AIConfPaper
← Search

Ruofan Liu

6 accepted papers

2026

DyaDiT: A Multi-Modal Diffusion Transformer for Socially Favorable Dyadic Gesture Generation

Yichen Peng, Jyun-Ting Song, Siyeol Jung, Ulsan National Institute of Science & Technology blank, Ruofan Liu, Haiyang Liu +5
CVPR 2026

Generating realistic conversational gestures are essential for achieving natural, socially engaging interactions with digital humans. However, existing methods typically map a single audio stream to a single speaker's motion, without considering social context or modeling the mutual dynamics between

Cited by 0Source ↗Scholar ↗
2026

TrainRef: Curating Data with Label Distribution and Minimal Reference for Accurate Prediction and Reliable Confidence

Murong Ma, Ruofan Liu, Yun Lin, Zhiyong Huang, Jin Song Dong
ICLR 2026poster

Practical classification requires both high predictive accuracy and reliable confidence for human-AI collaboration. Given that a high-quality dataset is expensive and sometimes impossible, learning with noisy labels (LNL) is of great importance. The state-of-the-art works propose many denoising appr…

Cited by 0Source ↗Scholar ↗
2025

From Pose to Muscle: Multimodal Learning for Piano Hand Muscle Electromyography

RUOFAN LIU, YICHEN PENG, Takanori Oku, Chen-Chieh Liao, Erwin Wu, Shinichi Furuya +1
NeurIPS 2025poster

Muscle coordination is fundamental when humans interact with the world. Reliable estimation of hand muscle engagement can serve as a source of internal feedback, supporting the development of embodied intelligence and the acquisition of dexterous skills. However, contemporary electromyography (EMG)…

Cited by 0Source ↗Scholar ↗
2022

Debugging and Explaining Metric Learning Approaches: An Influence Function Based Perspective

Ruofan Liu, Yun Lin, XIANGLIN YANG, Jin Song Dong
NeurIPS 2022accept

Deep metric learning (DML) learns a generalizable embedding space where the representations of semantically similar samples are closer. Despite achieving good performance, the state-of-the-art models still suffer from the generalization errors such as farther similar samples and closer dissimilar sa…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2022

DeepVisualInsight: Time-Travelling Visualization for Spatio-Temporal Causality of Deep Classification Training

Xianglin Yang, Yun Lin, Ruofan Liu, Zhenfeng He, Chao Wang, Jin Song Dong +1
AAAI 2022technical

Understanding how the predictions of deep learning models are formed during the training process is crucial to improve model performance and fix model defects, especially when we need to investigate nontrivial training strategies such as active learning, and track the root cause of unexpected traini…

Cited by 7Source ↗PDF ↗Scholar ↗
2022

Temporality Spatialization: A Scalable and Faithful Time-Travelling Visualization for Deep Classifier Training

Xianglin Yang, Yun Lin, Ruofan Liu, Jin Song Dong
IJCAI 2022poster

Time-travelling visualization answers how the predictions of a deep classifier are formed during the training. It visualizes in two or three dimensional space how the classification boundaries and sample embeddings are evolved during training. In this work, we propose TimeVis, a novel time-trave…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗