Author

Thomas Demeester

3 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Open access 2026

Hybrid Speculative Decoding in RAG: When Do the Pros Outweigh the Cons?

Speculative decoding emerged as a way to break the sequential autoregressive decoding of Large Language Models (LLMs), based on the idea that a lightweight model produces draft completions, to be efficiently verified in parallel by the actual LLM. Building on recent work where a hybrid speculative decoding strategy was...

Gianni van de Velde, Cédric Goemaere, François Remy et al. · IEEE Access · 0 citations

#artificial intelligence Preprint May 2026

Agent Collectives Should Not Detect Their Own Imposters: A Chess Case Study

It is found that merely warning the agents of potential imposter presence is not beneficial: it degrades decisions when no imposter is present, provokes reactions ranging from self-accusation to scapegoating, inflates token use, and reveals to the imposter how it was uncovered.

A. Mercier, Chris Develder, Thomas Demeester · 1 citation

#artificial intelligence Jan 2026

Hidden State Poisoning Attacks against Mamba-based Language Models

This paper studies the phenomenon whereby specific short input phrases induce a partial amnesia effect in state space models, by irreversibly overwriting information in their hidden states, referred to as a Hidden State Poisoning Attack (HiSPA).

A. Mercier, Chris Develder, Thomas Demeester · arXiv.org · 3 citations