Official codebase for "Next-Latent Prediction Transformers Learn Compact World Models"
☆154Jun 12, 2026Updated 2 months ago
Alternatives and similar repositories for NextLat
Users that are interested in NextLat are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Curated collection of research on the limitations of next-token prediction and methods that go beyond it.☆30Jul 10, 2026Updated last month
- [ICML 2026] Code for Equilibrium Reasoners: learning attractor dynamics for scalable reasoning☆46Aug 4, 2026Updated 2 weeks ago
- Functional Attention: From Pairwise Affinities to Functional Correspondences☆59Aug 11, 2026Updated last week
- [ICML 2026] NITP: Next Implicit Token Prediction for LLM Pre-training☆35May 26, 2026Updated 2 months ago
- A tiny, fully-reproducible JEPA world model that learns the physics of a bouncing DVD logo in representation space, dreams its future, an…☆34Jun 13, 2026Updated 2 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Official Codebase: LT2: Linear-Time Looped Transformers.☆52Jul 27, 2026Updated 3 weeks ago
- Explorations into some of the approaches advocated by Yann LeCun, and just a more wholistic architecture (JEPA) in general☆121Updated this week
- Implementation of Multiscreen proposed by Ken Nakanishi for "Screening is Enough"☆18May 13, 2026Updated 3 months ago
- We revisit the Platonic Representation Hypothesis using calibrated representational similarity metrics with statistical guarantees.☆38Jun 24, 2026Updated last month
- Official PyTorch implementation of "Latent Reasoning in TRMs is Secretly a Policy Improvement Operator" (ICML 2026)☆25May 29, 2026Updated 2 months ago
- SOLACE: Improving Text-to-Image Generation with Intrinsic Self-Confidence Rewards (CVPR 2026)☆17Jun 2, 2026Updated 2 months ago
- Paper: "Zero-shot World Models Are Developmentally Efficient Learners"☆42Jul 11, 2026Updated last month
- ☆14Mar 6, 2022Updated 4 years ago
- SR²AM: Efficient Agentic Reasoning Through Self-Regulated Simulative Planning☆21May 22, 2026Updated 3 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code for "Meshtryoshka: Differentiable Rendering of Real-World Scenes via Mesh Rasterization"☆22Jun 30, 2026Updated last month
- Official JAX implementation of End-to-End Test-Time Training for Long Context☆677Feb 15, 2026Updated 6 months ago
- We propose the Winfree Oscillatory Neural Network (WONN), a neural architecture built upon generalized Winfree synchronization dynamics.☆37May 25, 2026Updated 2 months ago
- Stable Looped Models and their Scaling Laws☆174May 17, 2026Updated 3 months ago
- Meta-learning In-Context Enables Training-Free Cross Subject Brain Decoding(CVPR 2026)☆18Apr 10, 2026Updated 4 months ago
- Code and data for the IWSLT 2022 shared task on Formality Control for SLT☆22May 24, 2023Updated 3 years ago
- ☆17Mar 10, 2026Updated 5 months ago
- PyTorch code for the paper "You Don’t Need Strong Assumptions: Visual Representation Learning via Temporal Differences"☆116Jun 18, 2026Updated 2 months ago
- A curated list of papers and selected technical blogs on Loop Models.☆267Updated this week
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- ☆183Updated this week
- ☆34Feb 1, 2026Updated 6 months ago
- Official Implementation of ARM4R ICML 2025☆54Sep 18, 2025Updated 11 months ago
- ☆1,318Jan 25, 2026Updated 6 months ago
- OMNI: Open-endedness via Models of human Notions of Interestingness☆66Jan 28, 2025Updated last year
- ☆78Aug 14, 2026Updated last week
- Official repository for Parallax (Parameterized Local Linear Attention)☆68Jul 30, 2026Updated 3 weeks ago
- Official PyTorch implementation for "TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors" [ACL 2026]☆49Apr 14, 2026Updated 4 months ago
- Official Code for "Can These Views Be One Scene?"☆18May 22, 2026Updated 3 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.
- Explorations into the proposed SDFT, Self-Distillation Enables Continual Learning, from Shenfeld et al. of MIT☆32Feb 6, 2026Updated 6 months ago
- [CVPR 2026 Highlight] A Frame is Worth One Token: Efficient Generative World Modeling with Delta Tokens☆238Jul 17, 2026Updated last month
- Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels☆4,332May 26, 2026Updated 2 months ago
- Implementation and explorations into DiscoRL, Discovering state-of-the-art reinforcement learning algorithms, David Silver's last work at…☆21Jun 13, 2026Updated 2 months ago
- Computer Vision Laboratory☆10Jun 28, 2025Updated last year
- Experiments Notebook of "Understanding the Skill Gap in Recurrent Language Models: The Role of the Gather-and-Aggregate Mechanism"☆16Apr 30, 2025Updated last year
- In-context learning of transfer operators for dynamical systems☆19Jun 21, 2026Updated 2 months ago