22 citations · 24 across the 5 of their papers we have counts for
Showing 2024Show all
3 papers · 1 filter
cs.LG2024
Simulating Hard Attention Using Soft Attention
Andy Yang, Lena Strobl, David Chiang +1
We study conditions under which transformers using soft attention can simulate hard attention, that is, effectively focus all attention on a subset of positions. First, we examine…
cs.LO2024
Counting Like Transformers: Compiling Temporal Counting Logic Into Softmax Transformers
Andy Yang, David Chiang
Deriving formal bounds on the expressivity of transformers, as well as studying transformers that are constructed to implement known algorithms, are both effective methods for bett…
cs.FL2024★ 1 cited
Transformers as Transducers
Lena Strobl, Dana Angluin, David Chiang +2
We study the sequence-to-sequence mapping capacity of transformers by relating them to finite transducers, and find that they can express surprisingly large classes of transduction…