Frozen vision-language models gain candidate diversity without training by reusing decoder-layer blocks, lifting pass@9 by 6.58 points on average
The work introduces architectural sampling, a training-free method that generates candidates through distinct forward computations by reusing selected blocks of decoder layers in a frozen model; across five Qwen checkpoints and twelve multimodal benchmarks it improves pass@9 over standard-path temperature sampling by 6.58 percentage points on average at the same nine-candidate budget, with the strongest gains from reusing early layers, candidate-coverage improvement persisting under greedy decoding, lower lexical overlap among candidates, and higher accuracy when the candidates serve as rollouts for label-free test-time reinforcement learning.