2 citations · 2 across the 4 of their papers we have counts for
5 papers
On the Monitorability of Natural Language Autoencoders: Identification vs Discrimination
Kevin Yandoka Denamganaï
Natural Language Autoencoders (NLAs) are proposed as oversight tools for language models: an Activation Verbaliser (AV) writes an English explanation of an activation vector, and a…
xInv: Explainable Optimization of Inverse Problems
Sean Memery, Kevin Denamganai, Anna Kapron-King +1
Inverse problems are central to a wide range of fields, including healthcare, climate science, and agriculture. They involve the estimation of inputs, typically via iterative optim…
CueTip: An Interactive and Explainable Physics-aware Pool Assistant
Sean Memery, Kevin Denamganai, Jiaxin Zhang +3
We present an interactive and explainable automated coaching assistant called CueTip for a variant of pool/billiards. CueTip's novelty lies in its combination of three features: a…
On (Emergent) Systematic Generalisation and Compositionality in Visual Referential Games with Straight-Through Gumbel-Softmax Estimator
Kevin Denamganaï, James Alfred Walker
The drivers of compositionality in artificial languages that emerge when two (or more) agents play a non-visual referential game has been previously investigated using approaches b…
ReferentialGym: A Nomenclature and Framework for Language Emergence & Grounding in (Visual) Referential Games
Kevin Denamganaï, James Alfred Walker
Natural languages are powerful tools wielded by human beings to communicate information and co-operate towards common goals. Their values lie in some main properties like compositi…