Skip to content

Author

Matthieu Zimmer

We have 6 of 19 papers

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.

#artificial intelligence Preprint Oct 2026

A Safe Action Is Not Enough: Feasible-Future Decoding for Vision-Language-Action Policies

This work develops a selective finite-candidate approximation and establishes conditions for recovering the best retained viable candidate in a frozen vision-language-action policy, grounded in an exact policy-relative target yet requiring neither policy retraining nor online rollouts.

Tu Nguyen, Matthieu Zimmer, Vu Anh Vu et al. · 0 citations
#artificial intelligence Preprint Sep 2026

The Weakest Link: Distilling LLM Reasoning with Worst-Case Constrained Reinforcement Learning

Distilling the reasoning capabilities of large language models (LLMs) into smaller students is a central challenge for efficient deployment. Current approaches face a fundamental tension: optimizing purely for verifiable task rewards (e.g., via GRPO) leads to reward hacking, where students arrive at correct final answe...

Matthieu Zimmer, Xiao-Tong Ji, Tu Nguyen et al. · 0 citations
#machine learning Review Sep 2026

Tail-Influence Sampling for CVaR Policy Evaluation

A tail influence for each queryable conditional law that aggregates how its uncertainty affects CVaR across every Bellman reuse is derived, and an exact-grid regime in which tail- and mean-optimal allocations coincide is characterized.

P. Bourigault, Xiao-Tong Ji, Matthieu Zimmer et al. · 1 citation

Beam Search as Test-Time Self-Distillation via Counterfactual Contexts

Test-time self-distillation is proposed, a decoding-time method that extracts a steering signal from the self-distillation framework without any parameter updates, reward models, or training data, demonstrating that the self-distillation principle can be operationalized at inference time.

S. Tan, Xiao-Tong Ji, Rasul Tutunov et al. · 0 citations
#artificial intelligence Preprint Sep 2026

Composable Decoding on the Probability Simplex: Theory and Implementation

CompoSimplex is introduced, a library with configurable support rules, regularisation primitives, and simplex solvers for constructing and evaluating compositional decoders, and it is shown that compositions can realise trade-offs between single-sample quality, multi-sample quality, and diversity that are not attained...

Xiao-Tong Ji, Ahmed Khaled Khamis, Rasul Tutunov et al. · 0 citations

iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs

Controling how much and when teacher information is introduced improves specialisation while preserving broader capability is shown, and results show that controlling how much and when teacher information is introduced improves specialisation while preserving broader capability.

Ahmed Khaled Khamis, Xiao-Tong Ji, Hassan Jaber et al. · 1 citation

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.