Published:
Imani was sponsored by the Cornell University Ann S. Bowers College of Computing and Information Science College of Diversity, Equity, and Inclusion to virtually attend the 2021 Grace Hopper Celebration of Women in Computing Conference. Imani was selected for this, in part, due to her community leadership as Events Chair of Underrepresented Minorities in Computing (URMC) at Cornell.
Published:
Imani was sponsored by the Cornell University Ann S. Bowers College of Computing and Information Science College of Diversity, Equity, and Inclusion to attend the 2022 CMD-IT/ACM Richard Tapia Celebration of Diversity in Computing Conference in Washington D.C. Imani was selected for this, in part, due to her community leadership as 2022 President of Underrepresented Minorities in Computing (URMC) at Cornell.
Published:
Throughout history and across the contemporary global sphere, religious practice, and ideology interweave themselves in the political and social fabric of human life. The Joseph E. Connolly ‘72 Memorial Prizes are awarded to undergraduates who have demonstrated exceptional scholarship at the intersection of religion and politics or society.
Published:
Imani was selected for Honorable Mention of the 2024 Computing Research Association’s (CRA) Outstanding Undergraduate Researcher Award (URA). This award commends recipients for their contributions to multiple research projects, several authored or coauthored multiple research papers, many presented their work at large-scale conferences, and others produced software artifacts that are now widely used. The nominee pool featured multiple nominations for students who successfully completed summer research or internship programs, and many students served their community as teaching assistants, tutors, and mentors.
Published:
This award was for an outstanding undergraduate honors thesis and academic record as an undergraduate within the Department of Literatures in English at Cornell University.
Published:
The objective of the Baggett Fellowships program is to provide intensive research training for post-baccalaureate students who wish to pursue a research career in the scientific study of language. Fellows will be exposed to a range of methods and tools for studying human language in the context of a collaborative research environment. Fellows will be fully engaged in the scientific investigation of fundamental questions about the human language capacity: How is linguistic knowledge represented in the mind? What types of computation are involved?
Published:
2D platformer game
Published:
3D music game
Published:
Travel blog
Published:
Study Abroad Program Recommendation App
Published:
Communications work at Cornell University
Published in Medium, 2021
Medium article introducing Cornell Bias Labs project team and bias in machine learning
Recommended citation: Cornell Data Science. (2021). "Bias in ML: An Introduction." Medium. https://cornell-data.medium.com/bias-in-ml-an-introduction-d74b8432ecf2
Published in Medium, 2022
Medium Article examining social biases in CLIP+ and DALLE-2
Recommended citation: Cornell Data Science. (2022). "How biased are text-to-image models?." Medium. 1(3). https://cornell-data.medium.com/how-biased-are-text-to-image-models-99e8fdb8c5ab
Published in Cornell University, Department of Literatures in English, 2024
This undergraduate honors thesis explores the effects of generative-AI literature on the future of the literary canon
Recommended citation: Finkley, Imani. (2024). "By AI: Authorship, Literature, and Large Language Models." Cornell University. 1(1). http://imanif.github.io/files/Finkley_HonorsThesis.pdf
Published:
Image translation, that is, to alter the style and content of a given image to match predefined objectives, is a novel technique for artists to achieve their artistic vision. Recent works in image-to-image translation introduce methods to generate photorealistic imagery from non-realistic domains (e.g. drawings, paintings, etc.). However, these models do not allow the user to select specific region(s) for transformation and control the style of generation through text while simulating a photorealistic style. In this project, we present a language-based image-to-image translation model that allows the user to perform object-level edits via semantic query texts. This model takes a sketched image, an instance segmentation mask of the various objects in the sketch, and their corresponding text descriptors as input to translate a sketched image into the photo-realistic domain through texture generation. We adapt existing image-to-image translation architecture along with a pre-trained text-image embedding model to encode text embeddings within an instance segmentation mask for controlled regional material appearance editing. Our method allows users to edit the object appearance, generating diverse outputs given the same input image. Our work automates architectural and product visualization by allowing users to control the modes in which the sketches and designs are presented in the photorealistic domain.
Published:
Presenting PyLAST, a PyTorch software library version of LAST (Google) that demonstrates the benefits of using weighted finite state algorithms for speech applications!
Published:
As part of the Theory Colloquiuim series hosted by the Department of Comparative Literature at Cornell University, Imani was invited to speak at one colloquia whose theme surrounded translation. Her presentation on a chapter of her undergraduate honors thesis, “By AI: Authorship, Literature, and Large Language Models,” examined how literature translates the self and human experience and then posing question of if and should we expect generative AI (ChatGPT, in particular) to do the same.
Published:
Imani presents her undergraduate honors thesis as part of the Spring Humanities Research Conference hosted by the Humanities Scholars Program at Cornell University. This thesis was awarded Summa Cum Luade by the Department of Literatures in English at Cornell.
Undergraduate course, Cornell University, Computer Science Department, 2022
Undergraduate Course, Cornell University, Information Science Department, 2024