Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks6 from public data
- Memory Limitations of Prompt Tuning in Transformers5
It is rigorously demonstrated that transformers inherently have limited memory, constraining the amount of information they can retain, regardless of the context size, which offers a fundamental understanding of the intrinsic limitations of transformer architectures, particularly their ability to handle long sequences.
- Varif.ai to Vary and Verify User-Driven Diversity in Scalable Image Generation4
This work proposes Varif.ai, a text-to-image and Large Language Models model that employs text-to-image and Large Language Models to iteratively generate a set of images and verifies if user-specified attributes have sufficient coverage, and vary existing or new attributes.
- Visual Explanations of Differentiable Greedy Model Predictions on the Influence Maximization Problem1
This work presents an end-to-end learning model, SGREEDYNN, for the selection of the most influential nodes in a social network, given a history of information diffusion, and observes that the method chooses more diverse and high-degree nodes compared to the classical training.
- How Many Different Outputs Can a Transformer Generate?–
It is proved that the maximal length of accessible sequences (those that the transformer can output for some prompt) grows linearly with the prompt length, and the linear coefficient relating prompt length to accessible sequence length admits a theoretical upper bound.
- –
- SketchXplain: Intuitive Visual Explanations of Image Classifiers with Sketches–
Evaluating on face expression recognition, modeling and user studies showed that SketchXplain supported quicker interpretation with more aligned visualizations than saliency maps or simple drawings, and found that SketchXplain more coherently visualized disease symptoms, better supporting lay diagnosis.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-11. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.