Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.
Linear mode connectivity in multitask and continual learning
4 Pith papers cite this work, alongside 13 external citations. Polarity classification is still indexing.
4
Pith papers citing it
13
external citations · external index
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 4roles
background 1polarities
background 1representative citing papers
FreeMOCA enables memory-free continual learning for malicious code analysis via adaptive layer-wise interpolation between warm-started task optima, outperforming baselines on EMBER and AZ benchmarks with up to 42% accuracy gains.
VC-Soup uses a cosine-similarity consistency metric to filter data, trains value-consistent policies, and applies linear merging with Pareto filtering to improve multi-value LLM alignment trade-offs.
Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.
citing papers explorer
-
Flat Channels to Infinity in Neural Loss Landscapes
Neural loss landscapes contain flat channels to infinity along which gradient flow leads pairs of neurons to implement gated linear units.
-
FreeMOCA: Memory-Free Continual Learning for Malicious Code Analysis
FreeMOCA enables memory-free continual learning for malicious code analysis via adaptive layer-wise interpolation between warm-started task optima, outperforming baselines on EMBER and AZ benchmarks with up to 42% accuracy gains.
-
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
VC-Soup uses a cosine-similarity consistency metric to filter data, trains value-consistent policies, and applies linear merging with Pareto filtering to improve multi-value LLM alignment trade-offs.
-
Reward-Free Code Alignment from Pretrained or Fine-Tuned LLM: Unpacking the Trade-offs for Code Generation
Empirical study on five LLMs finds pretrained-to-aligned paths yield bigger gains over baseline than finetuned-to-aligned paths, though absolute accuracy remains lower for pretrained starts.