Alexander M. Rush
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Alexander M. Rush has a total of 34 co-authors. Here are the top co-authors by number of shared publications:
- Justin T. Chiu
Cornell University, NYC, USA
2 shared publications - Minlan Yu
Harvard University, Cambridge, USA
2 shared publications - Binqian Yin
George Mason University, Fairfax, VA, USA
1 shared publication - Francis Y. Yan
University of Illinois Urbana-Champaign, Urbana, USA
1 shared publication - Gordon Wetzstein
Stanford University
1 shared publication - Guandao Yang
University of Texas at Austin, Austin, USA
1 shared publication
Latest Publications
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
MeshFlow: Mesh Generation with Equivariant Flow Matching
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessMeshFlow: Mesh Generation with Equivariant Flow Matching
- Open Access
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 952-958
Triton-Viz: Visualizing GPU Programming in AI Courses
GPU programming is a critical component in AI system courses, which is notoriously difficult to learn and teach, given its unique features such as massive parallelism and data movement across memory hierarchies. This paper presents Triton-Viz, an innovative visualization toolkit that helps students learn GPU programming using Triton, one of the most widely used programming languages to develop AI applications. Triton-Viz offers an intuitive interface with interactive visualizations of GPU operations from multiple perspectives, including parallelism, memory access, and performance metrics. By integrating into educational materials, Triton-Viz enhances hands-on learning and improves comprehension of GPU programming concepts and AI algorithms in real applications, as demonstrated in a study conducted with Computer Science students. The positive feedback from this study highlights the utility of Triton-Viz in educational settings and its potential to bridge the gap between the theoretical algorithm and practical implementations in AI courses.
- 12 February 2025
- Published by Association for Computing Machinery (ACM)
- p. 952-958
Open AccessTriton-Viz: Visualizing GPU Programming in AI Courses
GPU programming is a critical component in AI system courses, which is notoriously difficult to learn and teach, given its unique features such as massive parallelism and data movement across memory hierarchies. This paper presents Triton-Viz, an innovative visualization toolkit that helps students learn GPU programming using Triton, one of the most widely used programming languages to develop AI applications. Triton-Viz offers an intuitive interface with interactive visualizations of GPU operations from multiple perspectives, including parallelism, memory access, and performance metrics. By integrating into educational materials, Triton-Viz enhances hands-on learning and improves comprehension of GPU programming concepts and AI algorithms in real applications, as demonstrated in a study conducted with Computer Science students. The positive feedback from this study highlights the utility of Triton-Viz in educational settings and its potential to bridge the gap between the theoretical algorithm and practical implementations in AI courses.
- Top Cited PapersOpen Access
- 10 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 378-393
Teal: Learning-Accelerated Optimization of WAN Traffic Engineering
The rapid expansion of global cloud wide-area networks (WANs) has posed a challenge for commercial optimization engines to efficiently solve network traffic engineering (TE) problems at scale. Existing acceleration strategies decompose TE optimization into concurrent subproblems but realize limited parallelism due to an inherent tradeoff between run time and allocation performance. We present Teal, a learning-based TE algorithm that leverages the parallel processing power of GPUs to accelerate TE control. First, Teal designs a flow-centric graph neural network (GNN) to capture WAN connectivity and network flows, learning flow features as inputs to downstream allocation. Second, to reduce the problem scale and make learning tractable, Teal employs a multi-agent reinforcement learning (RL) algorithm to independently allocate each traffic demand while optimizing a central TE objective. Finally, Teal fine-tunes allocations with ADMM (Alternating Direction Method of Multipliers), a highly parallelizable optimization algorithm for reducing constraint violations such as overutilized links. We evaluate Teal using traffic matrices from Microsoft's WAN. On a large WAN topology with >1,700 nodes, Teal generates near-optimal flow allocations while running several orders of magnitude faster than the production optimization engine. Compared with other TE acceleration schemes, Teal satisfies 6--32% more traffic demand and yields 197--625× speedups.
- 10 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 378-393
Top Cited PapersOpen AccessTeal: Learning-Accelerated Optimization of WAN Traffic Engineering
The rapid expansion of global cloud wide-area networks (WANs) has posed a challenge for commercial optimization engines to efficiently solve network traffic engineering (TE) problems at scale. Existing acceleration strategies decompose TE optimization into concurrent subproblems but realize limited parallelism due to an inherent tradeoff between run time and allocation performance. We present Teal, a learning-based TE algorithm that leverages the parallel processing power of GPUs to accelerate TE control. First, Teal designs a flow-centric graph neural network (GNN) to capture WAN connectivity and network flows, learning flow features as inputs to downstream allocation. Second, to reduce the problem scale and make learning tractable, Teal employs a multi-agent reinforcement learning (RL) algorithm to independently allocate each traffic demand while optimizing a central TE objective. Finally, Teal fine-tunes allocations with ADMM (Alternating Direction Method of Multipliers), a highly parallelizable optimization algorithm for reducing constraint violations such as overutilized links. We evaluate Teal using traffic matrices from Microsoft's WAN. On a large WAN topology with >1,700 nodes, Teal generates near-optimal flow allocations while running several orders of magnitude faster than the production optimization engine. Compared with other TE acceleration schemes, Teal satisfies 6--32% more traffic demand and yields 197--625× speedups.
- Open Access
- 30 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Xatu
Traditional DDoS attack detection monitors volumetric traffic features to detect attack onset. To reduce false positives, such detection is often conservative---raising an alert only after a sustained period of observed anomalous behavior. However, contemporary attacks tend to be short, which combined with a long detection delay means that most of the attack still reaches and impacts the victim. We propose Xatu, a system that utilizes auxiliary signals to improve the accuracy and timeliness of existing DDoS detection systems. We explore two types of auxiliary signals, attack preparation signals and the history of prior attacks. These signals can be easily mined from existing traffic monitoring systems in many ISP networks. To leverage these auxiliary signals for attack detection, we propose a multi-timescale LSTM model, which derives both long-term and short-term patterns from diverse auxiliary signals. We then leverage survival analysis to quickly detect attacks when they occur while minimizing false positives and thus scrubbing costs. We evaluate Xatu on traffic from a large ISP, using commercial defense alert data to label prevalent attack events. Xatu would help the commercial defense scrub up to 44.1% additional anomalous traffic and would reduce its median detection delay by 9.5 minutes.1
- 30 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-17
Open AccessXatu
Traditional DDoS attack detection monitors volumetric traffic features to detect attack onset. To reduce false positives, such detection is often conservative---raising an alert only after a sustained period of observed anomalous behavior. However, contemporary attacks tend to be short, which combined with a long detection delay means that most of the attack still reaches and impacts the victim. We propose Xatu, a system that utilizes auxiliary signals to improve the accuracy and timeliness of existing DDoS detection systems. We explore two types of auxiliary signals, attack preparation signals and the history of prior attacks. These signals can be easily mined from existing traffic monitoring systems in many ISP networks. To leverage these auxiliary signals for attack detection, we propose a multi-timescale LSTM model, which derives both long-term and short-term patterns from diverse auxiliary signals. We then leverage survival analysis to quickly detect attacks when they occur while minimizing false positives and thus scrubbing costs. We evaluate Xatu on traffic from a large ISP, using commercial defense alert data to label prevalent attack events. Xatu would help the commercial defense scrub up to 44.1% additional anomalous traffic and would reduce its median detection delay by 9.5 minutes.1
- Open Access
ESB: A Benchmark For Multi-Domain End-to-End Speech Recognition
Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require dataset-specific tuning (audio filtering, punctuation removal and normalisation of casing), therefore assuming a-priori knowledge of both the audio and text distributions. This tuning requirement can lead to systems failing to generalise to other datasets and domains. To promote the development of multi-domain speech systems, we introduce the End-to-end Speech Benchmark (ESB) for evaluating the performance of a single automatic speech recognition (ASR) system across a broad set of speech datasets. Benchmarked systems must use the same data pre- and post-processing algorithm across datasets - assuming the audio and text data distributions are a-priori unknown. We compare a series of state-of-the-art (SoTA) end-to-end (E2E) systems on this benchmark, demonstrating how a single speech system can be applied and evaluated on a wide range of data distributions. We find E2E systems to be effective across datasets: in a fair comparison, E2E systems achieve within 2.6% of SoTA systems tuned to a specific dataset. Our analysis reveals that transcription artefacts, such as punctuation and casing, pose difficulties for ASR systems and should be included in evaluation. We believe E2E benchmarking over a range of datasets promotes the research of multi-domain speech recognition systems. ESB is available at https://huggingface.co/esb.
Open AccessESB: A Benchmark For Multi-Domain End-to-End Speech Recognition
Speech recognition applications cover a range of different audio and text distributions, with different speaking styles, background noise, transcription punctuation and character casing. However, many speech recognition systems require dataset-specific tuning (audio filtering, punctuation removal and normalisation of casing), therefore assuming a-priori knowledge of both the audio and text distributions. This tuning requirement can lead to systems failing to generalise to other datasets and domains. To promote the development of multi-domain speech systems, we introduce the End-to-end Speech Benchmark (ESB) for evaluating the performance of a single automatic speech recognition (ASR) system across a broad set of speech datasets. Benchmarked systems must use the same data pre- and post-processing algorithm across datasets - assuming the audio and text data distributions are a-priori unknown. We compare a series of state-of-the-art (SoTA) end-to-end (E2E) systems on this benchmark, demonstrating how a single speech system can be applied and evaluated on a wide range of data distributions. We find E2E systems to be effective across datasets: in a fair comparison, E2E systems achieve within 2.6% of SoTA systems tuned to a specific dataset. Our analysis reveals that transcription artefacts, such as punctuation and casing, pose difficulties for ASR systems and should be included in evaluation. We believe E2E benchmarking over a range of datasets promotes the research of multi-domain speech recognition systems. ESB is available at https://huggingface.co/esb.
- Open Access
Unsupervised Text Deidentification
Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that masks words that leak personally-identifying information. The approach utilizes a specially trained reidentification model to identify individuals from redacted personal documents. Motivated by K-anonymity based privacy, we generate redactions that ensure a minimum reidentification rank for the correct profile of the document. To evaluate this approach, we consider the task of deidentifying Wikipedia Biographies, and evaluate using an adversarial reidentification metric. Compared to a set of unsupervised baselines, our approach deidentifies documents more completely while removing fewer words. Qualitatively, we see that the approach eliminates many identifying aspects that would fall outside of the common named entity based approach.
Open AccessUnsupervised Text Deidentification
Deidentification seeks to anonymize textual data prior to distribution. Automatic deidentification primarily uses supervised named entity recognition from human-labeled data points. We propose an unsupervised deidentification method that masks words that leak personally-identifying information. The approach utilizes a specially trained reidentification model to identify individuals from redacted personal documents. Motivated by K-anonymity based privacy, we generate redactions that ensure a minimum reidentification rank for the correct profile of the document. To evaluate this approach, we consider the task of deidentifying Wikipedia Biographies, and evaluate using an adversarial reidentification metric. Compared to a set of unsupervised baselines, our approach deidentifies documents more completely while removing fewer words. Qualitatively, we see that the approach eliminates many identifying aspects that would fall outside of the common named entity based approach.
- Open Access
End-to-end learning of multiple sequence alignments with differentiable Smith-Waterman
Multiple Sequence Alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA generation is often treated as a separate pre-processing step, without any guidance from the application it will be used for. Here, we implement a smooth and differentiable version of the Smith-Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of relying on black-box methods for optimizing predictions of protein sequences.
Open AccessEnd-to-end learning of multiple sequence alignments with differentiable Smith-Waterman
Multiple Sequence Alignments (MSAs) of homologous sequences contain information on structural and functional constraints and their evolutionary histories. Despite their importance for many downstream tasks, such as structure prediction, MSA generation is often treated as a separate pre-processing step, without any guidance from the application it will be used for. Here, we implement a smooth and differentiable version of the Smith-Waterman pairwise alignment algorithm that enables jointly learning an MSA and a downstream machine learning system in an end-to-end fashion. To demonstrate its utility, we introduce SMURF (Smooth Markov Unaligned Random Field), a new method that jointly learns an alignment and the parameters of a Markov Random Field for unsupervised contact prediction. We find that SMURF learns MSAs that mildly improve contact prediction on a diverse set of protein and RNA families. As a proof of concept, we demonstrate that by connecting our differentiable alignment module to AlphaFold and maximizing predicted confidence, we can learn MSAs that improve structure predictions over the initial MSAs. Interestingly, the alignments that improve AlphaFold predictions are self-inconsistent and can be viewed as adversarial. This work highlights the potential of differentiable dynamic programming to improve neural network pipelines that rely on an alignment and the potential dangers of relying on black-box methods for optimizing predictions of protein sequences.
- 1 April 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19483546,p. 507-510
Power and data for a wireless implanted neural recording system
This paper reports a two-way communication and inductive power link for a neural recording system. For this system a telemetry circuit was designed which utilizes an Integer-N PLL to support multiple outward data channels. The PLL design consumes less than 1.3mW below 100MHz, uses self-biasing techniques for supply rejection, has dimensions of 350um × 680um, and generates frequencies with a phase noise of -83dBc/Hz @100kHz offset, as measured at 80MHz. A wireless demonstration of the implanted circuitry is presented. Wireless powering is achieved with the help of a Class E Converter and demodulation of ASK data sent from the implant at 10Mbps is achieved with a simple asynchronous receiver.
- 1 April 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 19483546,p. 507-510
Power and data for a wireless implanted neural recording system
This paper reports a two-way communication and inductive power link for a neural recording system. For this system a telemetry circuit was designed which utilizes an Integer-N PLL to support multiple outward data channels. The PLL design consumes less than 1.3mW below 100MHz, uses self-biasing techniques for supply rejection, has dimensions of 350um × 680um, and generates frequencies with a phase noise of -83dBc/Hz @100kHz offset, as measured at 80MHz. A wireless demonstration of the implanted circuitry is presented. Wireless powering is achieved with the help of a Class E Converter and demodulation of ASK data sent from the implant at 10Mbps is achieved with a simple asynchronous receiver.