GL

Guillaume Lample

Language-model researcher and builder

Many Builders reference roster

Open and efficient language-model development, including model safeguards and agentic systems.

Many Builders reference → Safety & alignment coverage →

Writing and research by Guillaume Lample

2 supplied byline matches

These articles, papers and essays carry Guillaume Lample in the source-supplied author field. Verify the definitive byline and text at the original publisher.

HuggingFace Daily Papers

Shieldstral — open the original publisher

By Antonia Calvi, Avinash Sooriyarachchi, Giada Pistilli, Guillaume Lample, Maarten Buyl, Maximilian Augustin

We introduce Shieldstral, a 3B-parameter policy-adaptive multimodal safety classifier that matches or outperforms models nearly 7times its size on text safety benchmarks and sets a new state of the art on multimodal safety classification. Shieldstral formulates content moderation as a binary question-answering task. This simple formulation unifies diverse moderation tasks into a single yes/no problem, enabling heterogeneous safety datasets with divergent taxonomies to be consolidated under one t

Research Regulation
HuggingFace Daily Papers

Robostral Navigate — open the original publisher

By Arjun Majumdar, Avinash Sooriyarachchi, Benjamin Tibi, Chris Bamford, Elliot Chane-Sane, Guillaume Lample

Deploying navigation systems at scale requires a recipe that minimizes sensor assumptions, generalizes across robot embodiments, and trains efficiently. Yet, today's best systems depend on depth sensors, multi-camera rigs, or pre-built maps, limiting the hardware they support and increasing deployment cost. We introduce Robostral Navigate, an 8B vision-language model built around this scalability objective. The model consumes only a stream of monocular RGB images - the most ubiquitous sensor acr

Research Agents & autonomy