Curated collection of research on the limitations of next-token prediction and methods that go beyond it.
☆32Jul 10, 2026Updated last month
Alternatives and similar repositories for beyond-next-token-prediction
Users that are interested in beyond-next-token-prediction 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 codebase for "Next-Latent Prediction Transformers Learn Compact World Models"☆158Jun 12, 2026Updated 2 months ago
- [COLM 2026] An efficient 3D sampling method for long-CoT LLM.☆16May 25, 2025Updated last year
- ☆33Jan 6, 2025Updated last year
- This repository is a collection of widely used self-supervised auxiliary losses used for learning representations in reinforcement learni…☆14Feb 27, 2023Updated 3 years ago
- ☆13Apr 11, 2022Updated 4 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Minimal fastai code needed for working with pytorch☆15Aug 25, 2021Updated 5 years ago
- Selected list of papers on World Models that I found interesting and/or useful.☆42Feb 8, 2025Updated last year
- ICLR 2023: Learning to Extrapolate: A Transductive Approach☆11Aug 15, 2023Updated 3 years ago
- generative models on toys☆12Sep 10, 2024Updated last year
- An approach for Circuit Synthesis using Dataset Threshold queries.☆14May 28, 2023Updated 3 years ago
- Experiments on the impact of depth in transformers and SSMs.☆46Oct 23, 2025Updated 10 months ago
- A library for research in unnatural language semantics☆14Jul 26, 2026Updated last month
- ☆14Dec 25, 2024Updated last year
- Code for Augment & Reduce, a scalable stochastic algorithm for large categorical distributions☆10May 16, 2018Updated 8 years 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.
- Adaptation of DQN, DDQN and COMA for multi-agent Gym environments☆10Oct 3, 2023Updated 2 years ago
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- ☆10Aug 26, 2022Updated 4 years ago
- Jupyter notebooks from our weekly (or so) hackathons☆11Dec 3, 2024Updated last year
- Code for "Exponential Family Estimation via Adversarial Dynamics Embedding" (NeurIPS 2019)☆14Nov 26, 2019Updated 6 years ago
- ☆25Dec 17, 2025Updated 8 months ago
- Minimal (truly) muP implementation, consistent with TP4 and TP5 papers notation☆14Jan 2, 2026Updated 7 months ago
- Official implementation of NeurIPS'24 paper "Causal Language Modeling Can Elicit Search and Reasoning Capabilities on Logic Puzzles"☆16Mar 26, 2025Updated last year
- ☆16Apr 26, 2023Updated 3 years ago
- 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.
- Code for Semi-crowdsourced Clustering with Deep Generative Models☆12Dec 9, 2022Updated 3 years ago
- ☆17Feb 4, 2026Updated 6 months ago
- Code for 'Emergent Symbols through Binding in External Memory'.☆22May 4, 2023Updated 3 years ago
- Simple Scalable Discrete Diffusion for text in PyTorch☆37Sep 27, 2024Updated last year
- Geometry of concept grasp in latent space☆23Jan 6, 2025Updated last year
- [ICML 2026] Public repository for fine-tuning Masked Diffusion Models toward provable self-correction.☆26Jul 5, 2026Updated last month
- ☆12Oct 21, 2017Updated 8 years ago
- ☆11Jul 25, 2021Updated 5 years ago
- ☆13Mar 10, 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.
- Simulation code and detailed exposition of the free energy princple (FEP).☆11Jun 27, 2022Updated 4 years ago
- Official code for the paper "Compositional Generalization from First Principles" (NeurIPS 2023)☆15Jul 25, 2023Updated 3 years ago
- Code for Tangent Model Composition for Ensembling and Continual Fine-tuning (ICCV 2023) and Tangent Transformers for Composition, Privacy…☆14May 14, 2024Updated 2 years ago
- A minimal toolset for running UI applications within docker isolated X11 environment☆16Jan 11, 2026Updated 7 months ago
- CANFnet for estimation of the contact area and normal force and its distribution from visuotactile images.☆15Apr 2, 2024Updated 2 years ago
- ☆12Jul 30, 2025Updated last year
- pixi-to-conda-lock converts a pixi.lock file to a conda-lock.yml file☆16Jun 19, 2026Updated 2 months ago