ICML 2024 Workshop WANT Submissions

An Analytical Approach to Enhancing DNN Efficiency and Accuracy Using Approximate Multiplication
Salar Shakibhamedan, Anice Jahanjoo, Amin Aminifar, Nima Amirafshar, Nima TaheriNejad, Axel Jantsch
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Accelerating Best-of-N via Speculative Rejection
Ruiqi Zhang, Momin Haider, Ming Yin, Jiahao Qiu, Mengdi Wang, Peter Bartlett, Andrea Zanette
- Published: 18 Jun 2024, Last Modified: 18 Jun 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Liouna: Biologically Plausible Learning for Efficient Pre-Training of Transferrable Deep Models
Fady Rezk, Antreas Antoniou, Henry Gouk, Timothy Hospedales
- Published: 18 Jun 2024, Last Modified: 12 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
AdaMeM: Memory Efficient Momentum for Adafactor
Nikhil Vyas, Depen Morwani, Sham M. Kakade
- Published: 18 Jun 2024, Last Modified: 17 Jul 2024
- WANT@ICML 2024 Oral
- Readers: Everyone
SatDiffMoE: A Mixture of Estimation Method for Satellite Image Super-resolution with Latent Diffusion Models
Zhaoxu Luo, Bowen Song, Liyue Shen
- Published: 18 Jun 2024, Last Modified: 21 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Model-Agnostic Graph Dataset Compression with the Tree Mover’s Distance
Mika Sarkin Jain, Stefanie Jegelka, Ishani Karmarkar, Luana Ruiz, Ellen Vitercik
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Bayesian-LoRA: LoRA based Parameter Efficient Fine-Tuning using Optimal Quantization levels and Rank Values trough Differentiable Bayesian Gates
Cristian Meo, Ksenia Sycheva, Anirudh Goyal, Justin Dauwels
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Adversarial Robustness Limits via Scaling-Law and Human-Alignment Studies
Brian R. Bartoldson, James Diffenderfer, Konstantinos Parasyris, Bhavya Kailkhura
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Coarse-to-Fine Semi-Structured Pruning of Graph Convolutional Networks for Skeleton-based Recognition
Hichem Sahbi
- Published: 18 Jun 2024, Last Modified: 05 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Optimistic Asynchrony Control: Achieving Synchronous Convergence With Asynchronous Throughput for Embedding Model Training
Roger Waleffe, Jason Mohoney
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones
Zhengqing Yuan, Zhaoxu Li, Weiran Huang, Yanfang Ye, Lichao Sun
- Published: 18 Jun 2024, Last Modified: 18 Jun 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Class-aware Initialization of Early Exits for Pre-training Large Language Models
Alperen Gormez, Erdem Koyuncu
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Resource-constrained Neural Architecture Search on Language Models: A Case Study
Andreas Paraskeva, Joao Pedro Reis, Suzan Verberne, Jan N. van Rijn
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Lowering PyTorch's Memory Consumption for Selective Differentiation
Samarth Bhatia, Felix Dangel
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Asynchronous Local-SGD Training for Language Modeling
Bo Liu, Rachita Chhaparia, Arthur Douillard, Satyen Kale, Andrei Alex Rusu, Jiajun Shen, Arthur Szlam, MarcAurelio Ranzato
- Published: 18 Jun 2024, Last Modified: 28 Jun 2024
- WANT@ICML 2024 Oral
- Readers: Everyone
DrJAX: Scalable and Differentiable MapReduce Primitives in JAX
J Keith Rush, Zachary Charles, Zachary Garrett, Sean Augenstein, Nicole Elyse Mitchell
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
u-μP: The Unit-Scaled Maximal Update Parametrization
Charlie Blake, Constantin Eichenberg, Josef Dean, Lukas Balles, Luke Yuri Prince, Björn Deiseroth, Andres Felipe Cruz-Salinas, Carlo Luschi, Samuel Weinbach, Douglas Orr
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Efficient Adaptive Federated Optimization
Su Hyeong Lee, Sidharth Sharma, Manzil Zaheer, Tian Li
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Single Train Multi Deploy on Topology Search Spaces using Kshot-Hypernet
Jingyue Zhuge, Christian Mayr, Anand Subramoney, David Kappel
- Published: 18 Jun 2024, Last Modified: 08 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Language Adaptation on a Tight Academic Compute Budget: Tokenizer Swapping Works and Pure bfloat16 Is Enough
Konstantin Dobler, Gerard de Melo
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Variational Stochastic Gradient Descent for Deep Neural Networks
Haotian Chen, Anna Kuzina, Babak Esmaeili, Jakub M. Tomczak
- Published: 18 Jun 2024, Last Modified: 09 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
LoQT: Low Rank Adapters for Quantized Training
Sebastian Bugge Loeschcke, Mads Toftrup, Michael Kastoryano, Serge Belongie, Vésteinn Snæbjarnarson
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Oral
- Readers: Everyone
Scalify: scale propagation for efficient low-precision LLM training
Paul Balanca, Samuel Hosegood, Carlo Luschi, Andrew W Fitzgibbon
- Published: 18 Jun 2024, Last Modified: 10 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs
Ashwinee Panda, Berivan Isik, Xiangyu Qi, Sanmi Koyejo, Tsachy Weissman, Prateek Mittal
- Published: 18 Jun 2024, Last Modified: 18 Jun 2024
- WANT@ICML 2024 Oral
- Readers: Everyone
Boolean Logic for Low-Energy Deep Learning
Van Minh Nguyen, Cristian Ocampo, Aymen Askri, Ba-Hien Tran
- Published: 18 Jun 2024, Last Modified: 02 Jul 2024
- WANT@ICML 2024 Poster
- Readers: Everyone