34 citations · 63 across the 9 of their papers we have counts for
9 papers
Steered Generation via Gradient Descent on Sparse Features
Sumanta Bhattacharyya, Pedram Rooshenas
Large language models (LLMs) encode a diverse range of linguistic features within their latent representations, which can be harnessed to steer their output toward specific target…
LLM-Driven Feedback for Enhancing Conceptual Design Learning in Database Systems Courses
Sara Riazi, Pedram Rooshenas
The integration of LLM-generated feedback into educational settings has shown promise in enhancing student learning outcomes. This paper presents a novel LLM-driven system that pro…
Multimodal ELBO with Diffusion Decoders
Daniel Wesego, Pedram Rooshenas
Multimodal variational autoencoders have demonstrated their ability to learn the relationships between different modalities by mapping them into a latent representation. Their desi…
Score-Based Multimodal Autoencoder
Daniel Wesego, Pedram Rooshenas
Multimodal Variational Autoencoders (VAEs) represent a promising group of generative models that facilitate the construction of a tractable posterior within the latent space given…
Energy-Based Reranking: Improving Neural Machine Translation Using Energy-Based Models
Sumanta Bhattacharyya, Amirmohammad Rooshenas, Subhajit Naskar +3
The discrepancy between maximum likelihood estimation (MLE) and task measures such as BLEU score has been studied before for autoregressive neural machine translation (NMT) and res…
Differential Equation Units: Learning Functional Forms of Activation Functions from Data
MohamadAli Torkamani, Shiv Shankar, Amirmohammad Rooshenas +1
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential e…
Learning Compact Neural Networks Using Ordinary Differential Equations as Activation Functions
MohamadAli Torkamani, Phillip Wallis, Shiv Shankar +1
Most deep neural networks use simple, fixed activation functions, such as sigmoids or rectified linear units, regardless of domain or network structure. We introduce differential e…
Search-Guided, Lightly-supervised Training of Structured Prediction Energy Networks
Amirmohammad Rooshenas, Dongxu Zhang, Gopal Sharma +1
In structured output prediction tasks, labeling ground-truth training output is often expensive. However, for many tasks, even when the true output is unknown, we can evaluate pred…
The Libra Toolkit for Probabilistic Models
Daniel Lowd, Amirmohammad Rooshenas
The Libra Toolkit is a collection of algorithms for learning and inference with discrete probabilistic models, including Bayesian networks, Markov networks, dependency networks, an…