papers

Publications (6)

cs.CV2026

VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment

Guoyang Xia, Fengfa Li, Hongjin Ji +4

Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to compare because…

cs.CV2022

Hierarchical Graph Convolutional Skeleton Transformer for Action Recognition

Ruwen Bai, Min Li, Bo Meng +4

Graph convolutional networks (GCNs) have emerged as dominant methods for skeleton-based action recognition. However, they still suffer from two problems, namely, neighborhood const…

cs.LG2026

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…

cs.CL2025

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…

cs.LG2026

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…

cs.CV2026

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…