Skip to yearly menu bar Skip to main content


Poster session
in
Workshop: 5th Workshop on practical ML for limited/low resource settings (PML4LRS) @ ICLR 2024

Coffee break + Poster session I

Jaeseong You · Danilo Silva · Amin Charusaie · Shuvom Sadhuka · Yuta Oshima · Sean Farhat · Jinsung Jeon · Luke Hudlass-Galley · Shiwei Liu · Johannes Schimunek · Keisuke Kamahori · Jiawei Zhao · Meisam Razaviyayn

[ ]
[ Slides
Sat 11 May 12:25 a.m. PDT — 1:25 a.m. PDT

Abstract:
  1. Addax: Memory-Efficient Fine-Tuning of Language Models with a Combination of Forward-Backward and Forward-Only Passes
    Zeman Li, Xinwei Zhang, Meisam Razaviyayn

  2. GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection
    Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, Yuandong Tian

  3. Fiddler: CPU-GPU Orchestration for Fast Inference of Mixture-of-Experts Models
    Keisuke Kamahori, Yile Gu, Kan Zhu, Baris Kasikci

  4. Autoregressive activity prediction for low-data drug discovery
    Johannes Schimunek, Lukas Friedrich, Daniel Kuhn, G√ľnter Klambauer

  5. Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity
    Lu Yin, You Wu, Zhenyu Zhang, Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Gen Li, AJAY KUMAR JAISWAL, Mykola Pechenizkiy, Yi Liang, Michael Bendersky, Zhangyang Wang, Shiwei Liu

  6. SparQ Attention: Bandwidth-Efficient LLM Inference
    Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, Douglas Orr

  7. How to Parameterize Asymmetric Quantization Ranges for Quantization-Aware Training
    Jaeseong You, Minseop Park, Markus Nagel, Kyunggeun Lee, Seokjun An, Chirag S Patel

  8. SPI-GAN: Denoising Diffusion GANs with Straight-Path Interpolations Jinsung Jeon, Noseong Park

  9. On the Surprising Efficacy of Distillation as an Alternative to Pre-Training Small Models
    Sean Farhat, Deming Chen

  10. SSM Meets Video Diffusion Models: Efficient Video Generation with Structured State Spaces
    Yuta Oshima, Shohei Taniguchi, Masahiro Suzuki, Yutaka Matsuo

  11. Multi-model evaluation with labeled & unlabeled data
    Divya M Shanmugam, Shuvom Sadhuka, Manish Raghavan, John Guttag, Bonnie Berger, Emma Pierson

  12. Defer-and-Fusion: Optimal Predictors that Incorporate Human Decisions
    Mohammad-Amin Charusaie, Amirmehdi Jafari Fesharaki, Samira Samadi

  13. Selective Prediction for Semantic Segmentation under Distribution Shift Bruno Laboissiere Camargos Borges, Bruno Machado Pacheco, Danilo Silva

Chat is not available.