable and photorealistic digital human avatars is a long-standing and important problem in Vision and Graphics. Recent methods have shown great progress in terms of either photorealism or inference speed while the combination of the two desired properties still remains unsolved. To this end, we propose a novel method, called DELIFFAS, which parameterizes the appearance of the human as a surface light field that is attached to a controllable and deforming human mesh model. At the core, we represent the light field around the human with a deformable two-surface parameterization, which enables fast and accurate inference of the human appearance. This allows perceptual supervision on the full image compared to previous approaches that could only supervise individual pixels or small patches due to their slow runtime. Our carefully designed human representation and supervision strategy leads to state-of-the-art synthesis results and inference time. The video results and code are available at https://vcai.


The Download: Musk and Altman's legal showdown, and AI's profit problem

MIT Technology Review

Plus: OpenAI has ended its exclusive partnership with Microsoft. Elon Musk and Sam Altman are going to court over OpenAI's future Ahead of OpenAI's IPO, the court could rule on whether the company can exist as a for-profit enterprise. It could even oust its leadership. Musk, an OpenAI co-founder, claims he was deceived into bankrolling the firm under false pretenses. Find out how the trial could upend the global AI race . In a celebrated episode, a community of gnomes sneak out at night to steal underpants.


Kevin O'Leary details massive Utah AI data center to rival China's tech dominance

FOX News

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .