11 papers
Pointer-Augmented Autoregressive Generation of Patent Claims with Joint Topology and Content Decoding
Yongmin Yoo, Zhangkai Wu, Longbing Cao
Autoregressive decoders emit flat token sequences and cannot enforce hierarchical constraints across output segments, a limitation that becomes acute in patent claim generation, wh…
Heterogeneous Dependency Graph-Guided Attentionfor Patent Representation Learning
Yongmin Yoo, Qiongkai Xu, Zhangkai Wu +1
Pre-trained language models advance patent classification and retrieval via encoding claims as flat token sequences, yet overlooking the dependency hierarchy among claims. Incorpor…
DUET: Unified Dual-Space Emotion Control for Diffusion and Flow-Matching Driven Text-to-Speech
Xu Zhang, Longbing Cao, Zhangkai Wu
Diffusion and flow-matching based text-to-speech (TTS) models excel in naturalness but often lack explicit emotion control, as emotional signals remain entangled with speaker ident…
Learning Physiology-Informed Vocal Spectrotemporal Representations for Speech Emotion Recognition
Xu Zhang, Longbing Cao, Runze Yang +1
Speech emotion recognition (SER) is essential for humanoid robot tasks such as social robotic interactions and robotic psychological diagnosis, where interpretable and efficient mo…
An Efficient Algorithm for Thresholding Monte Carlo Tree Search
Shoma Nameki, Atsuyoshi Nakamura, Junpei Komiyama +1
We introduce the Thresholding Monte Carlo Tree Search problem, in which, given a tree and a threshold , a player must answer whether the root node value of $\math…
Nested AutoRegressive Models
Hongyu Wu, Xuhui Fan, Zhangkai Wu +1
AutoRegressive (AR) models have demonstrated competitive performance in image generation, achieving results comparable to those of diffusion models. However, their token-by-token i…