Accepted Papers (Oral Presentation)

  1. Supernet Training for Federated Image Classification
    Taehyeon Aaron Kim (KAIST)*; Se-Young Yun (KAIST) [PDF]
  2. Achieving High TinyML Accuracy through Selective Cloud Interactions
    Anil Kag (Boston University)*; Igor Fedorov (Arm Research); Aditya Gangrade (Boston University); Paul Whatmough (Arm Research); Venkatesh Saligrama (Boston University) [PDF]
  3. Triangular Dropout: Variable Network Width without Retraining
    Edward W Staley (JHUAPL)*; Jared Markowitz (Johns Hopkins University Applied Physics Laboratory) [PDF]
  4. A Theoretical View on Sparsely Activated Networks
    Cenk Baykal (Google Research); Nishanth Dikkala (Google Research)*; Rina Panigrahy (Google); Cyrus Rashtchian (Google); Xin Wang (Google) [PDF] [Poster]
  5. Does Continual Learning Equally Forget All Parameters?
    Haiyan Zhao (University of Technology Sydney)*; Tianyi Zhou (University of Washington); Guodong Long (University of Technology Sydney); Jing Jiang (University of Technology Sydney); Chengqi Zhang (University of Technology Sydney) [PDF]
  6. PA-GNN: Parameter-Adaptive Graph Neural Networks
    Yuxin Yang (Tsinghua University)*; Yitao Liang (Peking University); Muhan Zhang (Peking University) [PDF]
  7. Slimmable Quantum Federated Learning
    Won Joon Yun (Korea University); Jae Pyoung Kim (Korea University); Soyi Jung (Hallym Univeristy); Jihong Park (Deakin University); Mehdi Bennis (University of Oulu); Joongheon Kim (Korea University, School of Electrical Engineering)* [PDF]
  8. Sparsifying Transformer Models with Trainable Representation Pooling
    Michał Pietruszka (Jagiellonian University)*; Łukasz Borchmann (Applica.ai); Łukasz Garncarek (Applica.ai)
  9. Play It Cool: Dynamic Shifting Prevents Thermal Throttling
    Yang Zhou (University of Texas at Austin )*; Feng Liang (The University of Texas at Austin); Ting-Wu Chin (Carnegie Mellon University); Diana Marculescu (The University of Texas at Austin) [PDF]
  10. Efficient Sparsely Activated Transformers
    Salar Latifi (University of Michigan)*; Saurav Muralidharan (NVIDIA); Michael Garland (NVIDIA) [PDF]
  11. Sparse Relational Reasoning with Object-centric Representations
    Alex F Spies (Imperial College London)*


Accepted Papers (Poster Presentation)

  1. The Spike Gating Flow: A Hierarchical Structure Based Spiking Neural Network for Spatiotemporal Computing
    Zihao Zhao (Fudan University)*; Yanhong Wang (Fudan university); Qiaosha Zou (Fudan University); Xiaoan Wang (BrainUp Research Lab); C.-J. Richard Shi (Fudan University); Junwen Luo (BrainUp Research Lab) [PDF]
  2. Back to the Source: Test-Time Diffusion-Driven Adaptation
    Jin Gao (Shanghai Jiaotong University); Jialing Zhang (Shanghai Jiaotong University); Xihui Liu (UC Berkeley); Trevor Darrell (UC Berkeley); Evan Shelhamer (DeepMind); Dequan Wang (UC Berkeley)*
  3. Dynamic Split Computing for Efficient Deep Edge Intelligence
    Arian Bakhtiarnia (Aarhus University)*; Nemanja B Milosevic (UNSPMF); Qi Zhang (Aarhus University); Dragana Bajović (University of Novi Sad); Alexandros Iosifidis (Aarhus University) [PDF]
  4. Learning Modularity for Generalizable Robotic Behaviors
    Corban Rivera (JHU/APL)*; Chace Ashcraft (JHU/APL); Katie Popek (JHU/APL); Edward Staley (JHU/APL); Kapil Katyal (Johns Hopkins University) [PDF]
  5. Inductive Biases for Object-Centric Representations in the Presence of Complex Textures
    Samuele Papa (University of Amsterdam)*; Ole Winther (DTU and KU); Andrea Dittadi (Technical University of Denmark) [PDF]
  6. Noisy Heuristics NAS: A Network Morphism based Neural Architecture Search using Heuristics
    Suman Sapkota (NAAMII)*; Binod Bhattarai (University College London) [PDF] [Poster]
  7. FLOWGEN: Fast and slow graph generation
    Aman Madaan (Carnegie Mellon University)*; Yiming Yang (Carnegie Mellon University) [PDF] [Poster]
  8. Fault-Tolerant Collaborative Inference through the Edge-PRUNE Framework
    Jani Boutellier (University of Vaasa)*; Bo Tan (Tampere University); Jari Nurmi (Tampere University, Finland) [PDF]
  9. Vote for Nearest Neighbors Meta-Pruning of Self-Supervised Networks
    Haiyan Zhao (University of Technology Sydney)*; Tianyi Zhou (University of Washington); Guodong Long (University of Technology Sydney); Jing Jiang (University of Technology Sydney); Chengqi Zhang (University of Technology Sydney) [PDF]
  10. A Product of Experts Approach to Early-Exit Ensembles
    James U Allingham (University of Cambridge)*; Eric Nalisnick (University of Amsterdam) [PDF]
  11. Neural Architecture Search with Loss Flatness-aware Measure
    Joonhyun Jeong (Clova Image Vision, NAVER Corp.)*; Joonsang Yu (NAVER CLOVA); Dongyoon Han (NAVER AI Lab); Youngjoon Yoo (Clova AI Research, NAVER Corp.) [PDF] [Poster]
  12. Is a Modular Architecture Enough?
    Sarthak Mittal (Mila)*; Yoshua Bengio (Mila); Guillaume Lajoie (Mila, Université de Montréal) [PDF] [Poster]
  13. Parameter efficient dendritic-tree neurons outperform perceptrons
    Ziwen Han (University of Toronto)*; Evgeniya Gorobets (University of Toronto); Pan Chen (University of Toronto) [PDF]
  14. Simple, Practical and Fast Dynamic Truncation Kernel Multiplication
    Lianke Qin (UCSB)*; Somdeb Sarkhel (Adobe); Zhao Song (Adobe Research); Danyang Zhuo (Duke University) [PDF] [Poster]
  15. Confident Adaptive Language Modeling
    Tal Schuster (Google)*; Adam Fisch (MIT); Jai Gupta (Google); Mostafa Dehghani (Google Brain); Dara Bahri (Google); Vinh Q Tran (Google); Yi Tay (Google); Donald Metzler (Google) [PDF]
  16. Provable Hierarchical Lifelong Learning with a Sketch-based Modular Architecture
    ZIHAO DENG (Washington University in St. Louis)*; Zee Fryer (Google Research); Brendan Juba (Washington University in St Louis); Rina Panigrahy (Google); Xin Wang (Google) [PDF]
  17. SnapStar Algorithm: a new way to ensemble Neural Networks
    Sergey Zinchenko (NSU)*; Dmitry Lishudi (Higher School of Economics) [PDF] [Poster]
  18. HARNAS: Neural Architecture Search Jointly Optimizing for Hardware Efficiency and Adversarial Robustness of Convolutional and Capsule Networks
    Alberto Marchisio (Technische Universität Wien (TU Wien))*; Vojtech Mrazek (Brno University of Technology); Andrea Massa (Politecnico di Torino); Beatrice Bussolino (Politecnico di Torino); Maurizio Martina (Politecnico di Torino); Muhammad Shafique (New York University Abu Dhabi) [PDF] [Poster]
  19. Dynamic Transformer Networks
    Amanuel N Mersha (Addis Ababa Institute Technology)* [PDF]
  20. Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules
    Kale-ab Tessera (InstaDeep)*; Chiratidzo Matowe (InstaDeep); Arnu Pretorius (Instadeep); Benjamin Rosman (University of the Witwatersrand); Sara Hooker (Cohere) [PDF]
  21. FedHeN: Federated Learning in Heterogeneous Networks
    Durmus Alp Emre Acar (Boston University)*; Venkatesh Saligrama (Boston University) [PDF]
  22. APP: Anytime Progressive Pruning
    Diganta Misra (MILA)*; Bharat Runwal (Indian Institute of Technology(IIT), Delhi); Tianlong Chen (Unversity of Texas at Austin); Zhangyang Wang (University of Texas at Austin); Irina Rish (Mila/UdeM) [PDF] [Poster]
  23. Deep Policy Generators
    Francesco Faccio (The Swiss AI Lab IDSIA); Vincent Herrmann (IDSIA)*; Aditya Ramesh (The Swiss AI Lab IDSIA); Louis Kirsch (Swiss AI Lab IDSIA); Jürgen Schmidhuber (IDSIA - Lugano) [PDF]
  24. Connectivity Properties of Neural Networks Under Performance-Resources Trade-off
    Aleksandra I Nowak (Jagiellonian Univeristy)*; Romuald Janik (Jagiellonian University) [PDF]