SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.
arXiv preprint arXiv:2308.00951 , year=
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 9roles
background 2polarities
background 2representative citing papers
Standard top-k routers in MoE language models often select suboptimal routes for difficult tokens, and updating only the final router layer raises pass@K on AIME and HMMT benchmarks across multiple models.
ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
B-MoE framework achieves state-of-the-art performance on micro-action recognition by using region-specific experts and cross-attention routing.
PathMoE constrains expert paths in MoE models by sharing router parameters across layer blocks, yielding more concentrated paths, better performance on perplexity and tasks, and no need for auxiliary losses.
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.
Introduces Adaptive Clustering router for MoE models that scales features to identify tight expert clusters, yielding faster convergence, robustness to corruption, and performance gains.
citing papers explorer
-
SplatWeaver: Learning to Allocate Gaussian Primitives for Generalizable Novel View Synthesis
SplatWeaver uses cardinality Gaussian experts and pixel-level routing to dynamically allocate varying numbers of Gaussian primitives for generalizable novel view synthesis.
-
When Are Experts Misrouted? Counterfactual Routing Analysis in Mixture-of-Experts Language Models
Standard top-k routers in MoE language models often select suboptimal routes for difficult tokens, and updating only the final router layer raises pass@K on AIME and HMMT benchmarks across multiple models.
-
Agent-Centric Observation Adaptation for Robust Visual Control under Dynamic Perturbations
ACO-MoE recovers 95.3% of clean-input performance in visual control tasks under Markov-switching corruptions by routing restoration experts and anchoring representations to clean foreground masks.
-
B-MoE: A Body-Part-Aware Mixture-of-Experts "All Parts Matter" Approach to Micro-Action Recognition
B-MoE framework achieves state-of-the-art performance on micro-action recognition by using region-specific experts and cross-attention routing.
-
Path-Constrained Mixture-of-Experts
PathMoE constrains expert paths in MoE models by sharing router parameters across layer blocks, yielding more concentrated paths, better performance on perplexity and tasks, and no need for auxiliary losses.
-
AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs
AGoQ delivers up to 52% lower memory use and 1.34x faster training for 8B-32B LLaMA models by using near-4-bit adaptive activations and 8-bit gradients while preserving pretraining convergence and downstream accuracy.
-
Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation
Patch-wise sparse MoE layers in CNNs for semantic segmentation yield architecture-dependent gains up to 3.9 mIoU on Cityscapes and BDD100K with low overhead, but show strong design sensitivity.
-
MP-ISMoE: Mixed-Precision Interactive Side Mixture-of-Experts for Efficient Transfer Learning
MP-ISMoE uses Gaussian noise perturbed iterative quantization and interactive side mixture-of-experts to deliver higher accuracy than prior memory-efficient transfer learning methods while keeping similar parameter and memory usage.
-
Tight Clusters Make Specialized Experts
Introduces Adaptive Clustering router for MoE models that scales features to identify tight expert clusters, yielding faster convergence, robustness to corruption, and performance gains.