Baluja, A. (2024). Text is not all you need: Multimodal prompting helps LLMs understand humor. In Proceedings of the 1st Workshop on Computational Humor (CHum) at COLING 2025.
Including TTS-generated audio in the prompt helps LLMs generate accurate pun explanations.
Baluja, S., Marwood, D., & Baluja, A. (2024). Making images from images: Tightly constrained parallel denoising. In Computer Vision – ECCV 2024 Workshops: AI for Visual Arts Workshop and Challenges.
Generate new images out of tiles from existing images by iteratively alternating between diffusion-based denoising and matching tiles between the generated and source images. Additionally, can generate two new images that can be transformed into eachother. Works in both latent and pixel space.
Ebert, T., Baluja, A., Hall, G. N., & Trosseille, C. (2024). Modeling of measurement uncertainties for X-ray radiograph analysis. [Conference presentation]. 25th Topical Conference on High Temperature Plasma Diagnostics.
Recover the range of possible 3D shapes of the capsules used in inertial-confinement-fusion as they implode, via gradient descent.
Baluja, A., Ebert, T., & Hall, G. N. (in preparation). Modeling measurement uncertainties for x-ray radiograph analysis using gradient descent with PEREGRINE. To be submitted to Computer Physics Communications.
By providing a library of simulations of common measurement errors/uncertainties and backpropagating through them, we can explicitly account for them.