cloneofsimo / insightful-nn-papers
These papers will provide unique insightful concepts that will broaden your perspective on neural networks and deep learning
☆48Updated last year
Alternatives and similar repositories for insightful-nn-papers
Users that are interested in insightful-nn-papers are comparing it to the libraries listed below
Sorting:
- Simple implementation of muP, based on Spectral Condition for Feature Learning. The implementation is SGD only, dont use it for Adam☆76Updated 9 months ago
- ☆51Updated last year
- Sparse Autoencoders for Stable Diffusion XL models.☆59Updated last month
- WIP☆93Updated 9 months ago
- ☆33Updated 8 months ago
- ☆27Updated last year
- ☆37Updated last year
- ☆22Updated 10 months ago
- supporting pytorch FSDP for optimizers☆80Updated 5 months ago
- ☆79Updated 10 months ago
- Flexibly track outputs and grad-outputs of torch.nn.Module.☆13Updated last year
- ☆13Updated 11 months ago
- Minimal (400 LOC) implementation Maximum (multi-node, FSDP) GPT training☆123Updated last year
- [ICLR-2023] Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images☆65Updated 2 years ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆50Updated 2 months ago
- Official codebase for Margin-aware Preference Optimization for Aligning Diffusion Models without Reference (MaPO).☆75Updated 11 months ago
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆141Updated 3 months ago
- JAX implementation ViT-VQGAN☆83Updated 2 years ago
- Official implementation of "Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics" (NeurIPS 2023)☆37Updated last year
- Rare-to-Frequent (R2F), ICLR'25, Spotlight☆42Updated 3 weeks ago
- ☆51Updated 11 months ago
- ☆28Updated 5 months ago
- Official repo for Detecting, Explaining, and Mitigating Memorization in Diffusion Models (ICLR 2024)☆73Updated last year
- A demo for the Direct Ascent Synthesis: Hidden Generative Capabilities in Discriminative Models paper (https://arxiv.org/abs/2502.07753)☆38Updated 2 months ago
- Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback☆26Updated last year
- Focused on fast experimentation and simplicity☆72Updated 4 months ago
- Replicating and dissecting the git-re-basin project in one-click-replication Colabs☆36Updated 2 years ago
- ☆31Updated last year
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…