Skip to content

Author

Wei-Ran Wang

We have 6 of 39 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Oct 2026

Hallucination Reduction for LLM-Based Audio Understanding via Multimodal Direct Preference Optimization

Large Audio Language Models (LALMs) are prone to hallucinating and over-relying on text priors when simultaneously presented with audio and text inputs. To mitigate these hallucinations, we propose utilizing the multimodal Direct Preference Optimization (mDPO) objective, which forces the model to ground its generation...

Bebe Cosgrove, A. Grace, Wei-Ran Wang · 0 citations

Structured Latent Modeling for Supervised Multimodal Information Decomposition

This work introduces a framework that applies contrastive or masked objectives at intermediate layers, coupled with source-wise invertible normalizing flows and a supervised, low-rank latent variable model, offering a practical latent-variable lens for characterizing continuous multimodal interactions.

Wan-Ting Huang, Sanvesh Srivastava, Wei-Ran Wang · 0 citations
#natural language process... Preprint Sep 2026

Transcribe, Translate, and Optimize: Joint Reward Learning for Speech Translation

In LLM-based speech translation, transcription-based chain-of-thought (CoT) suffers from a mismatch between reference transcripts used in supervised fine-tuning (SFT) and model-generated transcripts at inference. To address this, we propose joint recognition and translation fine-tuning via group relative policy optimiz...

Yang-He Dong, Wan-Ting Huang, Wei-Ran Wang · 0 citations

Adaptive Perturbation Selection for Contrastive Audio Decoding

This work improves upon earlier prompt engineering by showing that a simple binary yes/no constraint reduces the model's tendency to falsely confirm absent audio features, and evaluates a diverse library of targeted audio perturbations and adaptively selecting the optimal negative branch for each task and example.

A. Grace, Zhou-Yuan Huo, Wei-Ran Wang · 2 citations · ⚡1
#artificial intelligence Preprint Aug 2025

No Data Wasted: A Semi-supervised Generative Model for Incomplete Multi-view Data Integration with Missing Labels

This work proposes a semi-supervised generative model that utilizes both labeled and unlabeled samples in a unified framework and maximizes the likelihood of unlabeled samples to learn a latent space shared with the IB on labeled data.

Yiyang Shen, Wei-Ran Wang · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.