Papers with manifold learning

2 papers
MEPT: Mixture of Expert Prompt Tuning as a Manifold Mapper (2025.emnlp-main)

Copied to clipboard

Challenge: Empirical evaluations show that Mixture of Expert Prompt Tuning outperforms state-of-the-art parameter efficient baselines on SuperGLUE.
Approach: They propose a pretrain-then-fine-tune paradigm for manifold mapping using multiple prompt experts.
Outcome: Empirical results show that the proposed approach outperforms state-of-the-art methods on SuperGLUE while reducing activated prompts by 79.25%.
Pruning via Merging: Compressing LLMs via Manifold Alignment Based Layer Merging (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for parameter pruning fail to utilize the knowledge from pruned parameters.
Approach: They propose a method that uses manifold learning and the Information Bottleneck measure to merge similar layers to preserve model performance.
Outcome: The proposed method outperforms pruning methods on multiple datasets and LLMs with quantization and achieves substantial compression ratios.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations