Keanu Nichols

Hello! I am a PhD student in the Image and Video Computing (IVC) Group at Boston University. I am fortunate to be advised by Professor Bryan A. Plummer and Professor Deepti Ghadiyaram on topics related to orientation understanding for multi-modal models and diffusion based inpaintings for image manipulation localization.

Email / Scholar / Twitter / Hugging Face / Github / Resume

	Multi-axis Analysis of Image Manipulation Localization Keanu Nichols, Divya Appapogu, Giscard Biamby, Dina Bashkirova, Anna Rohrbach, Bryan A. Plummer Transactions on Machine Learning Research (TMLR), 2026 (Accepted) OpenReview / arXiv AUDITS is a benchmark of over 530,000 images for analyzing image manipulation localization across domain shifts, manipulation quality, type, and size.
	Seeing Isn't Orienting: A Cognitively Grounded Hierarchical Benchmark for Object Orientation in MLLMs Nazia Tasnim^, Keanu Nichols^, Yuting Yan, Nicholas Ikechukwu, Elva Zou, Deepti Ghadiyaram, Bryan A. Plummer European Conference on Computer Vision (ECCV), 2026 (Co-first author) ECCV paper / arXiv * Equal contribution. We introduce DORI, a benchmark for evaluating fine-grained object orientation understanding in multimodal large language models, including directional alignment, relative orientation, and rotational transformations.
	FuTCR: Future-Targeted Contrast and Repulsion for Continual Panoptic Segmentation Nicholas Ikechukwu^, Keanu Nichols^, Deepti Ghadiyaram, Bryan A. Plummer arXiv preprint, 2026 (Co-first author) arXiv / PDF * Equal contribution. FuTCR structures unlabeled regions through contrastive learning and known-class repulsion to improve continual panoptic segmentation as new categories are introduced.
	Estimating Deforestation using Machine Learning Algorithms Keanu Nichols, Patrick Hosein IDSTA2021, IEEE Estonia Section We present DORI (Discriminative Orientation Reasoning Intelligence) a dataset used to evaluate orientation reasoning for Multimodal large language models .
	Recommendations for Long-Term Profit Optimization Patrick Hosein, Inzamam Rahaman, Keanu Nichols, Kiran Maharaj ACM RecSys Workshop, 2019 (Best Paper) We present DORI (Discriminative Orientation Reasoning Intelligence) a dataset used to evaluate orientation reasoning for Multimodal large language models .

Feel free to steal this website's source code. Do not scrape the HTML from this page itself, as it includes analytics tags that you do not want on your own website — use the github code instead. Also, consider using Leonid Keselman's Jekyll fork of this page.