6 papers
FDIR: Harmonizing Fidelity and Human-Machine Preference in Lossy Compression Image Restoration
Kuan-Yen Chen, Fang-Yi Su, Philip Chikontwe +1
Image restoration quality can be evaluated along three complementary facets: pixel-level fidelity, human perception, and downstream machine preference. However, existing lossy comp…
The Self-Correction Illusion: Role Relabeling Gates Explicit Error Flagging in Large Language Models
Kuan-Yen Chen, Fang-Yi Su, Shih-Yen Lin +2
Recent works show that LLM agents struggle to correct errors in their own reasoning traces, despite their ability to correct errors from external sources. We ask whether this refle…
Beyond What to Select: A Plug-and-play Oscillatory Data-Volume Scheduling for Efficient Model Training
Suorong Yang, Hanqi Zhu, Hai Gan +4
Data selection accelerates training by identifying representative training data while preserving model performance. However, existing methods mainly focus on designing sample-impor…
Data Agent: Learning to Select Data via End-to-End Dynamic Optimization
Suorong Yang, Fangjian Su, Hai Gan +5
Dynamic Data selection aims to accelerate training by prioritizing informative samples during online training. However, existing methods typically rely on task-specific handcrafted…
SGD-Mix: Enhancing Domain-Specific Image Classification with Label-Preserving Data Augmentation
Yixuan Dong, Fang-Yi Su, Jung-Hsien Chiang
Data augmentation for domain-specific image classification tasks often struggles to simultaneously address diversity, faithfulness, and label clarity of generated data, leading to…
Debiasing Diffusion Model: Enhancing Fairness through Latent Representation Learning in Stable Diffusion Model
Lin-Chun Huang, Ching Chieh Tsao, Fang-Yi Su +1
Image generative models, particularly diffusion-based models, have surged in popularity due to their remarkable ability to synthesize highly realistic images. However, since these…