9 citations · 10 across the 8 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Representation Shattering in Transformers: A Synthetic Study with Knowledge Editing
Kento Nishi, Rahul Ramesh, Maya Okawa +3
Knowledge Editing (KE) algorithms alter models' weights to perform targeted updates to incorrect, outdated, or otherwise unwanted factual associations. However, recent work has sho…
cs.CV2024
Joint-Task Regularization for Partially Labeled Multi-Task Learning
Kento Nishi, Junsik Kim, Wanhua Li +1
Multi-task learning has become increasingly popular in the machine learning field, but its practicality is hindered by the need for large, labeled datasets. Most multi-task learnin…
cs.LG2024
Towards an Understanding of Stepwise Inference in Transformers: A Synthetic Graph Navigation Model
Mikail Khona, Maya Okawa, Jan Hula +5
Stepwise inference protocols, such as scratchpads and chain-of-thought, help language models solve complex problems by decomposing them into a sequence of simpler subproblems. Desp…