Photorealistic avatar videos decouple the appearance of a rendered face from the person who operates it, which makes conventional face recognition unsuitable for identifying the operator. Verifying the operator therefore requires representations of how a face moves that are insensitive to what the avatar looks like. We...
K. Ogata, Ryoya Yoshiyama, Kawachi Hodaka et al.· 0 citations
Class-conditional conformal prediction calibrates a separate score threshold for every class and therefore requires labelled calibration examples of every class. In long-tailed deployments these are exactly what is missing: rare classes are left with few or no held-out examples, and existing methods are either undefine...
One Octadion, N. Yudistira, Yuta Nakashima· 0 citations
A Japanese dataset for Aspect-based Sentiment Analysis (ABSA), annotated with both sentiment polarity and the emotional intensities for Plutchik’s eight emotions is constructed and it is demonstrated that multi-task learning, utilizing both word and sentence levels, can improve performance on difficult-to-estimate subj...
Kenta Hanafusa, Kota Manabe, Yuki Maeda et al.· International Conference on...· 0 citations
An automatic evaluation protocol based on temporal alignment metrics is defined, and it is found that an LLM-as-a-judge preference, a natural proxy for narrative quality, is unreliable for this task due to severe position bias.
K. Ogata, Zongshang Pang, Mayu Otani et al.· arXiv.org· 1 citation
This work introduces ANCHOR, an LLM-based supervisory framework that delivers evaluative feedback at multiple phases of self-evolution and aggregates reviewed signals into context for subsequent steps and shows that ANCHOR substantially improves safety performance while maintaining stable performance on the core capabi...
Dian-Xing Shi, Jun He, Junhao Chen et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
