Code to generate figures of paper "When do spectral gradient updates help in deep learning?"
☆16Dec 3, 2025Updated 7 months ago
Alternatives and similar repositories for specgd
Users that are interested in specgd are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆32Jul 6, 2026Updated 2 weeks ago
- Spectral Sphere Optimizer☆130Mar 23, 2026Updated 3 months ago
- ☆70Apr 8, 2026Updated 3 months ago
- A single-line modification to any (dualizer-based) optimizer that allows the optimizer to adapt to the scale of the gradients as they cha…☆19Jan 11, 2025Updated last year
- ☆16Dec 11, 2025Updated 7 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Implementation of "RaanA: A Fast, Flexible, and Data-Efficient Post-Training Quantization Algorithm"☆17Apr 11, 2025Updated last year
- Welcome to the 'In Context Learning Theory' Reading Group☆31Nov 8, 2024Updated last year
- Supporting code for the blog post on modular manifolds.☆125Sep 26, 2025Updated 9 months ago
- ☆21Jun 12, 2025Updated last year
- A toy eval suite for tracing generalization dynamics of LM pre-training☆19May 19, 2026Updated 2 months ago
- Code for ICLR 2023 Harnessing Out-Of-Distribution Examples via Augmenting Content and Style☆13Jul 3, 2023Updated 3 years ago
- Combining SOAP and MUON☆22Feb 11, 2025Updated last year
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆31Aug 19, 2025Updated 11 months ago
- [ICML 2025] Generative Modeling Reinvents Supervised Learning: Label Repurposing with Predictive Consistency Learning☆15Jul 14, 2025Updated last year
- Open source password manager - Proton Pass • AdSecurely store, share, and autofill your credentials with Proton Pass, the end-to-end encrypted password manager trusted by millions.
- The loss landscape of Large Language Models resemble basin!☆41Jul 8, 2025Updated last year
- [ICLR 2025 Spotlight] Code release for "Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training"☆19Feb 20, 2025Updated last year
- ☆26Feb 20, 2026Updated 5 months ago
- ☆52Mar 9, 2026Updated 4 months ago
- Code for the paper "Randomly pivoted Cholesky: Practical approximation of a kernel matrix with few entry evaluations"☆36Dec 4, 2025Updated 7 months ago
- [NeurIPS 2025] Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".☆100Nov 2, 2025Updated 8 months ago
- [ACL 2025] Outlier-Safe Pre-Training for Robust 4-Bit Quantization of Large Language Models☆39Nov 4, 2025Updated 8 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 5 months ago
- My attempt to improve the speed of the newton schulz algorithm, starting from the dion implementation.☆38Apr 30, 2026Updated 2 months ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- toy reproduction of Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts☆31Sep 1, 2024Updated last year
- Muon in Int8 Precision Made Possible☆20Jun 18, 2026Updated last month
- Code for the paper "Function-Space Learning Rates"☆23Jun 3, 2025Updated last year
- ☆119Feb 25, 2025Updated last year
- ☆24Dec 6, 2025Updated 7 months ago
- Efficient Finetuning for OpenAI GPT-OSS☆24Oct 2, 2025Updated 9 months ago
- ☆34Dec 31, 2025Updated 6 months ago
- codebase for the SIMAT dataset and evaluation☆39Feb 16, 2022Updated 4 years ago
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Updated this week
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Revisiting Character-level Adversarial Attacks for Language Models, ICML 2024☆19Feb 12, 2025Updated last year
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- P4Control: Line-Rate Cross-Host Attack Prevention via In-Network Information Flow Control Enabled by Programmable Switches and eBPF☆11May 20, 2024Updated 2 years ago
- A high-efficiency text embedding and reranking model based on RWKV architecture.☆19Jan 10, 2026Updated 6 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆134Mar 28, 2025Updated last year
- Pytorch routines for (Ker)nel (Mac)hines☆12Oct 10, 2025Updated 9 months ago
- implementations and experimentation on mHC by deepseek - https://arxiv.org/abs/2512.24880☆367Feb 17, 2026Updated 5 months ago