Junjie Yang
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
Junjie Yang has a total of 35 co-authors. Here are the top co-authors by number of shared publications:
- Hong Li
Meta, Menlo Park, CA, USA
4 shared publications - Hong Yan
Meta, Menlo Park, USA
4 shared publications - Li Yu
Meta, Menlo Park, USA
3 shared publications - Renzhi Wu
Meta, Menlo Park, CA, USA
3 shared publications - Sri Reddy
Meta Platforms, Inc., Menlo Park, CA, USA
3 shared publications - Jorge Piekarewicz
Florida State University
2 shared publications
Latest Publications
- Open Access
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1417-1426
RankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
- 27 September 2026
- Published by Association for Computing Machinery (ACM)
- p. 1417-1426
Open AccessRankGraph-2: Lifecycle Co-Design for Billion-Node Graph Learning in Recommendation
- Open Access
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4545-4549
CMSL: Constructive Multi-Sequence Learning for Recommendation Systems
- 19 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 4545-4549
Open AccessCMSL: Constructive Multi-Sequence Learning for Recommendation Systems
- Open Access
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1050-1053
RankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
- 22 September 2025
- Published by Association for Computing Machinery (ACM)
- p. 1050-1053
Open AccessRankGraph: Unified Heterogeneous Graph Learning for Cross-Domain Recommendation
- Open Access
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 778-780
Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational costs present substantial challenges. In this paper, we demonstrate our development of an efficiency-driven approach to explore these paradigms, moving beyond traditional reliance on native PyTorch modules. We address the specific challenges posed by ranking models’ dependence on categorical features, which vary in length and complicate GPU utilization. We introduce Jagged Feature Interaction Kernels, a novel method designed to extract fine-grained insights from long categorical features through efficient handling of dynamically sized tensors. We further enhance the performance of attention mechanisms by integrating Jagged tensors with Flash Attention. Our novel Jagged Flash Attention achieves up to 9 × speedup and 22 × memory reduction compared to dense attention. Notably, it also outperforms dense flash attention, with up to 3 × speedup and 53% more memory efficiency. In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.
- 8 October 2024
- Published by Association for Computing Machinery (ACM)
- p. 778-780
Open AccessEnhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previously deemed impractical. However, the GPU-based computational costs present substantial challenges. In this paper, we demonstrate our development of an efficiency-driven approach to explore these paradigms, moving beyond traditional reliance on native PyTorch modules. We address the specific challenges posed by ranking models’ dependence on categorical features, which vary in length and complicate GPU utilization. We introduce Jagged Feature Interaction Kernels, a novel method designed to extract fine-grained insights from long categorical features through efficient handling of dynamically sized tensors. We further enhance the performance of attention mechanisms by integrating Jagged tensors with Flash Attention. Our novel Jagged Flash Attention achieves up to 9 × speedup and 22 × memory reduction compared to dense attention. Notably, it also outperforms dense flash attention, with up to 3 × speedup and 53% more memory efficiency. In production models, we observe 10% QPS improvement and 18% memory savings, enabling us to scale our recommendation systems with longer features and more complex architectures.
- 5 November 2020
- Published by American Physical Society (APS) in Physical Review C
- Vol. 102 (5) , 054308
Dirac oscillator: An alternative basis for nuclear structure calculations
Background: The isotropic harmonic oscillator supplemented by a strong spin-orbit interaction has been the cornerstone of nuclear structure since its inception more than seven decades ago. In this paper we introduce—or rather re-introduce—the “Dirac oscillator,” a fully relativistic basis that has all the desired attributes of the ordinary harmonic oscillator while naturally incorporating a strong spin-orbit coupling.
- 5 November 2020
- Published by American Physical Society (APS) in Physical Review C
- Vol. 102 (5) , 054308
Dirac oscillator: An alternative basis for nuclear structure calculations
Background: The isotropic harmonic oscillator supplemented by a strong spin-orbit interaction has been the cornerstone of nuclear structure since its inception more than seven decades ago. In this paper we introduce—or rather re-introduce—the “Dirac oscillator,” a fully relativistic basis that has all the desired attributes of the ordinary harmonic oscillator while naturally incorporating a strong spin-orbit coupling.
- 1 November 2019
- Published by American Physical Society (APS) in Physical Review C
- Vol. 100 (5) , 054301
Electroweak probes of ground state densities
Background: Elastic electron scattering has been used for decades to paint the most accurate picture of the proton distribution in atomic nuclei. This stands in stark contrast to the neutron distribution that is traditionally probed using hadronic reactions that are hindered by large uncertainties in the reaction mechanism. Spurred by new experimental developments, it is now possible to gain valuable insights into the neutron distribution using exclusively electroweak probes.
- 1 November 2019
- Published by American Physical Society (APS) in Physical Review C
- Vol. 100 (5) , 054301
Electroweak probes of ground state densities
Background: Elastic electron scattering has been used for decades to paint the most accurate picture of the proton distribution in atomic nuclei. This stands in stark contrast to the neutron distribution that is traditionally probed using hadronic reactions that are hindered by large uncertainties in the reaction mechanism. Spurred by new experimental developments, it is now possible to gain valuable insights into the neutron distribution using exclusively electroweak probes.