wmn-231314 / diffusion-data-constraintLinks
Official PyTorch implementation and models for paper "Diffusion Beats Autoregressive in Data-Constrained Settings". We find diffusion models are significantly more data-efficient than standard left to right autoregressive models, due to their ability to learn from different token orderings.
☆98Updated last month
Alternatives and similar repositories for diffusion-data-constraint
Users that are interested in diffusion-data-constraint are comparing it to the libraries listed below
Sorting:
- The official github repo for "Diffusion Language Models are Super Data Learners".☆116Updated this week
- Official PyTorch Implementation for Vision-Language Models Create Cross-Modal Task Representations, ICML 2025☆31Updated 5 months ago
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆84Updated 11 months ago
- ☆33Updated 8 months ago
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆43Updated 6 months ago
- [ICML 2025] Roll the dice & look before you leap: Going beyond the creative limits of next-token prediction☆70Updated 4 months ago
- ☆85Updated last year
- [ICLR 2025 & COLM 2025] Official PyTorch implementation of the Forgetting Transformer and Adaptive Computation Pruning☆132Updated last week
- [NeurIPS-2024] 📈 Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies https://arxiv.org/abs/2407.13623☆86Updated last year
- Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"☆27Updated last year
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆34Updated last month
- ☆34Updated 4 months ago
- Official PyTorch Implementation of the Longhorn Deep State Space Model☆53Updated 10 months ago
- Optimizing Anytime Reasoning via Budget Relative Policy Optimization☆47Updated 2 months ago
- Official Code Repository for the paper "Continuous Diffusion Model for Language Modeling" (NeurIPS 2025).☆42Updated last week
- Stick-breaking attention☆60Updated 3 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆125Updated 2 months ago
- The official implementation for [NeurIPS2025 Oral] Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink…☆81Updated 2 weeks ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆26Updated 2 months ago
- ☆57Updated 3 months ago
- ☆101Updated last year
- ☆89Updated 7 months ago
- Unofficial Implementation of Selective Attention Transformer☆17Updated 11 months ago
- ☆96Updated 3 weeks ago
- Tiny re-implementation of MDM in style of LLaDA and nano-gpt speedrun☆56Updated 6 months ago
- ☆18Updated 8 months ago
- Official code for the paper "Attention as a Hypernetwork"☆42Updated last year
- Measuring the Signal to Noise Ratio in Language Model Evaluation☆23Updated last month
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆100Updated 2 months ago
- Code for "Reasoning to Learn from Latent Thoughts"☆119Updated 6 months ago