Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts — mentioned by viraptor

Sat, 12 Jul 2025 12:46:12 GMT

Sounds like dumping the routing information from programming questions would answer that... I guess I can do a dump from qwen or deepseek locally. You'd think someone would created that kind of graph already, but I couldn't find one. What I did find instead is that some MoE models are explicitly domain-routed (MoDEM), but it doesn't apply to deepseek which is just equally load balanced, so it's unlikely to apply to Kimi. On the other hand, https://arxiv.org/html/2505.21079v1 shows modality preferences between experts, even in mostly random training. So maybe there's something there.

Paper and discussion history. A mention is not an endorsement.

Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts · HackerPapers discussions

Uni3D-MoE: Scalable Multimodal 3D Scene Understanding via Mixture of Experts — mentioned by viraptor