More Like this

1. DSPO: Direct Score Preference Optimization for Diffusion Model Alignment.

   Zhu, Huaisheng; Xiao, Teng; Honavar, Vasant G (July 2025, International Conference on Learning Representations (ICLR 2025))

   Diffusion-based Text-to-Image (T2I) models have achieved impressive success in generating high-quality images from textual prompts. While large language models (LLMs) effectively leverage Direct Preference Optimization (DPO) for fine-tuning on human preference data without the need for reward models, diffusion models have not been extensively explored in this area. Current preference learning methods applied to T2I diffusion models immediately adapt existing techniques from LLMs. However, this direct adaptation introduces an estimated loss specific to T2I diffusion models. This estimation can potentially lead to suboptimal performance through our empirical results. In this work, we propose Direct Score Preference Optimization (DSPO), a novel algorithm that aligns the pretraining and fine-tuning objectives of diffusion models by leveraging score matching, the same objective used during pretraining. It introduces a new perspective on preference learning for diffusion models. Specifically, DSPO distills the score function of human-preferred image distributions into pretrained diffusion models, fine-tuning the model to generate outputs that align with human preferences. We theoretically show that DSPO shares the same optimization direction as reinforcement learning algorithms in diffusion models under certain conditions. Our experimental results demonstrate that DSPO outperforms preference learning baselines for T2I diffusion models in human preference evaluation tasks and enhances both visual appeal and prompt alignment of generated images. 

   more » « less
2. Token Imbalance Adaptation for Radiology Report Generation

   Wu, Yuexin; Huang, I-Chan; Huang, Xiaolei (August 2023, Proceedings of Machine Learning Research)

   Mortazavi, Bobak J; Sarker, Tasmie; Beam, Andrew; Ho, Joyce C (Ed.)

   Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. To solve the challenge, we propose the \textbf{T}oken \textbf{Im}balance Adapt\textbf{er} (\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation. 

   more » « less
3. Using Causal Analysis for Conceptual Deep Learning Explanation

   https://doi.org/10.1007/978-3-030-87199-4_49  

   Sumedha Singla, Stephen Wallace (September 2021, International Conference on Medical Image Computing and Computer-Assisted Intervention)

   null (Ed.)

   Model explainability is essential for the creation of trustworthy Machine Learning models in healthcare. An ideal explanation resembles the decision-making process of a domain expert and is expressed using concepts or terminology that is meaningful to the clinicians. To provide such explanation, we first associate the hidden units of the classifier to clinically relevant concepts. We take advantage of radiology reports accompanying the chest X-ray images to define concepts. We discover sparse associations between concepts and hidden units using a linear sparse logistic regression. To ensure that the identified units truly influence the classifier’s outcome, we adopt tools from Causal Inference literature and, more specifically, mediation analysis through counterfactual interventions. Finally, we construct a low-depth decision tree to translate all the discovered concepts into a straightforward decision rule, expressed to the radiologist. We evaluated our approach on a large chest x-ray dataset, where our model produces a global explanation consistent with clinical knowledge. 

   more » « less
4. Detecting Music Performance Errors with Transformers

   https://doi.org/10.1609/aaai.v39i22.34539  

   Chou, Benjamin Shiue_Hal; Jajal, Purvish; Eliopoulos, Nicholas John; Nadolsky, Tim; Yang, Cheng_Yun; Ravi, Nikita; Davis, James C; Yun, Kristen Yeon_Ji; Lu, Yung_Hsiang (April 2025, Proceedings of the AAAI Conference on Artificial Intelligence)

   Beginner musicians often struggle to identify specific errors in their performances, such as playing incorrect notes or rhythms. There are two limitations in existing tools for music error detection: (1) Existing approaches rely on automatic alignment; therefore, they are prone to errors caused by small deviations between alignment targets; (2) There is insufficient data to train music error detection models, resulting in over-reliance on heuristics. To address (1), we propose a novel transformer model, Polytune, that takes audio inputs and outputs annotated music scores. This model can be trained end-to-end to implicitly align and compare performance audio with music scores through latent space representations. To address (2), we present a novel data generation technique capable of creating large-scale synthetic music error datasets. Our approach achieves a 64.1% average Error Detection F1 score, improving upon prior work by 40 percentage points across 14 instruments. Additionally, our model can handle multiple instruments compared with existing transcription methods repurposed for music error detection. 

   more » « less
5. Joint Imbalance Adaptation for Radiology Report Generation

   https://doi.org/10.1007/s41666-025-00205-9  

   Li, Wang; Han, Guangzeng; Wu, Yuexin; Huang, I-Chan; Huang, Xiaolei (June 2025, Journal of Healthcare Informatics Research)

   Radiology report generation, translating radiological images into precise and clinically relevant description, may face the data imbalance challenge — medical tokens appear less frequently than regular tokens, and normal entries are significantly more than abnormal ones. However, very few studies consider the imbalance issues, not even with conjugate imbalance factors. In this study, we propose a Joint Imbalance Adaptation (JIMA) model to promote task robustness by leveraging token and label imbalance. We employ a hard-to-easy learning strategy that mitigates overfitting to frequent labels and tokens, thereby encouraging the model to focus more on infrequent labels and clinical tokens. JIMA presents notable improvements (16.75–50.50% on average) across evaluation metrics on IU X-ray and MIMIC-CXR datasets. Our ablation analysis and human evaluations show the improvements mainly come from enhancing performance on infrequent tokens and abnormal radiological entries, which can also lead to more clinically accurate reports. While data imbalance (e.g., infrequent tokens and abnormal labels) can lead to the underperformance of radiology report generation, our imbalance learning strategy opens promising directions on how to encounter data imbalance by reducing overfitting on frequent patterns and underfitting on infrequent patterns. 

   more » « less