Heyang Liu

Orcid: 0009-0007-0402-1078

According to our database1, Heyang Liu authored at least 15 papers between 2018 and 2025.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2025
SOVA-Bench: Benchmarking the Speech Conversation Ability for LLM-based Voice Assistant.
CoRR, June, 2025

VocalBench: Benchmarking the Vocal Conversational Abilities for Speech Interaction Models.
CoRR, May, 2025

VocalNet: Speech LLM with Multi-Token Prediction for Faster and High-Quality Generation.
CoRR, April, 2025

2024
Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal.
CoRR, 2024

Med-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm.
CoRR, 2024

Decoding Linguistic Representations of Human Brain.
CoRR, 2024

Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models.
CoRR, 2024

M<sup>3</sup>AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset.
CoRR, 2024

Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview.
CoRR, 2024

Towards an End-to-End Framework for Invasive Brain Signal Decoding with Large Language Models.
Proceedings of the 25th Annual Conference of the International Speech Communication Association, 2024

Post-decoder Biasing for End-to-End Speech Recognition of Multi-turn Medical Interview.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

MM-SAP: A Comprehensive Benchmark for Assessing Self-Awareness of Multimodal Large Language Models in Perception.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

M³AV: A Multimodal, Multigenre, and Multipurpose Audio-Visual Academic Lecture Dataset.
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2024

2023
LibriSQA: Advancing Free-form and Open-ended Spoken Question Answering with a Novel Dataset and Framework.
CoRR, 2023

2018
New Words Discovery Method Based On Word Segmentation Result.
Proceedings of the 17th IEEE/ACIS International Conference on Computer and Information Science, 2018


  Loading...