Cutting Off the Head Ends the Conflict: A Mechanism for Interpreting and Mitigating Knowledge Conflicts…
REPrune: Channel Pruning via Kernel Representative Selectionby Mincheol Park, Dongjin Kim, Cheonjun Park, Yuna Park,…
Efficient Parameter Mining and Freezing for Continual Object Detectionby Angelo G. Menezes, Augusto J. Peterlevitz,…
LaCo: Large Language Model Pruning via Layer Collapseby Yifei Yang, Zouying Cao, Hai ZhaoFirst submitted…
FGeo-TP: A Language Model-Enhanced Solver for Geometry Problemsby Yiming He, Jia Zou, Xiaokai Zhang, Na…
A Comprehensive Survey of Compression Algorithms for Language Modelsby Seungcheol Park, Jaehyeon Choi, Sojin Lee,…
TroVE: Inducing Verifiable and Efficient Toolboxes for Solving Programmatic Tasksby Zhiruo Wang, Daniel Fried, Graham…
PRILoRA: Pruned and Rank-Increasing Low-Rank Adaptationby Nadav Benedek, Lior WolfFirst submitted to arxiv on: 20…
Model Compression Techniques in Biometrics Applications: A Surveyby Eduarda Caldeira, Pedro C. Neto, Marco Huber,…
Tiny Multi-Agent DRL for Twins Migration in UAV Metaverses: A Multi-Leader Multi-Follower Stackelberg Game Approachby…