Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can degrade capabilities already present in the base model. KL regularization is widely used to mitigate such forgetting by constraining policy drift toward a reference model. H...
Li Wang, Xiaodong Lu, Xiaohan Wang et al.· 0 citations
To achieve effective, stealthy, and persistent control, TrojanWorld combines Decision-Reflective Induction to steer trigger-conditioned imagination toward attacker-specified actions using decision feedback, Clean Behavior Anchoring to preserve trigger-free predictive and behavioral fidelity, and Causal Propagation to s...
Wen-Kai Huang, Si-Yuan Liang, Gaolei Li et al.· 0 citations
The introduction of MM-BrowseComp, a novel benchmark comprising 400 challenging, hand-crafted questions designed to evaluate multimodal retrieval and reasoning capabilities, is introduced, establishing MM-BrowseComp as a rigorous new standard for the field.
Shilong Li, Xingyuan Bu, Wenjie Wang et al.· arXiv.org· 37 citations· ⚡7
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
