4 papers
Dense2MoE: Pushing the Pareto Frontier of On-Device LLMs via Unified Pruning and Upcycling
Fengfa Li, Hongjin Ji, Yifeng Ding +2
The Mixture of Experts MoE architecture is highly promising for resource constrained on device deployments yet training these models from scratch incurs prohibitive costs Current m…
FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning
Guoyang Xia, Yifeng Ding, Fengfa Li +4
Multimodal large language models (MLLMs) have achieved impressive performance, but high-resolution visual inputs result in long sequences of visual tokens and substantial inference…
Hardware Co-Design Scaling Laws via Roofline Modelling for On-Device LLMs
Luoyang Sun, Jiwen Jiang, Yifeng Ding +9
Vision-Language-Action Models (VLAs) have emerged as a key paradigm of Physical AI and are increasingly deployed in autonomous vehicles, robots, and smart spaces. In these resource…
SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language Capabilities
Guoyang Xia, Yifeng Ding, Fengfa Li +4
Mixture of Experts (MoE) architectures have become a key approach for scaling large language models, with growing interest in extending them to multimodal tasks. Existing methods t…