firstbacksecondback
57 Results
|
Affinity Workshop
|
Mon 4:50 |
Non-Uniform Parameter-Wise Model Merging |
|
|
Poster
|
Thu 4:30 |
CaM: Cache Merging for Memory-efficient LLMs Inference Yuxin Zhang · Yuxuan Du · Gen Luo · Yunshan Zhong · Zhenyu Zhang · Shiwei Liu · Rongrong Ji |
|
|
Workshop
|
Pretrained Hybrids with MAD Skills Nicholas Roberts · Samuel Guo · Zhiqi Gao · Satya Sai Srinath Namburi GNVV · Sonia Cromp · Chengjun Wu · Chengyu Duan · Frederic Sala |
||
|
Workshop
|
Merging Text Transformer Models from Different Initializations Neha Verma · Maha Elbayad |
||
|
Workshop
|
Combining Pre-trained LoRA Modules Improves Few-shot Adaptation of Foundation Models to New Tasks Nader Asadi · Mahdi Beitollahi · Yasser Khalil · Yinchuan Li · Guojun Zhang · Xi Chen |
||
|
Workshop
|
Learning Multi-Index Models with Neural Networks via Mean-Field Langevin Dynamics Alireza Mousavi-Hosseini · Denny Wu · Murat Erdogdu |
||
|
Workshop
|
Model Breadcrumbs: Scalable Upcycling of Finetuned Foundation Models via Sparse Task Vectors Merging MohammadReza Davari · Eugene Belilovsky |
||
|
Workshop
|
Lottery Ticket Adaptation: Mitigating Destructive Interference in LLMs Ashwinee Panda · Berivan Isik · Xiangyu Qi · Sanmi Koyejo · Tsachy Weissman · Prateek Mittal |
||
|
Poster
|
Thu 2:30 |
Localizing Task Information for Improved Model Merging and Compression Ke Wang · Nikolaos Dimitriadis · Guillermo Ortiz-Jimenez · François Fleuret · Pascal Frossard |