Fangxiang Feng
Scholar

Fangxiang Feng

Google Scholar ID: W0O_dfoAAAAJ
Beijing University of Posts and Telecommunications
Multimodal LearningImage Synthesis
Google Scholar↗
Citations & Impact
All-time
Citations
3,767
 
H-index
18
 
i10-index
23
 
Publications
20
 
Co-authors
0
 
Contact
No contact links provided.
Publications
9 items
What Makes an Efficient VLA? Navigating Action-Head Design, Scaling, and Latency
2026
Cited
0
VANE: Reliable Test-Time Training for Vision-Language-Action Models via Future Visual Representation Prediction
2026
Cited
0
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
2026
Cited
0
FastMMoE: Accelerating Multimodal Large Language Models through Dynamic Expert Activation and Routing-Aware Token Pruning
2025
Cited
0
ChunkLLM: A Lightweight Pluggable Framework for Accelerating LLMs Inference
2025
Cited
0
SMAR: Soft Modality-Aware Routing Strategy for MoE-based Multimodal Large Language Models Preserving Language Capabilities
2025
Cited
0
Evaluating MLLMs with Multimodal Multi-image Reasoning Benchmark
2025
Cited
0
FreeGraftor: Training-Free Cross-Image Feature Grafting for Subject-Driven Text-to-Image Generation
2025
Cited
0
Resume (English only)
Co-authors
0 total
Co-authors: 0 (list not available)