S³E framework finds excess decision-state displacement under semantic stress in multimodal models despite consistent correct forced-choice behavior.
arXiv preprint arXiv:2509.22415 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Multimodal LLMs exhibit functional sparsity where a small number of CoRe attention heads handle cross-modal retrieval, with ablation of the top 5% degrading performance while others have little effect.
MACS reduces Expert Parallelism stragglers in MoE MLLMs via entropy-weighted visual token load and dynamic modality-adaptive expert capacity, without retraining.
citing papers explorer
-
When Correct Decisions Hide Internal Stress: Decision-State Probing in Multimodal Language Models
S³E framework finds excess decision-state displacement under semantic stress in multimodal models despite consistent correct forced-choice behavior.
-
Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
Multimodal LLMs exhibit functional sparsity where a small number of CoRe attention heads handle cross-modal retrieval, with ablation of the top 5% degrading performance while others have little effect.
-
MACS: Modality-Aware Capacity Scaling for Efficient Multimodal MoE Inference
MACS reduces Expert Parallelism stragglers in MoE MLLMs via entropy-weighted visual token load and dynamic modality-adaptive expert capacity, without retraining.