paper

Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences

paperactiveprovisionalspeaking-the-language-of-science-toward-a-general-purpose-generative-foundation-model-for-the-natural-sciences-e79c17fc·1 events·first seen 25h ago

Aliases: Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences

Co-occurring entities

LOGOS

More like this (12)

generative language modeling generative models Reasoning Language Models Emergent Language as an Approach to Conscious AI Arithmetic Pedagogy for Language Models LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories causal generative modeling Diffusion Language Models Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application Transformer Language Models Automated reproducibility assessments in the social and behavioral sciences using large language models Language Generation in the Limit

Recent events (1)

6arXiv · cs.CL·25h ago·source ↗

LOGOS: A unified autoregressive foundation model for natural science tasks across domains

Researchers introduce LOGOS (Language Of Generative Objects in Science), a generative language model that encodes heterogeneous scientific objects and spatial interactions as discrete token sequences within a single autoregressive framework, avoiding explicit coordinates or geometric neural networks. Models are trained at 1B, 3B, and 8B parameter scales and consistently match or outperform domain-specific baselines across diverse scientific tasks. The work argues that AI for Science should converge on shared architectures and training paradigms with LLMs rather than maintaining a separate technical stack. Model weights are released publicly.

Frontier Model Releases Open Weights Progress Speaking the Language of Science: Toward a General-Purpose Generative Foundation Model for the Natural Sciences LOGOS