TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval
本文提出TAME，通过引入时间感知混合专家层和跨帧信息聚合机制来改进文本-视频检索中的时间建模问题。
0 citationsRead paper
Selected work
Representative Papers
HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training
To address semantic ambiguity in Korean large language models (LLMs) arising from homophonic Sino-Korean words indistinguishable in Hangul orthography, this paper proposes HanjaBridge: a continual pretraining method that introduces candidate Hanja characters as explicit semantic anchors, preserving all plausible Hanja forms for homographic words to strengthen contextual disambiguation. To mitigate catastrophic forgetting, token-level knowledge distillation is employed. The approach enables zero-overhead deployment—no inference-time modifications or auxiliary modules are required. On the KoBALT benchmark, HanjaBridge achieves a 21% relative improvement, significantly enhancing Korean language understanding. Moreover, it fosters cross-lingual semantic alignment between Korean and Chinese, demonstrating strong transferability. The core innovation lies in leveraging Hanja as a lightweight, interpretable semantic enhancement signal—effectively balancing model performance, training stability, and deployment efficiency.
0 citationsRead paper
Recent publications
Latest Papers
TAME: Temporal-Aware Mixture-of-Experts for Text-Video Retrieval
本文提出TAME，通过引入时间感知混合专家层和跨帧信息聚合机制来改进文本-视频检索中的时间建模问题。
0 citationsRead paper
HanjaBridge: Resolving Semantic Ambiguity in Korean LLMs via Hanja-Augmented Pre-Training
To address semantic ambiguity in Korean large language models (LLMs) arising from homophonic Sino-Korean words indistinguishable in Hangul orthography, this paper proposes HanjaBridge: a continual pretraining method that introduces candidate Hanja characters as explicit semantic anchors, preserving all plausible Hanja forms for homographic words to strengthen contextual disambiguation. To mitigate catastrophic forgetting, token-level knowledge distillation is employed. The approach enables zero-overhead deployment—no inference-time modifications or auxiliary modules are required. On the KoBALT benchmark, HanjaBridge achieves a 21% relative improvement, significantly enhancing Korean language understanding. Moreover, it fosters cross-lingual semantic alignment between Korean and Chinese, demonstrating strong transferability. The core innovation lies in leveraging Hanja as a lightweight, interpretable semantic enhancement signal—effectively balancing model performance, training stability, and deployment efficiency.
0 citationsRead paper