newsitem: ICML 2024
Our cluster will present no less
than 13 papers at the ICML 2024 conference and its workshops!
These are the works presented at the main
conference:
· Gradual Divergence for Seamless Adaptation: A Novel Domain Incremental Learning Method by Kishaan Jeeveswaran, Elahe Arani, and Bahram Zonooz
·
Efficient Exploration in
Average-Reward Constrained Reinforcement Learning: Achieving Near-Optimal
Regret With Posterior Sampling by Danil Provodin, Maurits Kaptein and
Mykola Pechenizkiy
·
MALIBO: Meta-learning for
Likelihood-free Bayesian Optimization by Jiarong Pan, Stefan Falkner, Felix
Berkenkamp, and Joaquin Vanschoren
·
TrustLLM: Trustworthiness in
Large Language Models by Lichao Sun et al. including Joaquin Vanschoren
·
Scalable Safe Policy
Improvement for Factored Multi-Agent MDPs by Federico Bianchi, Edoardo
Zorzi, Alberto Castellini, Thiago D. Simão, Matthijs T. J. Spaan, and
Alessandro Farinelli
·
Outlier
weighed layerwise sparsity (owl): A missing secret sauce for pruning llms to
high sparsity by Yin, Lu, You Wu, Zhenyu Zhang,
Cheng-Yu Hsieh, Yaqing Wang, Yiling Jia, Mykola Pechenizkiy, Yi Liang,
Zhangyang Wang, and Shiwei Liu
· Junk DNA hypothesis: A task-centric angle of llm pre-trained weights through sparsity by Yin, Lu, Shiwei Liu, Ajay Jaiswal, Souvik Kundu, and Zhangyang Wang
·
BiDST: Dynamic Sparse
Training is a Bi-Level Optimization Problem by Ji, Jie, Gen Li, Lu Yin,
Minghai Qin, Geng Yuan, Linke Guo, Shiwei Liu, and Xiaolong Ma
·
CaM: Cache Merging
for Memory-efficient LLMs Inference. by Yuxin Zhang, Yuxuan Du, Gen Luo,
Yunshan Zhong, Zhenyu Zhang, Shiwei Liu, Rongrong Ji
· Every Sparse Pattern Every Sparse Ratio All At Once by Zhangheng LI, Shiwei Liu, Tianlong Chen, AJAY KUMAR JAISWAL, Zhenyu Zhang, Dilin Wang, Raghuraman Krishnamoorthi, Shiyu Chang, Zhangyang Wang
We’ll also present the following workshop papers:
· Accelerating
Simulation of Two-Phase Flows with Neural PDE Surrogates by Yoeri Poels, Koen Minartz, Harshit Bansal, Vlado Menkovski
at the AI4Science workshop
· Exploring the
development of complexity over depth and time in deep neural networks by Hannah Pinson, Aurélien Boland, Vincent Ginis, Mykola Pechenizkiy at the HiLD workshop
· Variational Stochastic Gradient Descent for Deep Neural Networks by H Chen, A Kuzina, B Esmaeili, JM Tomczak at the WANT workshop
See you in Vienna!