Bayesian Model Merging
Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to multi-task learning when data access or computational budget is limited. Existing methods, however, face two key limitations: (1) they overlook the valuable inductive bias of strong anchor models and estimate the merged weights from scratch, and (2) they rely on a shared hyperparameter setting across different modules of the network, lacking a globa
Record details
Published: 13 May 2026
Source: arXiv
Category: Research
Topics: Bias & fairness
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.
Revisiting Reinforcement Learning with Verifiable Rewards from a Contrastive Perspective
arXiv · 13 May 2026
Do Fair Models Reason Fairly? Counterfactual Explanation Consistency for Procedural Fairness in Credit Decisions
arXiv · 12 May 2026
Context Matters: Auditing Gender Bias in T2I Generation through Risk-Tiered Use-Case Profiles
arXiv · 13 May 2026
STAR: Semantic-Temporal Adaptive Representation Learning for Few-Shot Action Recognition
arXiv · 13 May 2026
Fair outputs, Biased Internals: Causal Potency and Asymmetry of Latent Bias in LLMs for High-Stakes Decisions
arXiv · 12 May 2026
Incentivizing Truthfulness and Collaborative Fairness in Bayesian Learning
arXiv · 12 May 2026
How to cite this record
ethics.ai (13 May 2026), “Bayesian Model Merging,” evidence record 4427, https://ethics.ai/record/4427 (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.