Home
Tongyi Lab Open-Sources LOGOS, First Unified Scientific Large Model Outperforming NatureLM with 1B Parameters
On June 18, 2026, Tongyi Lab announced the open-source release of LOGOS (Language Of Generative Objects in Science), the first multi-domain scientific generative foundation model built on a unified "scientific grammar."
Developed jointly by ATH-Token Foundry and the Huoqian Institute of Artificial Intelligence at Renmin University, this model aims to break the fragmented "one task, one expert model" status quo in traditional AI for Science (AI4S). By encoding diverse scientific objects—proteins, small molecules, materials, and chemical reactions—into a unified discrete token sequence, it enables cross-domain knowledge integration and autoregressive generation within a native large model framework.

LOGOS's core breakthrough lies in its innovative "scientific grammar" design and spatial interaction discretization technology. This allows the model to deeply understand complex 3D spatial interaction rules and perform autoregressive generation without relying on scarce 3D coordinate data or specialized geometric networks, ensuring full consistency in form and objective between pre-training and downstream tasks.
Evaluation results show that LOGOS-1B, with just 1 billion parameters, consistently matches or surpasses domain-specific methods across six representative tasks: pocket-conditioned ligand generation, retrosynthesis prediction (Top-1 accuracy 74.8%), pocket site identification (Top-n accuracy 58.5% on the HOLO4K dataset), and MOF material generation (a 76% increase in the proportion of new building units). In some tasks, it even outperformed NatureLM—which uses 8×7B parameters—while using only 1/56 of the parameter count.

Related article
U.S. Stocks Hit Historic Milestone as AI and Aerospace Giants Prepare for Trillion-Dollar Debut
Elon Musk, Sam Altman, and Dario Amodei, three titans of the technology sector, are advancing toward initial public offerings for their respective ventures. With SpaceX, OpenAI, and Anthropic—three industry behemoths nearing trillion-dollar valuation
Swedish AI Startup Lovable Eyes $13.2 Billion Valuation After Major Funding Round
As AI-driven coding tools gain traction, Swedish startup Lovable has secured a major funding round. The company aims to raise $3 billion, potentially boosting its valuation to $13.2 billion—double the $6.6 billion recorded last December. Menlo Ventur
Google Tests Remy AI Agent for Gemini as Focus Shifts to User Control
According to Business Insider, Google is testing Remy, a new AI personal agent for Gemini. This tool aims to execute tasks on behalf of users, streamlining both professional workflows and daily routines.Currently, Remy is undergoing testing in an int
Related Special Topic Recommendations
Comments (0)
0/500
On June 18, 2026, Tongyi Lab announced the open-source release of LOGOS (Language Of Generative Objects in Science), the first multi-domain scientific generative foundation model built on a unified "scientific grammar."
Developed jointly by ATH-Token Foundry and the Huoqian Institute of Artificial Intelligence at Renmin University, this model aims to break the fragmented "one task, one expert model" status quo in traditional AI for Science (AI4S). By encoding diverse scientific objects—proteins, small molecules, materials, and chemical reactions—into a unified discrete token sequence, it enables cross-domain knowledge integration and autoregressive generation within a native large model framework.

LOGOS's core breakthrough lies in its innovative "scientific grammar" design and spatial interaction discretization technology. This allows the model to deeply understand complex 3D spatial interaction rules and perform autoregressive generation without relying on scarce 3D coordinate data or specialized geometric networks, ensuring full consistency in form and objective between pre-training and downstream tasks.
Evaluation results show that LOGOS-1B, with just 1 billion parameters, consistently matches or surpasses domain-specific methods across six representative tasks: pocket-conditioned ligand generation, retrosynthesis prediction (Top-1 accuracy 74.8%), pocket site identification (Top-n accuracy 58.5% on the HOLO4K dataset), and MOF material generation (a 76% increase in the proportion of new building units). In some tasks, it even outperformed NatureLM—which uses 8×7B parameters—while using only 1/56 of the parameter count.

U.S. Stocks Hit Historic Milestone as AI and Aerospace Giants Prepare for Trillion-Dollar Debut
Elon Musk, Sam Altman, and Dario Amodei, three titans of the technology sector, are advancing toward initial public offerings for their respective ventures. With SpaceX, OpenAI, and Anthropic—three industry behemoths nearing trillion-dollar valuation
Swedish AI Startup Lovable Eyes $13.2 Billion Valuation After Major Funding Round
As AI-driven coding tools gain traction, Swedish startup Lovable has secured a major funding round. The company aims to raise $3 billion, potentially boosting its valuation to $13.2 billion—double the $6.6 billion recorded last December. Menlo Ventur











