8 papers
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 blindly favor text over acoustic evidence, ca…
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…
Multimodal Self-Attention Network with Temporal Alignment for Audio-Visual Emotion Recognition
Inyong Koo, yeeun Seong, Minseok Son +2
Audio-visual emotion recognition (AVER) methods typically fuse utterance-level features, and even frame-level attention models seldom address the frame-rate mismatch across modalit…
Towards Efficient Vision State Space Models via Token Merging
Jinyoung Park, Minseok Son, Changick Kim
State Space Models (SSMs) have emerged as powerful architectures in computer vision, yet improving their computational efficiency remains crucial for practical and scalable deploym…
Don't Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models
Sangmin Woo, Donguk Kim, Jaehyuk Jang +2
Large Vision Language Models (LVLMs) demonstrate strong capabilities in visual understanding and description, yet often suffer from hallucinations, attributing incorrect or mislead…
Difficulty-aware Balancing Margin Loss for Long-tailed Recognition
Minseok Son, Inyong Koo, Jinyoung Park +1
When trained with severely imbalanced data, deep neural networks often struggle to accurately recognize classes with only a few samples. Previous studies in long-tailed recognition…