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.
arXiv:2608. 11661v1 Announce Type: cross Abstract: A multiplicative dual-encoder network computes a real-valued output for a pair of inputs as the inner product of their separate encodings.
arXiv:2602. 24012v2 Announce Type: replace Abstract: Contrastive learning has become a cornerstone of modern representation learning, allowing training with massive unlabeled data for both task-specific and general (foundation) models.
DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches state-of-the-art accuracy on clean intrinsic-dimen...
SAGG: Sample-Adaptive Gradient Gating for Robust Multimodal Learning under Heterogeneous Corruption proposes a new method for handling sample-heterogeneous corruption in multimodal training. The authors prove that batch-level, sample-agnostic linear estimators with a shared modulation parameter inevitably incur bias, and that a sample-level all-or-nothing gating strategy is the only unbiased approach within a natural estimator class. SAGG implements a binary retain-or-discard decision per sample using an online feature-norm quality test and a truncation mechanism for variance control, and demonstrates convergence to clean-loss stationary points while achieving superior performance over ten existing methods on Kinetics-Sounds and UCF-101 under various corruption scenarios.
arXiv:2608.29702v1 Announce Type: new Abstract: A token-embedding table holds a hub of short rows near its origin, and we show that this cluster biases what nearest-neighbor intrinsic-dimension (ID)...
arXiv:2606. 16050v1 Announce Type: cross Abstract: Robust deep learning under heavy-tailed and impulsive noise remains challenging because conventional losses such as mean squared error (MSE) exhibit unbounded sensitivity to outliers.
arXiv:2609.37114v1 Announce Type: new Abstract: DANCo (Dimensionality from Angle and Norm Concentration) jointly calibrates nearest-neighbor distance and angular statistics and consistently reaches s...
arXiv:2604. 03146v2 Announce Type: replace-cross Abstract: We study high-dimensional convex empirical risk minimization (ERM) under general non-Gaussian data designs.
arXiv:2606. 23838v1 Announce Type: new Abstract: When two or more parameters or labels produce similar data, they are degenerate, or hard to distinguish.
The paper investigates the limits of the maximal coding rate reduction (MCR²) framework for out‑of‑distribution (OOD) generalisation. It shows that MCR² can lead to complete prediction failure under distribution shift, even when a perfectly stable feature is available, and that adding invariance principles from IRM or REx does not resolve this issue. The authors conclude that additional assumptions or learning principles are needed to guarantee stable OOD predictions with MCR².
arXiv:2608.24881v1 Announce Type: cross Abstract: Generative models are commonly ranked by Fr\'echet Inception Distance (FID) and Kernel Inception Distance (KID), yet FID's first-two-moment summary c...
arXiv:2601. 22784v2 Announce Type: replace-cross Abstract: We introduce a rank-statistic approximation of $f$-divergences that avoids explicit density-ratio estimation by working directly with the distribution of ranks.