Multi-scale CIF (M-CIF), which performs multi-level alignment by integrating character and phoneme level supervision progressively distilled into subword representations, thereby enhancing robust acoustic-text alignment, is proposed.
Rui Mao, Xiangnan Ma, Qing Yang et al.· arXiv.org· 0 citations
Flow Continuous Trajectory Supervision (FlowCTS), which matches subsequent student and reference trajectories initialized from the same student-visited state to derive a temporally weighted velocity-matching upper bound and discretize it into practical objectives parameterized by the number of supervision steps.
Kaiyang Ye, Yuan Ge, Junxia Zhang et al.· arXiv.org· 0 citations
The method Syfer is introduced, a synthesizer-folding framework for multilingual multi-hop question answering that defers translation rather than applying it by default and attains competitive accuracy while striking a favourable balance between performance and computational cost.
Yilin Wang, Yuchun Fan, Weidong Bao et al.· 0 citations
This work proposes Dynamic Decomposition and Filtering for Multi-Hop Reasoning-Augmented Generation (D2F-ReAG), a novel paradigm that adaptively controls reasoning depth by judging the reliability of the root-level reasoning.
Jiaoyang Li, Junhao Ruan, Sheng-Wei Tang 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.