Hugging Face Trending Papers

ParVL: Parallel Scaling and Expandable Compute Allocation for Multimodal LLMs

Read the original on Hugging Face Trending Papers →

Existing scaling strategies for Multimodal Large Language Models (MLLMs) typically expand either model parameters or sequential inference computation, incurring substantial memory or latency overhead. More importantly, most existing methods fail to alter the rigid, fixed computation allocation between the Vision Transformer and the Large Language Model components, limiting task-specific optimization.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Jul 28

cMoLLM at Scale: Horizontal Scaling Laws for Mixture-of-LLMs

arXiv:2607. 22577v1 Announce Type: new Abstract: Scaling large language models (LLMs) has driven their success, yet dense Transformers couple capacity and computation: every parameter is activated for every token, making training and inference costs grow linearly with model size-a critical bottleneck as models approach trillion-parameter regimes.

By Xin Yang, Yemin Wang, Mingda Liu, Letian Li, Shuaishuai Cao, Zhengxiao He, Ryan Dong
arXiv AI
Jun 12

M*: A Modular, Extensible, Serving System for Multimodal Models

arXiv:2606. 12688v1 Announce Type: cross Abstract: We are entering a new era of composite model architectures that integrate diverse components such as vision encoders, language backbones, diffusion and flow heads, audio codecs, action generators, and world-model predictors.

By Atindra Jha, Naomi Sagan, Keisuke Kamahori, Irmak Sivgin, Rohan Sanda, Steven Gao, Mark Horowitz, Luke Zettlemoyer, Olivia Hsu, Jure Leskovec, Baris Kasikci, Stephanie Wang