9 papers
ImpactMat: Continuous Material Estimation for Inverse Impact Sound Rendering
Hyebin Cho, Bumsoo Kim, Joon Son Chung +1
Impact sound rendering synthesizes the sound produced when a 3D object is struck, but practical renderers often rely on fixed material presets such as wood, plastic, or steel. Thes…
Uncovering Ordinal-Matching Bias in Audio-Visual LLMs
Jihoo Jung, Youngjoon Jang, Hyebin Cho +2
This work aims to improve how audio-visual large language models (AVLLMs) associate speech with the correct visible speaker in multi-speaker scenes. We find that current AVLLMs fre…
OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents
Jihoo Jung, Suho Yoo, Jeongsoo Choi +5
Smart-home assistants are expected to handle diverse, realistic requests that arise in daily life. In such interactions, users often rely on the surrounding multimodal context-poin…
Tracing Audio Grounding and Answer Selection in Audio LLMs
Hyebin Cho, Suho Yoo, Jihoo Jung +1
Audio Large Language Models (Audio LLMs) have advanced in audio understanding, yet they can still predict the answer by reasoning from textual cues or linguistic priors rather than…
Out of Sight, Still in Mind: Token Compression for Omni-LLMs
Suho Yoo, Youngjoon Jang, Hyebin Cho +1
The goal of this paper is to reduce the input token cost of Omni-modal large language models (Omni-LLMs) at inference time. Omni-LLMs reason jointly over audio, video and text, but…
Acoustic Prompting via Stage-wise Modulation for Few-Shot Learning in Audio Language Models
Hyebin Cho, Jaehyuk Jang, Changick Kim +1
Audio-Language Models (ALMs) have shown remarkable success in zero-shot audio classification by aligning audio waveforms with text. Recent efforts to improve downstream performance…
Who Wins the Conflict? Mechanistic Interpretability of Text Bias in Audio LLMs
Hyebin Cho, Suho Yoo, Jaehyuk Jang +2
While Audio Large Language Models (Audio LLMs) excel at multimodal understanding, they suffer from text dominance, a bias where models favor text over acoustic evidence, potentiall…
Uncertainty-Guided Face Matting for Occlusion-Aware Face Transformation
Hyebin Cho, Jaehyup Lee
Face filters have become a key element of short-form video content, enabling a wide array of visual effects such as stylization and face swapping. However, their performance often…
Realistic Bokeh Effect Rendering on Mobile GPUs, Mobile AI & AIM 2022 challenge: Report
Andrey Ignatov, Radu Timofte, Jin Zhang +21
As mobile cameras with compact optics are unable to produce a strong bokeh effect, lots of interest is now devoted to deep learning-based solutions for this task. In this Mobile AI…