ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
针对视觉-语言导航中不确定性估计的问题，提出了一种基于序列归一化的保形预测方法（ENCP），通过调整非一致性分数来提高预测准确性。
0 citationsRead paper
Selected work
Representative Papers
Sense Representations Are Inducible Interfaces
This work addresses the limitation of existing pretrained language models, which require explicit incorporation of lexical semantic structures during training to obtain interpretable word sense representations, thereby compromising their generalizability. The authors propose ACROS, a novel method that leverages a gated residual addition mechanism to dynamically induce a unified, explicit word sense pathway within a frozen pretrained decoder—eliminating the need for fine-tuning while supporting diverse semantic tasks. ACROS is the first approach to demonstrate effective word sense disambiguation, lexically guided generation, and cross-lingual alignment without modifying model weights. Evaluated on SmolLM2-360M, it achieves a zero-shot word sense disambiguation F1 score of 64.95, approximately 90% lexical guidance recovery rate, and strong cross-lingual adaptation performance on the four-language SENSIA benchmark with R@1 = 0.988 and PPL = 7.94.
0 citationsRead paper
Recent publications
Latest Papers
ENCP: Episode-Normalized Conformal Prediction for Vision-and-Language Navigation
针对视觉-语言导航中不确定性估计的问题，提出了一种基于序列归一化的保形预测方法（ENCP），通过调整非一致性分数来提高预测准确性。
0 citationsRead paper
Sense Representations Are Inducible Interfaces
This work addresses the limitation of existing pretrained language models, which require explicit incorporation of lexical semantic structures during training to obtain interpretable word sense representations, thereby compromising their generalizability. The authors propose ACROS, a novel method that leverages a gated residual addition mechanism to dynamically induce a unified, explicit word sense pathway within a frozen pretrained decoder—eliminating the need for fine-tuning while supporting diverse semantic tasks. ACROS is the first approach to demonstrate effective word sense disambiguation, lexically guided generation, and cross-lingual alignment without modifying model weights. Evaluated on SmolLM2-360M, it achieves a zero-shot word sense disambiguation F1 score of 64.95, approximately 90% lexical guidance recovery rate, and strong cross-lingual adaptation performance on the four-language SENSIA benchmark with R@1 = 0.988 and PPL = 7.94.
0 citationsRead paper