5 papers
LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing
Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis +1
Lifelong knowledge editing aims to efficiently and sequentially update language models over time, as new knowledge becomes available or when the model makes mistakes, while preserv…
ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
Arash Akbari, Arman Akbari, Masih Eskandar +11
Vision-Language-Action (VLA) models exhibit remarkable action generation for embodied intelligence, but their heavy compute make deployment on edge platforms impractical. Aggressiv…
Online Two-Stage Submodular Maximization
Iasonas Nikolaou, Miltiadis Stouras, Stratis Ioannidis +1
Given a collection of monotone submodular functions, the goal of Two-Stage Submodular Maximization (2SSM) [Balkanski et al., 2016] is to restrict the ground set so an objective sel…
Enabling Flexible Multi-LLM Integration for Scalable Knowledge Aggregation
Zhenglun Kong, Zheng Zhan, Shiyue Hou +10
Large language models (LLMs) have shown remarkable promise but remain challenging to continually improve through traditional finetuning, particularly when integrating capabilities…
Exploring Token Pruning in Vision State Space Models
Zheng Zhan, Zhenglun Kong, Yifan Gong +8
State Space Models (SSMs) have the advantage of keeping linear computational complexity compared to attention modules in transformers, and have been applied to vision tasks as a ne…