Skip to main content

# Verifiable Rewards

2 related articles

Subscribe to updates

Hugging Face - Blog Oct 15, 2026
Apertus 1.5 folds images and audio into the text vocabulary: same architecture, 8B and 70B weights open under Apache 2.0
Switzerland's Apertus project released 1.5 versions of its 8B and 70B models, continuing pretraining from 1.0 to add image and audio understanding, an optional thinking mode, and a context window of 262,144 tokens. Multimodality arrives by early fusion: images and audio become discrete tokens placed in the same sequence as text, with no separate vision encoder, so the architecture is unchanged and training runs at text-only speed. The models read images and audio but generate only text, speech handling remains experimental, and the project says the release still trails frontier open-weight models.
Switzerland's Apertus project released 1.5 versions of its 8B and 70B models, continuing pretraining from 1.0 to add image and audio understanding, an optional thinking mode, and a context window of 262,144 tokens. Multimodality arrives by early fusion: images and audio become discrete tokens placed in the same sequence as text, with no separate vision encoder, so the architecture is unchanged and training runs at text-only speed. The models read images and audio but generate only text, speech handling remains experimental, and the project says the release still trails frontier open-weight models.
Apertus 1.5 Post-training Multimodal Reasoning Verifiable Rewards Instruction Following
arXiv Sep 26, 2026
EAGER boosts generative event extraction with verifiable-reward reinforcement learning, beating prompting, supervised fine-tuning, and prior RL baselines across seven benchmarks
The work presents EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards; its reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision, and across seven benchmark datasets it consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method.
The work presents EAGER, a reinforcement learning framework for generative event extraction that combines fine-grained verifiable rewards with Schema-Contrastive Advantage Estimation to alleviate advantage collapse under sparse binary rewards; its reward design explicitly targets structural validity, extraction accuracy, groundedness, coverage, over-generation, and span precision, and across seven benchmark datasets it consistently outperforms prompting, supervised fine-tuning, and prior reinforcement learning baselines, achieving a substantial improvement over the strongest prior method.
German Research Centre for Artificial Intelligence Carl von Ossietzky Universität Oldenburg
Omar Adjali（First author）
EAGER Event Extraction Reinforcement Learning Verifiable Rewards Schema-Contrastive Advantage Estimation

You’re all caught up