2 papers
cs.LG2026
Beyond Variance: Prompt-Efficient RLVR via Rare-Event Amplification and Bidirectional Pairing
Yujuan Pang, Jiaxin Li, Xin Sheng +2
Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prior work shows RLVR works with few…
cs.CV2026
Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints
Chenxi Li, Xianggan Liu, Dake Shen +9
Despite the rapid progress of Large Vision-Language Models (LVLMs), the integration of visual modalities introduces new safety vulnerabilities that adversaries can exploit to elici…