RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
In: International Conference on Learning Representations (2022)
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
years
2026 4representative citing papers
Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.
citing papers explorer
-
When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing
RRDA introduces a router plus separate edit and locality adapters for memory-assisted knowledge editing, reporting highest accuracy on CounterFact, ZsRE, and MQuAKE-CF across two 8B models.
-
Can Multimodal Large Language Models Truly Understand Small Objects?
Current MLLMs show weak performance on small object understanding tasks, but fine-tuning with the new SOU-Train dataset measurably improves their capabilities.
-
SpaR3D-MoE: Adaptive 3D Spatial Reasoning from Sparse Views Meets Geometry-Inductive Mixture-of-Experts
Adaptive manifold keyframe sampling plus an instruction-pose-aware geometry MoE raises sparse-RGB 3D spatial reasoning to 63.5 average on VSI-Bench, beating strong baselines by 7.8 points.
-
Free Geometry: Refining 3D Reconstruction from Longer Versions of Itself
Free Geometry enables test-time self-improvement of 3D reconstruction models via cross-view consistency between full and masked observations, yielding average gains of 3.73% in pose accuracy and 2.88% in point maps.