A Testable Certificate for Constant Collapse in Teacher-Guided VAEs
Posterior collapse in variational autoencoders is often diagnosed by its symptoms: a small KL term, a strong decoder, or weak use of the latent code. These signals are useful, but they do not define a collapse boundary. We study a concrete failure mode, input-independent constant collapse, and show that this case admits an exact threshold. For any fixed nonconstant teacher distribution \(T(\cdot\mid x)\), the best constant student is the dataset-average teacher distribution, and its alignment co
Record details
Published: 7 May 2026
Source: arXiv
Category: Research
Topics: Safety & alignment · Healthcare · Children & education
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains
arXiv · 19 May 2026
LLM-as-a-Judge in Healthcare: A Scoping Analysis of Applications, Methods, and Human Alignment
arXiv · 24 May 2026
Reasoning-targeted Jailbreak Attacks on Large Reasoning Models via Semantic Triggers and Psychological Framing
arXiv · 17 April 2026
Phoneme-Level Mispronunciation Screening in Polish-Speaking Children with an Explainable Assistant
arXiv · 23 June 2026
Composed Vision-Language Retrieval for Skin Cancer Case Search via Joint Alignment of Global and Local Representations
arXiv · 10 March 2026
Fine-Tuning, Retrieval-Augmented Generation, and Hybrid Large Language Models for Postoperative Decision Support: Comparative Analysis
JMIR (Journal of Medical Internet Research) · 14 July 2026
How to cite this record
ethics.ai (7 May 2026), “A Testable Certificate for Constant Collapse in Teacher-Guided VAEs,” evidence record 4857, https://ethics.ai/record/4857 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.