collaborators

11 papers

cs.SD2026

STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity

Sitong Cheng, Weizhen Bian, Songjun Cao +9

Speech-to-speech translation (S2ST) should preserve not only lexical meaning, but also expressive attributes: emotion, scenario style (e.g., news reporting vs. dramatic dialogue),…

cs.AI2026

MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning

Wanshi Xu, Haokun Zhao, Haidong Yuan +2

Chain-of-Thought (CoT) reasoning has extended from purely linguistic domains to multimodal scenarios; however, existing approaches often treat visual inputs as homogeneous or auxil…

cs.SD2026

Diffusion Reconstruction towards Generalizable Audio Deepfake Detection

Bo Cheng, Songjun Cao, Xiaoming Zhang +3

Achieving robust generalization against unseen attacks remains a challenge in Audio Deepfake Detection (ADD), driven by the rapid evolution of generative models. To address this, w…

cs.CL2026

Controllable Spoken Dialogue Generation: An LLM-Driven Grading System for K-12 Non-Native English Learners

Haidong Yuan, Haokun Zhao, Wanshi Xu +4

Large language models (LLMs) often fail to meet the pedagogical needs of K-12 English learners in non-native contexts due to a proficiency mismatch. To address this widespread chal…

cs.AI2026

Thinking with Constructions: A Benchmark and Policy Optimization for Visual-Text Interleaved Geometric Reasoning

Haokun Zhao, Wanshi Xu, Haidong Yuan +3

Geometric reasoning inherently requires "thinking with constructions" -- the dynamic manipulation of visual aids to bridge the gap between problem conditions and solutions. However…

cs.SD2026

Leveraging large multimodal models for audio-video deepfake detection: a pilot study

Songjun Cao, Yuqi Li, Yunpeng Luo +2

Audio-visual deepfake detection (AVD) is increasingly important as modern generators can fabricate convincing speech and video. Most current multimodal detectors are small, task-sp…