firstbacksecondback
17 Results
|
Workshop
|
Medical Unlearnable Examples: Securing Medical Data from Unauthorized Traning via Sparsity-Aware Local Masking Weixiang Sun · Yixin Liu · Zhiling Yan · Kaidi Xu · Lichao Sun |
||
|
Poster
|
Tue 4:30 |
SPP: Sparsity-Preserved Parameter-Efficient Fine-Tuning for Large Language Models Xudong LU · Aojun Zhou · Yuhui Xu · Renrui Zhang · Peng Gao · Hongsheng Li |
|
|
Poster
|
Thu 2:30 |
SPADE: Sparsity-Guided Debugging for Deep Neural Networks Arshia Soltani Moakhar · Eugenia Iofinova · Elias Frantar · Dan Alistarh |
|
|
Poster
|
Wed 4:30 |
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 Jaiswal · Mykola Pechenizkiy · Yi Liang · Michael Bendersky · Zhangyang “Atlas” Wang · Shiwei Liu |
|
|
Poster
|
Tue 2:30 |
A Sparsity Principle for Partially Observable Causal Representation Learning Danru Xu · Dingling Yao · Sébastien Lachapelle · Perouz Taslakian · Julius von Kügelgen · Francesco Locatello · Sara Magliacane |
|
|
Poster
|
Tue 4:30 |
Smoothing Proximal Gradient Methods for Nonsmooth Sparsity Constrained Optimization: Optimality Conditions and Global Convergence Ganzhao Yuan |
|
|
Workshop
|
Decomposed Linear Dynamical Systems (dLDS) for identifying the latent dynamics underlying high-dimensional time-series Noga Mudrik · Yenho Chen · Eva Yezerets · Christopher Rozell · Adam Charles |
||
|
Workshop
|
Rapid Switching and Multi-Adapter Fusion via Sparse High Rank Adapters Kartikeya Bhardwaj · Nilesh Prasad Pandey · Sweta Priyadarshi · Viswanath Ganapathy · Rafael Esteves · Shreya Kadambi · Shubhankar Borse · Paul Whatmough · Risheek Garrepalli · Marinus van Baalen · Harris Teague · Markus Nagel |
||
|
Workshop
|
Zeroth-Order Fine-Tuning of LLMs with Extreme Sparsity Wentao Guo · Jikai Long · YIMENG ZENG · Zirui Liu · Xinyu Yang · Yide Ran · Jacob Gardner · Osbert Bastani · Chris De Sa · Xiaodong Yu · Beidi Chen · Zhaozhuo Xu |
||
|
Workshop
|
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion Filip Szatkowski · Bartosz Wójcik · Mikołaj Piórczyński · Simone Scardapane |
||
|
Workshop
|
Hurdle conjugate priors for scalable Tucker decomposition John Hood · Aaron Schein |
||
|
Workshop
|
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs Ashwinee Panda · Berivan Isik · Xiangyu Qi · Sanmi Koyejo · Tsachy Weissman · Prateek Mittal |