activity
20242026
most citedMed-PMC: Medical Personalized Multi-modal Consultation with a Proactive Ask-First-Observe-Next Paradigm

1 citations · 1 across the 6 of their papers we have counts for

collaborators

7 papers

cs.CL2026

Cross-Modal Coreference Alignment: Enabling Reliable Information Transfer in Omni-LLMs

Hongcheng Liu, Yuhao Wang, Zhe Chen +5

Omni Large Language Models (Omni-LLMs) have demonstrated impressive capabilities in holistic multi-modal perception, yet they consistently falter in complex scenarios requiring syn…

cs.CL2025

VocalBench-zh: Decomposing and Benchmarking the Speech Conversational Abilities in Mandarin Context

Heyang Liu, Ziyang Cheng, Yuhao Wang +6

The development of multi-modal large language models (LLMs) leads to intelligent approaches capable of speech interactions. As one of the most widely spoken languages globally, Man…

cs.CL2025

When Seeing Is not Enough: Revealing the Limits of Active Reasoning in MLLMs

Hongcheng Liu, Pingjie Wang, Yuhao Wang +3

Multimodal large language models (MLLMs) have shown strong capabilities across a broad range of benchmarks. However, most existing evaluations focus on passive inference, where mod…

cs.CL2025

VocalBench-DF: A Benchmark for Evaluating Speech LLM Robustness to Disfluency

Hongcheng Liu, Yixuan Hou, Heyang Liu +3

While Speech Large Language Models (Speech-LLMs) show strong performance in many applications, their robustness is critically under-tested, especially to speech disfluency. Existin…

cs.AI2025

Bridging the Dynamic Perception Gap: Training-Free Draft Chain-of-Thought for Dynamic Multimodal Spatial Reasoning

Siqu Ou, Hongcheng Liu, Pingjie Wang +4

While chains-of-thought (CoT) have advanced complex reasoning in multimodal large language models (MLLMs), existing methods remain confined to text or static visual domains, often…

cs.CL2024

Drawing the Line: Enhancing Trustworthiness of MLLMs Through the Power of Refusal

Yuhao Wang, Zhiyuan Zhu, Heyang Liu +4

Multimodal large language models (MLLMs) excel at multimodal perception and understanding, yet their tendency to generate hallucinated or inaccurate responses undermines their trus…