4 papers
Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families
Abdulrahman Alabdulkareem, Irene Tenison, Yang Zhang +3
LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to…
ArtifactArena: Evaluating Models by What They Build in the Physical World
Kushagra Tiwary, Kushagra Tiwary*, David Mayo* +7
To evaluate the frontier, we must measure models not by what they say, but by what they can engineer and build in grounded physical environments. We introduce ArtifactArena, an ope…
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
David Mayo, Christopher Wang, Asa Harbin +4
When evaluating stimuli reconstruction results it is tempting to assume that higher fidelity text and image generation is due to an improved understanding of the brain or more powe…
Information-Theoretic Lower Bounds for Zero-Order Stochastic Gradient Estimation
Abdulrahman Alabdulkareem, Jean Honorio
In this paper we analyze the necessary number of samples to estimate the gradient of any multidimensional smooth (possibly non-convex) function in a zero-order stochastic oracle mo…