Jason Li

AAAI Conference 2026 Conference Paper

Advancing Safe Mechanical Ventilation Using Offline RL with Hybrid Actions and Clinically Aligned Rewards

• Muhammad Hamza Yousuf
• Jason Li
• Sahar Vahdati
• Raphael Theilen
• Jakob Wittenstein
• Jens Lehmann

Invasive mechanical ventilation (MV) is a life-sustaining therapy commonly used in the intensive care unit (ICU) for patients with severe and acute conditions. These patients frequently rely on MV for breathing. Given the high risk of death in such cases, optimal MV settings can reduce mortality, minimize ventilator-induced lung injury, shorten ICU stays, and ease the strain on healthcare resources. However, optimizing MV settings remains a complex and error-prone process due to patient-specific variability. While Offline Reinforcement Learning (RL) shows promise for optimizing MV settings, current methods struggle with the hybrid (continuous and discrete) nature of MV settings. Discretizing continuous settings leads to exponential growth in the action space, which limits the number of optimizable settings. Converting the predictions back to continuous can cause a distribution shift, compromising safety and performance. To address this challenge, in the IntelliLung project, we are developing an AI-based approach where we constrain the action space and employ factored action critics. This approach allows us to scale to six optimizable settings compared to 2-3 in previous studies. We adapt SOTA offline RL algorithms to operate directly on hybrid action spaces, avoiding the pitfalls of discretization. We also introduce a clinically grounded reward function based on ventilator-free days and physiological targets. Using multi-objective optimization for reward selection, we show that this leads to a more equitable consideration of all clinically relevant objectives. Notably, we develop a system in close collaboration with healthcare professionals that is aligned with real-world clinical objectives and designed with future deployment in mind.

AAAI Conference 2026 Conference Paper

UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing

• Lichen Ma
• Xiaolong Fu
• GaojingZhou
• Zipeng Guo
• Ting Zhu
• Yichun Liu
• Yu Shi
• Jason Li

With the rapid advancement of image generation, visual text editing using natural language instructions has received increasing attention. The main challenge of this task is to fully understand the instruction and reference image, and thus generate visual text that is style-consistent with the image. Previous methods often involve complex steps of specifying the text content and attributes, such as font size, color, and layout, without considering the stylistic consistency with the reference image. To address this, we propose UM-Text, a unified multimodal model for context understanding and visual text editing by natural language instructions. Specifically, we introduce a Visual Language Model (VLM) to process the instruction and reference image, so that the text content and layout can be elaborately designed according to the context information. To generate an accurate and harmonious visual text image, we further propose the UM Encoder to combine the embeddings of various condition information, where the combination is automatically configured by VLM according to the input instruction. During training, we propose a regional consistency loss to offer more effective supervision for glyph generation on both latent and RGB space, and design a tailored three-stage training strategy to further enhance model performance. In addition, we contribute the UM-DATA-200K, a large-scale visual text image dataset on diverse scenes for model training. Extensive qualitative and quantitative results on multiple public benchmarks demonstrate that our method achieves state-of-the-art performance.

AAAI Conference 2020 Conference Paper

Segment-Then-Rank: Non-Factoid Question Answering on Instructional Videos

• Kyungjae Lee
• Nan Duan
• Lei Ji
• Jason Li
• Seung-won Hwang

We study the problem of non-factoid QA on instructional videos. Existing work focuses either on visual or textual modality of video content, to find matching answers to the question. However, neither is flexible enough for our problem setting of non-factoid answers with varying lengths. Motivated by this, we propose a two-stage model: (a) multimodal segmentation of video into span candidates and (b) lengthadaptive ranking of the candidates to the question. First, for segmentation, we propose Segmenter for generating span candidates of diverse length, considering both textual and visual modality. Second, for ranking, we propose Ranker to score the candidates, dynamically combining the two models with complementary strength for both short and long spans respectively. Experimental result demonstrates that our model achieves state-of-the-art performance.

AAAI Conference 2014 Conference Paper

A Region-Based Model for Estimating Urban Air Pollution

• Arnaud Jutzeler
• Jason Li
• Boi Faltings

Air pollution has a direct impact to human health, and data-driven air quality models are useful for evaluating population exposure to air pollutants. In this paper, we propose a novel region-based Gaussian process model for estimating urban air pollution dispersion, and applied it to a large dataset of ultrafine particle (UFP) measurements collected from a network of sensors located on several trams in the city of Zurich. We show that compared to existing grid-based models, the regionbased model produces better predictions across aggregates of all time scales. The new model is appropriate for many useful user applications such as exposure assessment and anomaly detection.

AAAI Conference 2010 Conference Paper

In Defense of Large Qualitative Calculi

• Jason Li
• Jochen Renz