In-Context Learning (ICL) enables pretrained LLMs to adapt to downstream tasks from a small set of input-output demonstrations, without parameter updates. Yet existing theory primarily explains ICL as identifying a latent task already represented in pretraining, leaving unclear whether ICL can succeed when either the i...
In-context learning (ICL) adapts frozen large multimodal models (LMMs) to new tasks from a few demonstrations (demos), but re-encodes them at every query, where each demo image adds up to hundreds of visual tokens. Demo-free methods remove this cost with a compact task state. However, they add it at locations searched...
An assistant that serves the same user over a long horizon has to answer from what that user has revealed: which preferences still hold, which were revised, and which constraints apply now. Retaining that information is not the same as acting on it, and the two are usually optimized as if they were. Keeping the informa...
Jing-Xuan Wu, Yuzhe Yang, Yi-Qiao Huang et al.· 0 citations
This work proposes Interactive-Policy Distillation (IPD), which applies adaptive teacher intervention to the student rollout and designs a dedicated fused inference engine that co-hosts both models in one serving instance with separate KV caches and instantiates the state machine model to distribute, collect, and proce...
Shu-Tong Wu, Xi-Wen Chen, B. Rappazzo et al.· 0 citations
This work proposes SAGE (Structural Admissibility-Guided Exploration), a unified framework that injects structural guidance to alleviate exploration bias and compounding bias in long-horizon reasoning and achieves up to an 8-fold improvement on the Andrews-Curtis problem.
Xin-Yue Zeng, Jia-Wei Zhang, Yu-Jun Yan et al.· 0 citations
This work introduces a two-stage keyword-perturbation method for hallucination detection and extends the same probabilistic framework to four hallucination regimes: knowledge deficit, wrong knowledge, context distraction, and unstable inference.
Xu-Han Tong, Hao-Yue Bai, Da-Wei Zhou et al.· 0 citations
A cheap density prior is introduced over natural protein activations and keeps only the candidates that remain typical under it, a training-free post-hoc step the authors call Mahalanobis filtering that improves both the property score and the structural plausibility of the sequences it keeps at negligible cost, withou...
Shuibai Zhang, Xin-Chi Liu, Fred Zhangzhi Peng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.