Papers by Ali Veisi

1 papers
Context-aware Biases for Length Extrapolation (2025.emnlp-main)

Copied to clipboard

Challenge: Existing methods for Relative Positional Encoding (RPE) lack the capacity to adapt to different input contexts.
Approach: They propose an additive RPE method that learns token-specific, context-aware biases for each attention head in transformers by dynamically adjusting positional biase based on the input sequence.
Outcome: The proposed method significantly improves the extrapolation performance of existing RPE methods on the fineWeb-Edu-10B and WikiText-103 datasets.

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