MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Ranking
Overall
87
Content
95
Popularity
67
Observed public metrics from 1 member.
Merged summary
TL;DR - MoE-ViE efficiently scales CLIP-style vision encoders using fine-grained mixture-of-experts designs, specialized load balancing, and an optimized inference kernel. Its largest model matches a state-of-the-art encoder 1.7Ă— larger while using 76% of its latency.
- Fine-grained MoE topologies consistently outperform dense and standard MoE vision encoders across model sizes.
- An auxiliary-loss-free balancing method improves expert utilization, while a specialized MoE kernel reduces inference overhead.
- Frame-level distillation and selective freezing add video capabilities while preserving learned image knowledge.
- When aligned with an LLM, MoE-ViE leads the compared image and video benchmarks, including against encoders with up to 5Ă— more activated parameters.
Sources (1)
MoE-ViE: Mixture of Experts Vision Encoder for Efficient Image and Video Understanding
Public signals
Hugging Face upvotes 19
TL;DR - MoE-ViE efficiently scales CLIP-style vision encoders using fine-grained mixture-of-experts designs, specialized load balancing, and an optimized inference kernel. Its largest model matches a state-of-the-art encoder 1.7Ă— larger while using 76% of its latency.
- Fine-grained MoE topologies consistently outperform dense and standard MoE vision encoders across model sizes.
- An auxiliary-loss-free balancing method improves expert utilization, while a specialized MoE kernel reduces inference overhead.
- Frame-level distillation and selective freezing add video capabilities while preserving learned image knowledge.
- When aligned with an LLM, MoE-ViE leads the compared image and video benchmarks, including against encoders with up to 5Ă— more activated parameters.