New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
Note on a Method for Calculating Corrected Sums of Squares and Products
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
citation-role summary
method 2
background 1
citation-polarity summary
verdicts
UNVERDICTED 4representative citing papers
Adaptive multi-criteria scoring with online logistic regression for Benders subproblem selection yields statistically significant runtime and integral improvements on 135 survivable network design instances.
TOPPO reformulates PPO with critic balancing to address gradient ill-conditioning in multi-task RL and reports stronger mean and tail performance than SAC baselines on Meta-World+ using fewer parameters and steps.
An enhanced octree S^3 algorithm reduces CFD mesh cells 35-95% across three test cases while preserving dominant dynamics for efficient post-processing.
citing papers explorer
-
Model Merging: Foundations and Algorithms
New cycle-consistent optimization, task vector theory, singular vector decompositions, adaptive routing, and efficient evolutionary search provide foundations for merging neural network weights across tasks.
-
Adaptive Subproblem Selection in Benders Decomposition for Survivable Network Design Problems
Adaptive multi-criteria scoring with online logistic regression for Benders subproblem selection yields statistically significant runtime and integral improvements on 135 survivable network design instances.
-
TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing
TOPPO reformulates PPO with critic balancing to address gradient ill-conditioning in multi-task RL and reports stronger mean and tail performance than SAC baselines on Meta-World+ using fewer parameters and steps.
-
An octree-based sampling algorithm for analyzing big simulation data
An enhanced octree S^3 algorithm reduces CFD mesh cells 35-95% across three test cases while preserving dominant dynamics for efficient post-processing.