2 papers
cs.LG2026
Sparsity Moves Computation: How FFN Architecture Reshapes Attention in Small Transformers
Gabriel Smithline, Chris Mascioli
Architectural choices inside the Transformer feedforward network (FFN) block do not merely affect the block itself; they reshape the computations learned by the rest of the model.…
cs.GT2026
FAIRFORMER: A transformer architecture for discrete fair division
Chris Mascioli, Satyam Goyal, Mithun Chakraborty
We propose a deep neural network-based solution to the problem of allocating indivisible goods under additive subjective valuations without monetary transfers, trading off economic…