16 citations · 23 across the 16 of their papers we have counts for
17 papers
MoRE: Mixture of Reused Experts
Eric S. Qiu, Utku Umur Acikalin, Justin Lovelace +4
Mixture-of-Experts (MoE) architectures decouple model capacity from computational cost, yet incur high memory footprints as parameters grow linearly with the number of experts. Rec…
Optimize Your Sampling: Tuned Diffusion Sampling with Bayesian Optimization
Travis Zhang, Christian Belardi, Justin Lovelace +4
Sampling from a diffusion model typically requires many forward passes through a large neural network, making generation computationally expensive. While much work has focused on e…
Self-Augmenting Retrieval for Diffusion Language Models
Paul Jünger, Justin Lovelace, Linxi Zhao +2
Discrete diffusion language models generate text by iteratively denoising an entire response in parallel. At each step, they predict tentative tokens for every masked position, com…
Music Transcription with (Almost) No Supervision
Saebyeol Shin, Chao Wan, Zhenzhen Liu +4
Competitive music transcription models require large amounts of paired audio-score data, which is scarce due to collection costs, alignment difficulty, and copyright restrictions.…
Prescriptive Scaling Laws for Data Constrained Training
Justin Lovelace, Christian Belardi, Srivatsa Kundurthy +2
Training compute is increasingly outpacing the availability of high-quality data. This shifts the central challenge from optimal compute allocation to extracting maximum value from…
Adaptive Moments are Surprisingly Effective for Plug-and-Play Diffusion Sampling
Christian Belardi, Justin Lovelace, Kilian Q. Weinberger +1
Guided diffusion sampling relies on approximating often intractable likelihood scores, which introduces significant noise into the sampling dynamics. We propose using adaptive mome…
Stop-Think-AutoRegress: Language Modeling with Latent Diffusion Planning
Justin Lovelace, Christian Belardi, Sofian Zalouk +3
The Stop-Think-AutoRegress Language Diffusion Model (STAR-LDM) integrates latent diffusion planning with autoregressive generation. Unlike conventional autoregressive language mode…
SpeechOp: Inference-Time Task Composition for Generative Speech Processing
Justin Lovelace, Rithesh Kumar, Jiaqi Su +3
While generative Text-to-Speech (TTS) systems leverage vast ``in-the-wild" data to achieve remarkable success, speech-to-speech processing tasks like enhancement face data limitati…
Improving Multislice Electron Ptychography with a Generative Prior
Christian K. Belardi, Chia-Hao Lee, Yingheng Wang +4
Multislice electron ptychography (MEP) is an inverse imaging technique that computationally reconstructs the highest-resolution images of atomic crystal structures from diffraction…
Pre-training Limited Memory Language Models with Internal and External Knowledge
Linxi Zhao, Sofian Zalouk, Christian K. Belardi +7
Neural language models are black-boxes--both linguistic patterns and factual knowledge are distributed across billions of opaque parameters. This entangled encoding makes it diffic…
Sample-Efficient Diffusion for Text-To-Speech Synthesis
Justin Lovelace, Soham Ray, Kwangyoun Kim +2
This work introduces Sample-Efficient Speech Diffusion (SESD), an algorithm for effective speech synthesis in modest data regimes through latent diffusion. It is based on a novel d…
Diffusion Guided Language Modeling
Justin Lovelace, Varsha Kishore, Yiwei Chen +1
Current language models demonstrate remarkable proficiency in text generation. However, for many applications it is desirable to control attributes, such as sentiment, or toxicity,…
IncDSI: Incrementally Updatable Document Retrieval
Varsha Kishore, Chao Wan, Justin Lovelace +2
Differentiable Search Index is a recently proposed paradigm for document retrieval, that encodes information about a corpus of documents within the parameters of a neural network a…
Latent Diffusion for Language Generation
Justin Lovelace, Varsha Kishore, Chao Wan +2
Diffusion models have achieved great success in modeling continuous data modalities such as images, audio, and video, but have seen limited use in discrete domains such as language…
Robust Knowledge Graph Completion with Stacked Convolutions and a Student Re-Ranking Network
Justin Lovelace, Denis Newman-Griffis, Shikhar Vashishth +2
Knowledge Graph (KG) completion research usually focuses on densely connected benchmark datasets that are not representative of real KGs. We curate two KG datasets that include bio…
Dynamically Extracting Outcome-Specific Problem Lists from Clinical Notes with Guided Multi-Headed Attention
Justin Lovelace, Nathan C. Hurley, Adrian D. Haimovich +1
Problem lists are intended to provide clinicians with a relevant summary of patient medical issues and are embedded in many electronic health record systems. Despite their importan…
Explainable Prediction of Adverse Outcomes Using Clinical Notes
Justin R. Lovelace, Nathan C. Hurley, Adrian D. Haimovich +1
Clinical notes contain a large amount of clinically valuable information that is ignored in many clinical decision support systems due to the difficulty that comes with mining that…