GUIDE: A Global Unified Inference Engine for Deploying Large Language Models in Heterogeneous Environmentsby Yanyu…
Enhancing Mathematical Reasoning in LLMs with Background Operatorsby Jiajun Chen, Yik-Cheung TamFirst submitted to arxiv…
CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversationsby Subash Neupane, Himanshu Tripathi,…
A Contemporary Overview: Trends and Applications of Large Language Models on Mobile Devicesby Lianjun Liu,…
AIM: Adaptive Inference of Multi-Modal LLMs via Token Merging and Pruningby Yiwu Zhong, Zhuoming Liu,…
VideoICL: Confidence-based Iterative In-context Learning for Out-of-Distribution Video Understandingby Kangsan Kim, Geon Park, Youngwan Lee,…
[CLS] Attention is All You Need for Training-Free Visual Token Pruning: Make VLM Inference Fasterby…
RandAR: Decoder-only Autoregressive Visual Generation in Random Ordersby Ziqi Pang, Tianyuan Zhang, Fujun Luan, Yunze…
AccDiffusion v2: Towards More Accurate Higher-Resolution Diffusion Extrapolationby Zhihang Lin, Mingbao Lin, Wengyi Zhan, Rongrong…
PLD+: Accelerating LLM inference by leveraging Language Model Artifactsby Shwetha Somasundaram, Anirudh Phukan, Apoorv SaxenaFirst…