RankElastor mitigates embedding collapse via spectrum-robust token mixing and GLU-based P-FFNs, yielding better performance and scaling on industrial recommendation datasets.
Berg, Wan-Yen Lo, Piotr Dollar, and Ross Girshick
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
baseline 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
baseline 1polarities
baseline 1representative citing papers
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.
citing papers explorer
-
Expand More, Shrink Less: Shaping Effective-Rank Dynamics for Dense Scaling in Recommendation
RankElastor mitigates embedding collapse via spectrum-robust token mixing and GLU-based P-FFNs, yielding better performance and scaling on industrial recommendation datasets.
-
LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models
LAST augments MLLMs with a tool-abstraction sandbox and three-stage training to deliver around 20% gains on spatial reasoning tasks, outperforming closed-source models.