arXiv:2609.38785v1 Announce Type: new Abstract: How accurate must a numerical approximation be within a learning system? Primitive error alone cannot answer this question: errors of the same magnitud...
arXiv:2607. 09832v1 Announce Type: new Abstract: Long-tailed recognition methods often modify losses, margins, or representations to reduce the dominance of frequent classes.
arXiv:2606. 12171v1 Announce Type: cross Abstract: Knowledge Distillation (KD) and mixup have proven effective at inducing smoothness in class boundaries; KD captures inherent class relationships in probability distributions, and mixup enforces them through convex combinations of inputs.
The paper investigates how knowledge distillation from Vision Transformers to smaller CNNs can cause dimensional collapse in the student’s representation space. Using SVD and Shannon entropy, the authors show that cosine‑based distillation leads to a drastic reduction in effective rank, while adding an InfoNCE objective can double the rank but harms downstream accuracy due to signal dilution. They further demonstrate that a label‑aware contrastive objective (Supervised Contrastive distillation) can maintain or improve accuracy without unnecessary rank expansion, indicating that effective rank alone is not a reliable indicator of representation quality.
arXiv:2607. 23050v1 Announce Type: new Abstract: Neural scaling laws describe how loss decreases as models, data, and compute grow, but they do not answer a prior question: for a fixed task, what is the minimum model capacity required to solve it?
arXiv:2503. 08038v2 Announce Type: replace-cross Abstract: In this paper, we delve deeper into the Kullback-Leibler (KL) Divergence loss and mathematically prove that it is equivalent to the Decoupled Kullback-Leibler (DKL) Divergence loss that consists of (1) a weighted Mean Square Error (wMSE) loss and (2) a Cross-Entropy loss incorporating soft labels.
arXiv:2512. 24780v2 Announce Type: replace Abstract: Neural networks trained with standard objectives exhibit behaviors characteristic of probabilistic inference: soft clustering, prototype specialization, and Bayesian uncertainty tracking.
arXiv:2606. 26617v1 Announce Type: new Abstract: Scaling laws describe how learning performance varies with model size, data size, and compute.
arXiv:2604.15678v2 Announce Type: replace Abstract: Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) met...
arXiv:2602. 18849v2 Announce Type: replace-cross Abstract: We develop a sensitivity analysis for transformer attention in a geometry aligned with tokenwise computation.
arXiv:2609.10084v1 Announce Type: cross Abstract: Generalized zero-shot learning (GZSL) has emerged as an important paradigm for visual recognition systems that must generalize to classes that were n...
arXiv:2608. 01263v1 Announce Type: new Abstract: On-policy distillation (OPD) samples trajectories from the current student policy and minimizes token-level divergence between student and teacher next-token distributions at prefixes along those trajectories.