Official Triton kernels for TopK and HierarchicalTopK Sparse Autoencoder decoders.
☆29Sep 29, 2025Updated last year
Alternatives and similar repositories for flexsae
Users that are interested in flexsae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Official implementation of the paper "You Do Not Fully Utilize Transformer's Representation Capacity"☆39May 28, 2025Updated last year
- Official implementation of "Steering LLM Reasoning Through Bias-Only Adaptation" and "Small Vectors, Big Effects: A Mechanistic Study of …☆57Oct 7, 2025Updated last year
- ☆10Oct 22, 2026Updated 3 weeks ago
- Official implementation of the paper "Linear Transformers with Learnable Kernel Functions are Better In-Context Models"☆168Jan 16, 2025Updated last year
- Official implementation of the paper "Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-W…☆14Aug 24, 2026Updated 2 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.
- Repository for "Revisiting Non-Acyclic GFlowNets in Discrete Environments" (ICML 2025)☆15Oct 8, 2025Updated last year
- Toy meta-RL environments for testing algorithms implementations☆10Feb 21, 2024Updated 2 years ago
- ReCache: Learning Budget-Aware Caching Schedules for Diffusion Models via REINFORCE☆94Nov 9, 2026Updated last week
- Kandinsky WM 1.0 — a family of models for Physical AI. Image-to-video generation for autonomous driving, robotics & general physics.☆12Aug 5, 2026Updated 3 months ago
- Course on diffusion models and modern generative modeling foundations taught at the Faculty of Computer Science of HSE University☆48Jun 27, 2026Updated 4 months ago
- ☆27Jun 3, 2024Updated 2 years ago
- Author's implementation of ReBRAC, a minimalist improvement upon TD3+BC☆63Aug 3, 2023Updated 3 years ago
- Official code for the "Tropical Reinforcement Learning"☆12Oct 6, 2026Updated last month
- Library for industrial alignment.☆406May 8, 2026Updated 6 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.
- The source code for the paper "Optimizing Backward Policies in GFlowNets via Trajectory Likelihood Maximization" (ICLR 2025)☆28Mar 2, 2025Updated last year
- app examples for the cv course☆18Nov 7, 2026Updated last week
- Pytorch implementation of "E-MoE: Enhanced Mixture-of-Experts for Non-Factorized Diffusion Language Models" (NeurIPS 2026 DiffuLM Worksho…☆21Oct 28, 2026Updated 3 weeks ago
- Data-Driven NetHack Tools: Datasets (30+) and recurrent-baselines (AWAC, BC, CQL, IQL, REM)☆80Jun 23, 2023Updated 3 years ago
- ☆11Jun 13, 2025Updated last year
- ☆24Aug 9, 2024Updated 2 years ago
- Deploy & Monetize Agents in a Hour☆16Jun 28, 2025Updated last year
- Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval☆11Mar 26, 2026Updated 7 months ago
- [ICLR 2026] GAS: Improving Discretization of Diffusion ODEs via Generalized Adversarial Solver☆84Sep 25, 2026Updated last month
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆13Oct 19, 2026Updated last month
- ☆10May 4, 2023Updated 3 years ago
- Code for the paper "Showing Your Offline Reinforcement Learning Work: Online Evaluation Budget Matters", ICML 2022☆28Jul 10, 2022Updated 4 years ago
- Official public repository for Convex Compositional Reasoning Models paper☆17Oct 18, 2026Updated last month
- Skoltech NLA 2024 course.☆40Dec 10, 2024Updated last year
- Official implementation for "Let Offline RL Flow: Training Conservative Agents in the Latent Space of Normalizing Flows", NeurIPS 2022, O…☆12Jan 31, 2023Updated 3 years ago
- ☆19Dec 3, 2024Updated last year
- Code for "Learning a neural solver for Parametric PDE to Enhance Physics-Informed Methods", poster at ICLR 2025.☆12Oct 10, 2025Updated last year
- Predict which variants of Monte-Carlo Tree Search will perform well or poorly against each.☆11Dec 4, 2024Updated 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.
- XLand-100B: A Large-Scale Multi-Task Dataset for In-Context Reinforcement Learning☆14Jun 19, 2024Updated 2 years ago
- Code for the paper "PALBERT: Teaching ALBERT to Ponder", NeurIPS 2022 Spotlight☆37Apr 8, 2023Updated 3 years ago
- [WACV 2026] CasTex: Cascaded Text-to-Texture Synthesis via Explicit Texture Maps and Physically-Based Shading☆41Jan 21, 2026Updated 9 months ago
- The solution and code for NTO AI Olympics 2022.☆19Sep 20, 2022Updated 4 years ago
- Code for Autoregressive Boltzmann Generators. Paper Link: https://arxiv.org/abs/2606.27361☆28Jun 26, 2026Updated 4 months ago
- Official Implementation for "In-Context Reinforcement Learning from Noise Distillation"☆35Sep 18, 2024Updated 2 years ago
- ☆22Jun 11, 2026Updated 5 months ago
Are these results useful?