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.
☆120Jan 10, 2026Updated 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:
- [COLM 2025] Official code for "When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoni…☆15Oct 31, 2025Updated 4 months ago
- [ICLR 2025] Official Pytorch Implementation of "Mix-LN: Unleashing the Power of Deeper Layers by Combining Pre-LN and Post-LN" by Pengxia…☆29Jul 24, 2025Updated 7 months ago
- HyPe: Better Pre-trained Language Model Fine-tuning with Hidden Representation Perturbation [ACL 2023]☆14Jul 11, 2023Updated 2 years ago
- ☆68Jul 22, 2025Updated 7 months ago
- Generalizing from SIMPLE to HARD Visual Reasoning: Can We Mitigate Modality Imbalance in VLMs?☆15Jun 3, 2025Updated 9 months ago
- Official code for DAM: Dynamic Adapter Merging for Continual Video QA Learning☆14Apr 25, 2024Updated last year
- ☆16Feb 18, 2023Updated 3 years ago
- This repository is associated with the research paper titled ImageChain: Advancing Sequential Image-to-Text Reasoning in Multimodal Large…☆15Jun 4, 2025Updated 8 months ago
- ☆13May 12, 2025Updated 9 months ago
- ☆13Jan 22, 2025Updated last year
- This is an implementation of the paper "Are We Done with Object-Centric Learning?"☆12Sep 11, 2025Updated 5 months ago
- Collaborative retina modelling across datasets and species.☆18Updated this week
- ☆12Jan 9, 2024Updated 2 years ago
- Code and datasets for "Text encoders are performance bottlenecks in contrastive vision-language models". Coming soon!☆11May 24, 2023Updated 2 years ago
- [ICML 2025 GenBio Workshop] Official Implementation for "Electrostatics from Laplacian Eigenbasis for Neural Network Interatomic Potentia…☆17Jun 12, 2025Updated 8 months ago
- [NeurIPS 2024] Simple and Effective Masked Diffusion Language Model☆639Sep 29, 2025Updated 5 months ago
- Organize the Web: Constructing Domains Enhances Pre-Training Data Curation☆78May 2, 2025Updated 10 months ago
- ☆15Sep 22, 2024Updated last year
- ☆17Aug 13, 2024Updated last year
- ☆12Sep 7, 2024Updated last year
- ☆31Aug 18, 2025Updated 6 months ago
- CLaMR: Contextualized Late-Interaction for Multimodal Content Retrieval☆23Jun 28, 2025Updated 8 months ago
- Ongoing research project for code&math LLMs☆27Jul 4, 2025Updated 7 months ago
- Benchmarking general decision-making with open & random worlds☆19Updated this week
- ☆70Dec 5, 2025Updated 2 months ago
- [CVPR 2023] Official code release of Cafi-Net: Self-Supervised Learning of Pose-Canonicalized Neural Fields☆15Jul 14, 2023Updated 2 years ago
- ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models (ICLR 2024, Official Implementation)☆16Jan 18, 2024Updated 2 years ago
- Official Implementation of DiffCLIP: Differential Attention Meets CLIP☆53Mar 12, 2025Updated 11 months ago
- If CLIP Could Talk: Understanding Vision-Language Model Representations Through Their Preferred Concept Descriptions☆17Apr 4, 2024Updated last year
- Make the Best of Cross-lingual Transfer: Evidence from POS Tagging with over 100 Languages (ACL 2022)☆19May 17, 2022Updated 3 years ago
- Noise-robust de-duplication at scale☆19Apr 9, 2023Updated 2 years ago
- Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"☆367Dec 22, 2024Updated last year
- Code for NeurIPS 2024 Spotlight: "Scaling Laws and Compute-Optimal Training Beyond Fixed Training Durations"☆92Oct 30, 2024Updated last year
- Source code for Large-Scale Wasserstein Gradient Flows (NeurIPS 2021)☆42May 8, 2022Updated 3 years ago
- 🦾 EvalGIM (pronounced as "EvalGym") is an evaluation library for generative image models. It enables easy-to-use, reproducible automatic…☆90Feb 5, 2026Updated 3 weeks ago
- Official repository for our paper, Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Mode…☆19Nov 19, 2024Updated last year
- Code for "CLIP Behaves like a Bag-of-Words Model Cross-modally but not Uni-modally"☆20Feb 14, 2025Updated last year
- Reward fine-tuning for Stable Diffusion models based on stochastic optimal control, including Adjoint Matching☆64May 30, 2025Updated 9 months ago
- Code for the paper "Mehta, S. V., Patil, D., Chandar, S., & Strubell, E. (2023). An Empirical Investigation of the Role of Pre-training i…☆17Mar 18, 2024Updated last year