The paper investigates the use of the squared norm of a whitened foundation‑model embedding as a training‑free likelihood surrogate. It shows that the apparent Gaussianity of whitened coordinates stems from the projection central limit theorem, not from a true joint Gaussian distribution, and that the norm is systematically over‑dispersed compared to a Gaussian reference. The authors explain that whitening reverses the encoder’s spectral hierarchy, concentrating norm contributions in near‑degenerate directions dominated by noise, and propose interpreting the squared norm as a Mahalanobis measure of semantic atypicality rather than a log‑likelihood.
By Mohammed Ahnouch, Lotfi Elaachak
arXiv:2607. 16811v3 Announce Type: replace Abstract: Drift detectors that work tend not to explain themselves, and drift detectors that explain themselves tend to fail in high dimension.
By Behnam Asadi
arXiv:2606. 27242v1 Announce Type: new Abstract: Training-free source selection for LLM families with shared vocabularies arises in scientific string domains such as SMILES, protein, and genomic sequences, where candidate corpora share a tokenizer but differ in prediction targets.
By John Sweeney
arXiv:2606. 06888v1 Announce Type: new Abstract: Classical scaling laws for language model pretraining balance model size against training dataset size under a fixed compute budget, assuming abundant data and a single pass over the corpus.
By Zhiwei Xu, Shihao Wu, Hanseul Cho, Wei Hu, Yixin Wang
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
The paper introduces Murmur2Vec, a lightweight, alignment‑free embedding that uses k‑mer counts hashed with MurmurHash to create a compact representation for biological sequences. It provides a full theoretical analysis, including bias/variance formulas, a Johnson–Lindenstrauss‑style concentration bound, and an excess‑risk bound that clarifies the trade‑off between hash‑table size and classifier performance. Empirically, Murmur2Vec matches or surpasses a fine‑tuned 650M‑parameter ESM‑2 protein language model across several classification tasks, including SARS‑CoV‑2 spike lineage and HIV‑1 Env subtype identification.
By Sarwan Ali, Taslim Murad, Imdadullah Khan, Safi Faizullah
arXiv:2607. 25271v1 Announce Type: cross Abstract: Classical compute-optimal scaling laws assume an unbounded supply of fresh pretraining data, yet pretraining is increasingly entering a regime in which compute grows faster than the availability of high-quality data.
By Tian Qin, Kimia Hamidieh, David Alvarez-Melis
arXiv:2606. 02765v1 Announce Type: cross Abstract: Model dimension ($d_{model}$) is a fundamental hyperparameter in transformer language models, yet its role in setting the geometric limits of feature representation remains under-explored.
By Alexander Guha
arXiv:2607. 16811v4 Announce Type: replace Abstract: Drift detectors that work tend not to explain themselves, and drift detectors that explain themselves tend to fail in high dimension.
By Behnam Asadi
arXiv:2608. 02412v1 Announce Type: new Abstract: Large language models (LLMs) have become the default tool for a remarkable range of tasks, yet they have had conspicuously little success at one of the most common machine learning workloads: predictive analytics over tabular data.
By Marta Garnelo, Wojciech M. Czarnecki
arXiv:2608. 10566v1 Announce Type: cross Abstract: How many directions does a neural representation use to encode a concept?
By Tingan Jin, Shuhang Dong, Haosong Li, Chung-Hsien Chou
arXiv:2609. 31181v1 Announce Type: new Abstract: Black-box model identification works by scoring a model's response to natural-language prompts.
By Nicol\'as Vera Z\'u\~niga