search
paper models
Trends
- 1
A newly surfaced arXiv preprint introduces the concept of Context Language Models, an alternative framing to large language models that emphasizes context as a central architectural component. The paper is drawing attention on technology forums, with commenters debating how the approach differs from existing transformer-based systems and whether it could change how language models are designed.
- 2Harvard physicist Matthew Schwartz publishes 36 papers co-authored with Claude▼Harvard particle physicist Matthew Schwartz drops 36 papers authored with Claude
Harvard particle physicist Matthew Schwartz has released 36 research papers authored in collaboration with Anthropic's Claude AI assistant. The unusual volume and the use of a large language model as a research partner are drawing attention among physicists, who are debating the quality of the work and what it means for the role of AI in scientific authorship.
- 3Polyedergarten Showcases Handmade Paper Polyhedron Models●Polyedergarten: Garden of Paper Polyhedron Models
Polyedergarten, a German website, presents an extensive collection of handmade paper models of polyhedra, the geometric solids studied since antiquity. The site documents dozens of intricate constructions, from Platonic and Archimedean solids to more exotic star polyhedra, complete with photographs and building notes. Geometry and craft enthusiasts are sharing it as a charming intersection of mathematics and paper art.
- 4Researchers unveil FastOPD framework for compact vision-language-action robots●Researchers proposed FastOPD, a foundation-to-lightweight VLA framework enabling deployment through efficient on-policy
Researchers have proposed FastOPD, a new framework that compresses large foundation vision-language-action models into lightweight versions suitable for real-world robot deployment. The approach uses efficient on-policy distillation, allowing small models to learn directly from a big model's behavior. The work was released as a paper on arXiv in the robotics category, and early discussion is focused on whether it makes advanced robot policies cheaper and easier to run on hardware.
- 5New robotics paper proposes SafeStreamingFlow method●SafeStreamingFlow aligns flow sampling dynamics with execution dynamics. arXiv cs.RO Source: arXiv cs.RO https:// arxiv.
A new arXiv paper in robotics introduces SafeStreamingFlow, a method that aligns flow sampling dynamics with execution dynamics. The approach is aimed at improving how flow-based models behave during real-time robot execution. Details of experiments and performance have not yet been widely discussed.
- 6SocialVLA turns human reactions into robot intervention signals●SocialVLA converts spontaneous human reactions into runtime intervention signals for VLA manipulation. Source: arXiv cs.
A new paper on arXiv introduces SocialVLA, a vision-language-action model that reads spontaneous human reactions and converts them into runtime intervention signals for robot manipulation. The aim is to let robots respond to natural human cues, like flinches or gestures, while working alongside people. Details of performance and real-world testing remain in the paper itself.