EgAS
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Boosting RL-Based Visual Reasoning with Selective Adversarial Entropy Intervention
arXiv:2512.10414v2 Announce Type: replace Abstract: Recently, reinforcement learning (RL) has become a common choice in enhancing the reasoning capabilities of vision-language models (VLMs). Considering existing RL-based finetuning methods, entropy intervention turns out to be an effective way to benefit exploratory ability, thereby improving policy performance. Notably, most existing studies intervene in entropy by simply controlling the update of specific tokens during policy optimization...