Probing and steering biology across Boltz-1s trunk-diffusion boundary

• URL: http://arxiv.org/abs/2608.11475v1
• Date: Tue, 11 Aug 2026 22:25:42 GMT
• Title: Probing and steering biology across Boltz-1s trunk-diffusion boundary
• Abstract summary: We analyze per-residue activations from the Pairformer trunk and diffusion module of Boltz-1 using linear probes, sparse autoencoders, and causal interventions.<n>We release the trained trunk and diffusion SAEs, Boltz-1 per-residue activations, and the analysis code.
• Score: 32.505127447635864
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AlphaFold3-class structure predictors pair a representational trunk, which processes sequence and context, with a diffusion module, which generates atomic coordinates. How biological information changes as it crosses this architectural boundary remains poorly understood. We analyze per-residue activations from the Pairformer trunk and diffusion module of Boltz-1 using linear probes, sparse autoencoders (SAEs), and causal interventions. From the trunk, both geometry (secondary structure, disorder) and sequence chemistry (amino-acid identity, signal peptides, disulfide-bond annotations) are linearly decodable. In the diffusion module, the two diverge. Secondary structure transfers essentially unchanged, whereas sequence chemistry is strongly attenuated. We then test whether decodable directions can steer the model, intervening on the final trunk single representation that conditions the diffusion module. Helix and coil directions change predicted structure dose-dependently against matched-norm random controls, but a beta-strand direction that is highly predictive (F1 =0.82) produces no measurable increase in strand content: linear decodability does not imply causal influence at the site we tested. The same probes also score markedly lower against sparse SwissProt annotations than against dense DSSP labels, because unannotated residues that the model gets right are charged as false positives; such scores are therefore lower bounds. Finally, supervised probes outscore single SAE features wherever a label already exists. We release the trained trunk and diffusion SAEs, Boltz-1 per-residue activations, and the analysis code.

Related papers

• Schrödinger Bridges on Lie Group Manifolds for Probabilistic Intrinsic Generation [8.18074374709342]
  We study Schrodinger bridges for kinetic dynamics on Lie group manifold with state X_t = (g_t, xi_t) in G x g.<n> entropy projection determines the conditional law of the unobserved endpoint velocities.<n>Experiments on multiple Lie group manifold datasets validate the feasibility and consistency of our proposed method.
  arXiv  Detail & Related papers  (2026-09-02T07:01:21Z)
• Is Convergence Inevitable? Tracing Output Homogeneity Back to Base Models [49.46165710676499]
  We find that semantic convergence is observed from the first alignment stage.<n>We find that convergence can be revealed and amplified, but not introduced by the SFT data.<n> Taken together, our results suggest that semantic convergence may arise naturally from the objectives underlying LM training.
  arXiv  Detail & Related papers  (2026-08-11T20:47:06Z)
• Intrinsic Structure: Spectral Identifiability for Mechanistic Interpretability [51.56484100374058]
  We prove the first identifiability theorem for a mechanistic-interpretability primitive.<n>The spectrum is an identifiable, model-intrinsic fingerprint with a stated error bar, not a legible decomposition.
  arXiv  Detail & Related papers  (2026-08-10T19:42:01Z)
• scHelix: Asymmetric Dual-Stream Integration via Explicit Gene-Level Disentanglement [84.88065404629079]
  scHelix is a dataset-adaptive framework that fundamentally changes how features are processed.<n> scHelix utilizes a dual-stream sparse diffusion encoder equipped with stop-gradient graph caching.<n> scHelix outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2026-05-18T15:55:13Z)
• Operator Spectroscopy of Trained Lattice Samplers [0.0]
  We analyze the trained field-space function itself.<n>We project these functions onto operator bases fixed before the fit.<n>The operator basis is model- and symmetry-dependent, but the test is common.
  arXiv  Detail & Related papers  (2026-05-11T20:06:15Z)
• Measuring and Decomposing Mode Separation via the Canonical Diffusion [0.0]
  Mode separation is a fundamental geometric property of densities, difficult to quantify in high dimensions.<n>We measure mode separation through a single process intrinsic to the density.<n>We apply our framework to three settings: (i) synthetic Gaussian mixtures, where SSA tracks mutual information; (ii) SDXL text-to-image generations, where SSA and DA capture structure that entropy and PCA miss; and (iii) molecular dynamics of alanine dipeptide, where DA recovers the known slow backbones from static samples alone.
  arXiv  Detail & Related papers  (2026-05-09T08:05:55Z)
• Learning Stable Predictors from Weak Supervision under Distribution Shift [2.8410059035029955]
  Learning from weak or proxy supervision is common when ground-truth labels are unavailable.<n>We formalize this as supervision drift, defined as changes in P(y | x, c) across contexts.<n>We study it in CRISPR-Cas13d experiments where guide efficacy is inferred indirectly from RNA-seq responses.
  arXiv  Detail & Related papers  (2026-04-05T23:46:49Z)
• Departures: Distributional Transport for Single-Cell Perturbation Prediction with Neural Schrödinger Bridges [51.83259180910313]
  A major bottleneck in gene function analysis is the unpaired nature of single-cell data.<n>We approximate Schrdinger Bridge (SB) to tackle unpaired single-cell perturbation data.<n>Our model effectively captures heterogeneous single-cell responses and achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2025-11-17T08:27:13Z)
• Rao-Blackwell Gradient Estimators for Equivariant Denoising Diffusion [55.95767828747407]
  In domains such as molecular and protein generation, physical systems exhibit inherent symmetries that are critical to model.<n>We present a framework that reduces training variance and provides a provably lower-variance gradient estimator.<n>We also present a practical implementation of this estimator incorporating the loss and sampling procedure through a method we call Orbit Diffusion.
  arXiv  Detail & Related papers  (2025-02-14T03:26:57Z)
• Diffusion-Jump GNNs: Homophiliation via Learnable Metric Filters [10.357474047610172]
  High-order Graph Neural Networks (HO-GNNs) have been developed to infer consistent latent spaces in the heterophilic regime. Homophiliation, i.e., the process of learning piecewise smooth latent spaces in the heterophilic regime, is formulated as a Dirichlet problem.
  arXiv  Detail & Related papers  (2023-06-29T14:31:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.