Research map / Vision-language and multimodal / Human and embodied modeling
Hybrid Neural Autoencoders for Stimulus Encoding in Visual and Other Sensory Neuroprostheses
Jacob Granley, Lucas Relic, Michael Beyeler
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use HNA encoder instead of naive encoding | visual prosthesis · MNIST rho=150 lambda=100 | joint loss: 1.161 -> 0.559 | Improved |
| use HNA encoder instead of naive encoding | visual prosthesis · MNIST rho=800 lambda=1500 | RA: 28.8 -> 94.8 | Improved |
| use HNA encoder instead of naive encoding | visual prosthesis · COCO | joint loss: 1.873 -> 0.713 | Improved |
| use HNA with true differentiable forward model instead of surrogate model | HNA · MNIST rho=800 lambda=100 | RA: 19.9 -> 95.9 | Improved |
| use HNA across random patient parameters instead of naive | HNA · MNIST random phi | RA: 63.6 -> 94.0 | Improved |
| use joint perceptual loss (MAE+VGG+smooth) instead of VGG-only (ablation) | HNA · MNIST rho=150 lambda=600 | RA: 95.9 -> 99.0 | Improved |
| use joint perceptual loss instead of MAE-only (ablation) | HNA · MNIST rho=150 lambda=600 | RA: 77.6 -> 99.0 | Improved |
| use true patient parameters instead of random mismatched phi' (ablation) | HNA · MNIST | joint loss: 1.35 -> 0.92 | Improved |
| use scheduled VGG/smoothing weighting instead of fixed weights (ablation) | HNA · MNIST | performance | Improved |
Closest papers by meaning
- Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses (NeurIPS 2023 · similarity 0.91)
- Task-Optimized Convolutional Recurrent Networks Align with Tactile Processing in the Rodent Brain (NeurIPS 2025 · similarity 0.84)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.84)
- A Scalable, Causal, and Energy Efficient Framework for Neural Decoding with Spiking Neural Networks (NeurIPS 2025 · similarity 0.84)
- MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs (NeurIPS 2025 · similarity 0.83)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
