arXiv Computation and Language
Putting Transformer Theories to the Test
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv Machine Learning
Jul 21
Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks
arXiv:2607. 17624v1 Announce Type: new Abstract: Transformers are remarkably versatile and their design is largely consistent across a variety of applications.
arXiv AI
Jul 8
Transformers converge to invariant algorithmic cores
arXiv:2602. 22600v2 Announce Type: replace-cross Abstract: Training selects for behavior, not circuitry: many weight configurations can implement the same function.
arXiv AI
2d ago
The Long Delay to Arithmetic Generalization
arXiv:2604.13082v3 Announce Type: replace-cross Abstract: Large language models today still make mistakes on multi-digit arithmetic when they do not have tools, and part of the reason is how numbers...
arXiv Machine Learning
Aug 4
CurveShift: Is Agent Progress Scalar? Separating Level from Shape
arXiv:2608. 00355v1 Announce Type: cross Abstract: Progress in large language models is often summarized using a single scalar measure, such as a time horizon, a latent ability estimate, or an aggregate benchmark score.
arXiv AI
Aug 11
The Transformer Revolution, Part 1: Dynamic Processing through Output-Weight Interconnections
arXiv:2608. 03921v2 Announce Type: replace Abstract: This paper offers a new interpretation of the Transformer during inference.
arXiv Machine Learning
1d ago
Represented Is Not Computed: A Causal Test of Candidate Algorithmic Intermediates in a Transformer
arXiv:2605. 22488v2 Announce Type: replace Abstract: Structured prompts require integrating components according to task-relevant relations.