AIAny
Icon for item

Calpha: Toward Native Biomolecular Intelligence in a General-Purpose Language Model

Connects single-chain protein folding to a general-purpose language model, using its residue representations to drive a pretrained structure generator. Current results show weaker performance on longer chains and reduced scores on a general-knowledge test after protein training.

Introduction

The central test here is not whether a language model can produce protein coordinates, but whether its own representations can serve as a useful bridge between language and structural biology. Calpha demonstrates that pathway, while its results also show that connecting the modalities does not by itself improve folding accuracy.

Key Findings
  • Qwen3.5-9B receives protein sequences enriched with residue features from ESM2-3B; a generated trigger token routes its residue states to a pretrained SimpleFold-3B structure head. The head receives protein information through those states rather than a separate sequence input.
  • The system reports mean TM-scores of 0.808 on FoldBench-334, 0.635 on CASP16 domains, and 0.900 on a CAMEO-style PDB set. These figures establish a workable integration route, not a new accuracy record.
  • Comparisons with an ESM2-to-SimpleFold baseline are mixed. For 100–299-residue chains, paired confidence intervals include zero; at 300–600 residues, Calpha scores lower, with reported mean differences of -0.044, -0.160, and -0.025 across the three sets.
  • Protein training reduced accuracy on a 350-item MMLU-Pro subset from 77.4% to 70.3%. This makes the trade-off between adding a specialized capability and preserving general-purpose performance concrete.
Who It Suits—and the Trade-Off

A good fit for researchers studying how general-purpose LLM representations can connect to scientific prediction systems, especially protein-structure modeling. Look elsewhere if you need state-of-the-art folding, reliable long-chain results, complexes, ligands, or evidence that natural-language reasoning improves predicted structures; those capabilities are not established here.

Information

  • Websitearxiv.org
  • AuthorsYong Liu, Zhanpeng Shi, Peicong Lin, Zhenyi Zhong, Yizhou Dang, Wendi Wu, Haoling Li, Shuangjia Zheng
  • Published date2026/11/16

More Items

Reduces Transformer parameter count by repeatedly applying shared blocks, then combines their updates with geometric decay and learned attention. On ClimbMix, it beats standard baselines in validation loss with fewer Transformer parameters.

Proposes a framework for robots that combine foundation models with an embodied runtime to interpret intent, call skills, verify outcomes, and adapt. It also outlines an evaluation framework and a roadmap toward sustained autonomy.

Turns screen observations into keyboard and mouse actions to complete long-horizon game tasks. Sparse reasoning, persistent memory, and online reinforcement learning support real-time interaction and multi-step decisions.