1 citations · 2 across the 7 of their papers we have counts for
4 papers · 1 filter
Robot World Models Are Not Invariant to How the Actions Are Written
Ahmed Karim, Leon Chlon
A robot policy is trained with one of two action parameterizations: absolute joint targets, or deltas relative to the current state. The choice is a live engineering decision in ro…
Exact Finite Attention Responses From RoPE Derivatives
Julie Huang, Maggie Chlon, Gregory Gutin +1
We derive exact local responses for attention interventions, allowing candidate edits to be scored from a cached baseline and one backward pass. The starting point is the RoPE deri…
RoPE attention is an exact forward-pass gradient step with softmax intact
Julie Huang, Maggie Chlon, Leon Chlon
We derive an exact gradient-step representation of the RoPE-softmax forward pass. For every deterministic RoPE-softmax attention head with arbitrary affine projection weights, we c…
Attention Deficits in Language Models: Causal Explanations for Procedural Hallucinations
Ahmed Karim, Fatima Sheaib, Zein Khamis +3
Large language models can follow complex procedures yet fail at a seemingly trivial final step: reporting a value they themselves computed moments earlier. We study this phenomenon…