Profiles2022-2026
Benyou Wang
The Chinese University of Hong Kong
33Papers
18Last author
50Unique co-authors
0First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers33
- S2S-Arena: Evaluating Paralinguistic Instruction Following in Speech-to-Speech ModelsAuthor 8 of 9ACL 2026 · 17 citations
- EchoMind: An Interrelated Multi-level Benchmark for Evaluating Empathetic Speech Language ModelsAuthor 8 of 9ICLR 2026 · 13 citations
- Benchmarking LLMs on Authentic Cases from Medical JournalsAuthor 6 of 6ACL Findings 2026 · 1 citation
- Human or Machine? A Preliminary Turing Test for Speech-to-Speech InteractionAuthor 8 of 8ICLR 2026 · 1 citation
- ClinAlign: Scaling Healthcare Alignment from Clinician PreferenceAuthor 8 of 9ACL Findings 2026
- Cut Your Losses! Learning to Prune Paths Early for Efficient Parallel ReasoningAuthor 5 of 5ACL 2026
- OnePO: Direct One-stage Policy Optimization for SFT-free Domain AdaptationAuthor 4 of 4ICML 2026
- PrinciplismQA: A Philosophy-Grounded Approach to Assessing LLM-Human Clinical Medical Ethics AlignmentAuthor 7 of 8ACL Findings 2026
- TalkVid: A Large-Scale Diversified Dataset for Audio-Driven Talking Head SynthesisAuthor 15 of 15CVPR Findings 2026
- The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning ModelsAuthor 10 of 13NeurIPS 2025 · 33 citations
- Beyond Binary: Towards Fine-Grained LLM-Generated Text Detection via Role Recognition and Involvement MeasurementAuthor 4 of 5WWW 2025 · 20 citations
- Towards Medical Complex Reasoning with LLMs through Medical Verifiable ProblemsAuthor 7 of 7ACL Findings 2025 · 14 citations
- CoD, Towards an Interpretable Medical Agent using Chain of DiagnosisAuthor 7 of 7ACL Findings 2025 · 13 citations
- Soundwave: Less is More for Speech-Text Alignment in LLMsAuthor 5 of 6ACL 2025 · 11 citations
- Second Language (Arabic) Acquisition of LLMs via Progressive Vocabulary ExpansionAuthor 21 of 22ACL 2025 · 7 citations
- Both Text and Images Leaked! A Systematic Analysis of Data Contamination in Multimodal LLMAuthor 6 of 6EMNLP Findings 2025 · 1 citation
- RAG-Instruct: Boosting LLMs with Diverse Retrieval-Augmented InstructionsAuthor 6 of 6EMNLP 2025 · 1 citation
- DRBO: Mitigating Short Board Effect via Dynamic Reward Balancing in Multi-reward LLM OptimizationAuthor 7 of 7EMNLP Findings 2025
- Efficiently Democratizing Medical LLMs for 50 Languages via a Mixture of Language Family ExpertsAuthor 6 of 6ICLR 2025
- Exploring Compositional Generalization of Multimodal LLMs for Medical ImagingAuthor 9 of 9ACL 2025
- Unlocking LLMs' Self-Improvement Capacity with Autonomous Learning for Domain AdaptationAuthor 6 of 6ACL Findings 2025
- Towards Injecting Medical Visual Knowledge into Multimodal LLMs at ScaleAuthor 12 of 12EMNLP 2024 · 43 citations
- Humans or LLMs as the Judge? A Study on Judgement BiasAuthor 5 of 5EMNLP 2024 · 37 citations
- Alignment at Pre-training! Towards Native Alignment for Arabic LLMsAuthor 11 of 12NeurIPS 2024 · 19 citations
- VLFeedback: A Large-Scale AI Feedback Dataset for Large Vision-Language Models AlignmentAuthor 8 of 10EMNLP 2024 · 9 citations
- Rethinking the Uniformity Metric in Self-Supervised LearningAuthor 4 of 4ICLR 2024 · 3 citations
- HuatuoGPT, Towards Taming Language Model to Be a DoctorAuthor 12 of 13EMNLP Findings 2023 · 216 citations
- Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing BiasAuthor 5 of 9NeurIPS 2023 · 114 citations
- Towards Unifying Medical Vision-and-Language Pre-training via Soft PromptsAuthor 3 of 5ICCV 2023 · 50 citations
- Effective Open Intent Classification with K-center Contrastive Learning and Adjustable Decision BoundaryAuthor 6 of 7AAAI 2023 · 11 citations
Showing the 30 most recent indexed papers.
