Josh Gardner
YOU?
Author Swipe
View article: OLMoASR: Open Models and Data for Training Robust Speech Recognition Models
OLMoASR: Open Models and Data for Training Robust Speech Recognition Models Open
Improvements in training data scale and quality have led to significant advances, yet its influence in speech recognition remains underexplored. In this paper, we present a large-scale dataset, OLMoASR-Pool, and series of models, OLMoASR, …
View article: Language Models Improve When Pretraining Data Matches Target Tasks
Language Models Improve When Pretraining Data Matches Target Tasks Open
Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine …
View article: Large Scale Transfer Learning for Tabular Data via Language Modeling
Large Scale Transfer Learning for Tabular Data via Language Modeling Open
Tabular data -- structured, heterogeneous, spreadsheet-style data with rows and columns -- is widely used in practice across many domains. However, while recent foundation models have reduced the need for developing task-specific datasets …
View article: DataComp-LM: In search of the next generation of training sets for language models
DataComp-LM: In search of the next generation of training sets for language models Open
We introduce DataComp for Language Models (DCLM), a testbed for controlled dataset experiments with the goal of improving language models. As part of DCLM, we provide a standardized corpus of 240T tokens extracted from Common Crawl, effect…
View article: Benchmarking Distribution Shift in Tabular Data with TableShift
Benchmarking Distribution Shift in Tabular Data with TableShift Open
Robustness to distribution shift has become a growing concern for text and image models as they transition from research subjects to deployment in the real world. However, high-quality benchmarks for distribution shift in tabular machine l…
View article: LLark: A Multimodal Instruction-Following Language Model for Music
LLark: A Multimodal Instruction-Following Language Model for Music Open
Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal …
View article: VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use
VisIT-Bench: A Benchmark for Vision-Language Instruction Following Inspired by Real-World Use Open
We introduce VisIT-Bench (Visual InsTruction Benchmark), a benchmark for evaluation of instruction-following vision-language models for real-world use. Our starting point is curating 70 'instruction families' that we envision instruction t…
View article: OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models
OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models Open
We introduce OpenFlamingo, a family of autoregressive vision-language models ranging from 3B to 9B parameters. OpenFlamingo is an ongoing effort to produce an open-source replication of DeepMind's Flamingo models. On seven vision-language …
View article: Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation
Subgroup Robustness Grows On Trees: An Empirical Baseline Investigation Open
Researchers have proposed many methods for fair and robust machine learning, but comprehensive empirical evaluation of their subgroup robustness is lacking. In this work, we address this gap in the context of tabular data, where sensitive …
View article: The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling
The Chamber Ensemble Generator: Limitless High-Quality MIR Data via Generative Modeling Open
Data is the lifeblood of modern machine learning systems, including for those in Music Information Retrieval (MIR). However, MIR has long been mired by small datasets and unreliable labels. In this work, we propose to break this bottleneck…
View article: Multi-instrument Music Synthesis with Spectrogram Diffusion
Multi-instrument Music Synthesis with Spectrogram Diffusion Open
An ideal music synthesizer should be both interactive and expressive, generating high-fidelity audio in realtime for arbitrary combinations of instruments and notes. Recent neural synthesizers have exhibited a tradeoff between domain-speci…
View article: MT3: Multi-Task Multitrack Music Transcription
MT3: Multi-Task Multitrack Music Transcription Open
Automatic Music Transcription (AMT), inferring musical notes from raw audio, is a challenging task at the core of music understanding. Unlike Automatic Speech Recognition (ASR), which typically focuses on the words of a single speaker, AMT…
View article: Engineering Design Of Musical Instruments As A Context For Math Physics And Technical Writing In A Freshman Learning Community Course
Engineering Design Of Musical Instruments As A Context For Math Physics And Technical Writing In A Freshman Learning Community Course Open
NOTE: The first page of text has been automatically extracted and included below in lieu of an abstract Engineering Design of Musical Instruments as a Context for Math, Physics and Technical Writing in a Freshman Learning Community Course …
View article: Driving with Data in the Motor City: Mining and Modeling Vehicle Fleet Maintenance Data
Driving with Data in the Motor City: Mining and Modeling Vehicle Fleet Maintenance Data Open
The City of Detroit maintains an active fleet of over 2500 vehicles, spending an annual average of over \$5 million on purchases and over \$7.7 million on maintenance. Modeling patterns and trends in this data is of particular importance t…
View article: MORF: A Framework for Predictive Modeling and Replication At Scale With Privacy-Restricted MOOC Data
MORF: A Framework for Predictive Modeling and Replication At Scale With Privacy-Restricted MOOC Data Open
Big data repositories from online learning platforms such as Massive Open Online Courses (MOOCs) represent an unprecedented opportunity to advance research on education at scale and impact a global population of learners. To date, such res…
View article: Beyond A/B Testing: Sequential Randomization for Developing Interventions in Scaled Digital Learning Environments
Beyond A/B Testing: Sequential Randomization for Developing Interventions in Scaled Digital Learning Environments Open
Randomized experiments ensure robust causal inference that are critical to effective learning analytics research and practice. However, traditional randomized experiments, like A/B tests, are limiting in large scale digital learning enviro…
View article: Evaluating Predictive Models of Student Success: Closing the Methodological Gap
Evaluating Predictive Models of Student Success: Closing the Methodological Gap Open
Model evaluation – the process of making inferences about the performance of predictive models – is a critical component of predictive model-ing research in learning analytics. In this work, we present an overview of the state-of-the-pract…
View article: Enabling End-To-End Machine Learning Replicability: A Case Study in Educational Data Mining
Enabling End-To-End Machine Learning Replicability: A Case Study in Educational Data Mining Open
The use of machine learning techniques has expanded in education research, driven by the rich data from digital learning environments and institutional data warehouses. However, replication of machine learned models in the domain of the le…
View article: Dropout Model Evaluation in MOOCs
Dropout Model Evaluation in MOOCs Open
The field of learning analytics needs to adopt a more rigorous approach for predictive model evaluation that matches the complex practice of model-building. In this work, we present a procedure to statistically test hypotheses about model …
View article: MORF: A Framework for MOOC Predictive Modeling and Replication At Scale.
MORF: A Framework for MOOC Predictive Modeling and Replication At Scale. Open
The MOOC Replication Framework (MORF) is a novel software system for feature extraction, model training/testing, and evaluation of predictive dropout models in Massive Open Online Courses (MOOCs). MORF makes large-scale replication of comp…
View article: Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit
Driving with Data: Modeling and Forecasting Vehicle Fleet Maintenance in Detroit Open
The City of Detroit maintains an active fleet of over 2500 vehicles, spending an annual average of over \$5 million on new vehicle purchases and over \$7.7 million on maintaining this fleet. Understanding the existence of patterns and tren…