Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration
Quick summary
arXiv:2609.05801v1 Announce Type: new Abstract: A document modeled as a discrete sequence of tokens can be thought of as being generated from a composition of texts from different domains; a README file, for example, moves between prose, code, and configuration. When such a document is corrupted and only frozen domain experts are available, restoring it requires deciding both what is missing and which expert to trust at each position, at test time and without region labels or a trained router. We introduce evidence-aligned local composition, which infers a soft, position-wise weighting over th
Key takeaways
- arXiv:2609.05801v1 Announce Type: new Abstract: A document modeled as a discrete sequence of tokens can be thought of as being generated from a composition of texts from different domains; a README file, for example, moves between prose, code, and configuration.
- When such a document is corrupted and only frozen domain experts are available, restoring it requires deciding both what is missing and which expert to trust at each position, at test time and without region labels or a trained router.
- We introduce evidence-aligned local composition, which infers a soft, position-wise weighting over th
Why it matters
The importance of “Evidence-Aligned Local Composition of Discrete Experts for Sequence Restoration” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments