Vision-language models (VLMs) face compositional safety risks where harmful intent emerges from the interaction between visual and textual inputs. As mixture-of-experts (MoE) VLMs become increasingly common, recent work has explored various safety interventions, including prompting, supervised fine-tuning, and routing-...
Zi-Yuan Yang, Wen-Xuan Ding, Shang-Bin Feng et al.· 0 citations
It is established that principled and informed team selection is critical and strong model selection algorithms for assembling effective multi-LLM systems are presented.
Zong-Wan Cao, Zi-Yuan Yang, Shang-Bin Feng et al.· 0 citations
A pool of language models can collaborate and improve collectively by learning from one another's responses. These interactions depend on the instructions used during training. Existing methods typically sample instructions uniformly, even though their usefulness may change as the models improve: an instruction on whic...
Christina Hahn, Shang-Bin Feng, Dean Light et al.· 0 citations
Contextual Early Reward (CER), which predicts terminal reward through behavioral evidence in a trajectory prefix, provides an interpretable, efficient, and dense evaluation method for long-horizon coding agents.
Ji-Han Yao, Si-Han Zeng, Shang-Bin Feng et al.· 0 citations
Group-relative reinforcement learning (RL) relies on reward variation among sampled responses to estimate informative relative advantages. As language models become increasingly capable, existing training data can become reward-saturated: all sampled responses to the same problem might receive equally high rewards, whe...
Zi-Yuan Yang, Yike Wang, Shang-Bin Feng et al.· 0 citations
FLIP (FLipped Inference for Prompt reconstruction), a reference-free and rubric-free reward modeling approach that reformulates reward modeling through backward inference that enables reliable reward modeling in downscaled regimes where judgment methods fail, is proposed.
