← Back to all news
arXiv AI By Saurabh Rai, Sanmay Ganguly

What the Primary Lund Plane Omits: A Model-Stitching Diagnosis of a Jet-Tagger Representation Gap

Read the original on arXiv AI →

The study investigates why Lund‑plane and Particle Transformer (ParT) jet taggers can perform differently by using model stitching to isolate representation from computation. By linking frozen early layers of one network to frozen late layers of another, the authors show that a known deficit in the primary Lund representation is purely representational, not computational, and that this gap is invisible in AUC but appears in background rejection at low signal efficiency. Rebuilding the representation on the full Cambridge/Aachen declustering tree largely closes the gap, revealing that the primary branch carries most of the discriminative power while secondary splittings mainly make the representation learnable.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

Related stories

arXiv Machine Learning
Sep 29

The Residual Stream's Effective Depth

The paper introduces effective depth (Deff), a scalar diagnostic that treats a transformer’s layer‑wise residual stream as a discrete‑time process and measures how representation similarity decays with layer distance. Across sixteen decoder‑only language models, Deff reveals that most models exhibit a lower similarity decay than the closed‑form reference, indicating correlated residual updates rather than unused depth. The study also shows that this effect is robust to various controls and persists early in training, suggesting Deff is a global accumulated‑state diagnostic rather than a capability score.

By Barak Gahtan, Ido Galil, Alex M. Bronstein
llmsefficiency
More like this →
arXiv Computation and Language
Sep 10

Through the Looking Glass: Directly Reading and Writing Transformers

The paper investigates how many transformer components influence a token prediction by measuring the absolute contribution of each unit and channel to the logit. It finds that thousands of components contribute to a single prediction, yet a small subset—often just dozens—carries the majority of the predictive mass. Across models ranging from 124 M to 7 B parameters, the proportion of the model involved in a prediction remains around one to three percent, independent of size, and the study demonstrates that specific components can be directly read and written to modify model behavior without additional training.

By Mark Oskin
llmsrag
More like this →
arXiv Machine Learning
5d ago

Combinatorial Residual Network: a decay-chain-aware classifier without explicit jet assignment

arXiv:2610. 40749v1 Announce Type: cross Abstract: Final states with several jets from the decays of heavy particles pose a combinatorial problem, since the jets must be assigned, at least implicitly, to their parent particles.

By John Alison, Patrick Bryant, Alejandro Gomez Espinosa, Christian Guinto-Brody, Aniket Khanal, Chuyuan Liu, Sindhu Murthy, Guanglei Zhao
llmsbenchmarks
More like this →