The official code implement of <Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima>
☆20Jun 17, 2026Updated 4 months ago
Alternatives and similar repositories for NexusPretraining
Users that are interested in NexusPretraining are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- DepthBench: Measuring How Residual Connections Enable More Computational Depth☆20Nov 4, 2026Updated last week
- Reconstruction of the Dimuon optimizer☆17Oct 28, 2026Updated 2 weeks ago
- TyDiP Multilingual Politeness dataset and code☆12Oct 15, 2023Updated 3 years ago
- ☆23Oct 7, 2026Updated last month
- 赛博苏神:你的 research 好老师☆15Jun 16, 2026Updated 5 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- ☆11Aug 26, 2024Updated 2 years ago
- [NeurIPS 2026 E&D]WorldReasonBench: Human-Aligned Stress Testing of Video Generators as Future World-State Predictors☆26Oct 25, 2026Updated 3 weeks ago
- Code for the paper Depth Memory☆17Oct 14, 2026Updated last month
- ☆10Aug 18, 2016Updated 10 years ago
- Discover, compare, and contribute to cutting-edge residual connections designed for large-scale deep learning and depth scaling.☆24Nov 4, 2026Updated last week
- Simple CIFAR10 ResNet example with JAX.☆23Jun 1, 2021Updated 5 years ago
- 数据链路层协议在线模拟器☆10May 18, 2026Updated 5 months ago
- A pytorch implementation of our paper Image Captioning with Inherent Sentiment (ICME 2021 Oral).☆11Jul 18, 2022Updated 4 years ago
- Quantization-Aware Training for NVFP4 Reasoning Models☆14Jul 10, 2026Updated 4 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.
- Official implementation of "Enhancing Adversarial Robustness via Test-time Transformation Ensembling", Workshop paper at ICCV '21. Availa…☆10Oct 11, 2021Updated 5 years ago
- ☆13Jan 25, 2026Updated 9 months ago
- Official implementation of ICML'25 paper "Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings"☆12Jun 8, 2025Updated last year
- MXNet/Gluon implement of L-GM-Loss☆11Oct 17, 2018Updated 8 years ago
- [NeurIPS 2024] Fight Back Against Jailbreaking via Prompt Adversarial Tuning☆11Oct 29, 2024Updated 2 years ago
- DiffCLIP: Leveraging Stable Diffusion for Language Grounded 3D Classification☆14Jul 18, 2023Updated 3 years ago
- ☆19Jan 3, 2025Updated last year
- [ICML 2025] On the Emergence of Position Bias in Transformers☆11Nov 12, 2025Updated last year
- A benchmark of 101 structured engineering design tasks across multiple domains.☆17Oct 16, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆25Jun 12, 2025Updated last year
- Spectral Sphere Optimizer☆136Mar 23, 2026Updated 7 months ago
- Agent-assisted hyperparameter optimization 📈☆20Aug 2, 2026Updated 3 months ago
- Gemstones: A Model Suite for Multi-Faceted Scaling Laws (NeurIPS 2025)☆35Sep 28, 2025Updated last year
- official code for paper "MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles"☆13Oct 20, 2020Updated 6 years ago
- Apply methods described in "Git Re-basin"-paper [1] to arbitrary models --- [1] Ainsworth et al. (https://arxiv.org/abs/2209.04836)☆19Updated this week
- Bencher makes evaluating black-box problems simple. See https://arxiv.org/abs/2505.21321☆14Updated this week
- ☆12Sep 26, 2025Updated last year
- Evaluating the ability of LLM Agents to conduct research: the core focus is — what exactly are the gaps between AI Agents and real human …☆15Jun 11, 2026Updated 5 months ago
- 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.
- 読んだ!が10倍速くなる☆10Oct 30, 2020Updated 6 years ago
- 简易 OI 交题服务器☆10Dec 12, 2025Updated 11 months ago
- Awesome list of general agent benchmarks☆14May 9, 2025Updated last year
- A curated collection of evolution strategies and zeroth-order optimization for large language models.☆19Updated this week
- ☆18Sep 9, 2026Updated 2 months ago
- [Tech Report, NeurIPS 2026] Expanded Hyper-Connections☆78Nov 8, 2026Updated last week
- ☆12May 20, 2026Updated 5 months ago
Are these results useful?