3 papers
cs.LG2026
On-policy Distillation with Verifiable Reward
Wenze Lin, Jiale Zhao, Xitai Jiang +5
Reinforcement Learning with Verifiable Rewards (RLVR) and on-policy distillation (OPD) have become two widely adopted paradigms for post-training large language models. However, RL…
cs.CV2025
One Object, Multiple Lies: A Benchmark for Cross-task Adversarial Attack on Unified Vision-Language Models
Jiale Zhao, Xinyang Jiang, Junyao Gao +2
Unified vision-language models(VLMs) have recently shown remarkable progress, enabling a single model to flexibly address diverse tasks through different instructions within a shar…
cs.CV2025
TRAIL: Transferable Robust Adversarial Images via Latent diffusion
Yuhao Xue, Zhifei Zhang, Xinyang Jiang +6
Adversarial attacks exploiting unrestricted natural perturbations present severe security risks to deep learning systems, yet their transferability across models remains limited du…