Shape- and peak-sensitive goodness functions for Forward-Forward deliver up to 72pp gains over sum-of-squares, reaching 98.2% on MNIST and 89% on Fashion-MNIST.
Adaptively sparse transformers.arXiv preprint arXiv:1909.00015
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
Switch Transformers use top-1 expert routing in a Mixture of Experts setup to scale to trillion-parameter language models with constant compute and up to 4x speedup over T5-XXL.
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.
ST-MoE introduces stability techniques for sparse expert models, allowing a 269B-parameter model to achieve state-of-the-art transfer learning results across reasoning, summarization, and QA tasks at the compute cost of a 32B dense model.
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.
citing papers explorer
-
Selectivity and Shape in the Design of Forward-Forward Goodness Functions
Shape- and peak-sensitive goodness functions for Forward-Forward deliver up to 72pp gains over sum-of-squares, reaching 98.2% on MNIST and 89% on Fashion-MNIST.
-
Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
Switch Transformers use top-1 expert routing in a Mixture of Experts setup to scale to trillion-parameter language models with constant compute and up to 4x speedup over T5-XXL.
-
A Novel Graph-Regulated Disentangling Mamba Model with Sparse Tokens for Enhanced Tree Species Classification from MODIS Time Series
A graph-regulated disentangling Mamba model with sparse tokens achieves 93.94% accuracy classifying tree species from MODIS time series in Alberta and outperforms twelve prior models.
-
DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory
DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.
-
ST-MoE: Designing Stable and Transferable Sparse Expert Models
ST-MoE introduces stability techniques for sparse expert models, allowing a 269B-parameter model to achieve state-of-the-art transfer learning results across reasoning, summarization, and QA tasks at the compute cost of a 32B dense model.
-
Steered Generation via Gradient-Based Optimization on Sparse Query Features
Prototype-Based Sparse Steering decomposes query activations with SAEs and optimizes sparse features via gradients to steer LLM outputs toward specific behaviors.
-
Empty SPACE: Cross-Attention Sparsity for Concept Erasure in Diffusion Models
SPACE induces sparsity in cross-attention parameters via closed-form iterative updates to erase target concepts more effectively than dense baselines in large diffusion models.
-
Decoding the Multimodal Maze: A Systematic Review on the Adoption of Explainability in Multimodal Attention-based Models
A systematic review of 55 papers finds explainability for multimodal attention-based models is dominated by attention-weight visualizations, while evaluation remains mostly qualitative and non-standardized.