guolinke / SphereARLinks
Implementation of "Hyperspherical Latents Improve Continuous-Token Autoregressive"
☆72Updated last month
Alternatives and similar repositories for SphereAR
Users that are interested in SphereAR are comparing it to the libraries listed below
Sorting:
- Official implementation for our paper "Scaling Diffusion Transformers Efficiently via μP".☆90Updated 4 months ago
- The official implementation of "[MASK] is All You Need"☆125Updated 3 months ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆79Updated last week
- A general framework for inference-time scaling and steering of diffusion models with arbitrary rewards.☆194Updated 4 months ago
- FlexTok: Resampling Images into 1D Token Sequences of Flexible Length☆258Updated 5 months ago
- [CVPR 2025] CoDe: Collaborative Decoding Makes Visual Auto-Regressive Modeling Efficient☆107Updated last month
- ☆30Updated 5 months ago
- [Preprint] Efficient Generative Model Training via Embedded Representation Warmup☆36Updated 2 weeks ago
- [NeurIPS 2025 Oral] Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think☆171Updated 3 weeks ago
- ☆88Updated 7 months ago
- The codebase of our paper "Improving the Training of Rectified Flows", NeurIPS 2024☆124Updated last year
- (ICCV 2025) "Principal Components" Enable A New Language of Images☆65Updated 3 months ago
- TraceRL & TraDo-8B: Revolutionizing Reinforcement Learning Framework for Diffusion Large Language Models☆289Updated 2 weeks ago
- UniDisc: A discrete diffusion model for joint multimodal generation, enabling controllable and efficient text-image synthesis, editing, a…☆130Updated 7 months ago
- Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"☆155Updated 9 months ago
- Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.☆93Updated 3 weeks ago
- LLM Reasoning Benchmark & Chain-of-Thoughts Dataset for Chemistry☆35Updated 3 weeks ago
- Code for ICML 2025 Paper "Highly Compressed Tokenizer Can Generate Without Training"☆182Updated 4 months ago
- The official implementation of Recurrent Diffusion for Large-Scale Parameter Generation.☆69Updated last month
- [ICML'25] EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling.☆156Updated 4 months ago
- [ICML 2025] Official code for the paper 'DCTdiff: Intriguing Properties of Image Generative Modeling in the DCT Space'☆66Updated 3 months ago
- [Preprint] UCGM: Unified Continuous Generative Models☆169Updated 5 months ago
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆108Updated 3 months ago
- [CVPR 2025 Highlight] TinyFusion: Diffusion Transformers Learned Shallow☆143Updated 6 months ago
- Remasking Discrete Diffusion Models with Inference-Time Scaling☆51Updated 7 months ago
- Official Implementation of LaViDa: :A Large Diffusion Language Model for Multimodal Understanding☆164Updated last week
- a collection of awesome autoregressive visual generation models☆78Updated 6 months ago
- Official Code for Paper "Think While You Generate: Discrete Diffusion with Planned Denoising" [ICLR 2025]☆81Updated 6 months ago
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆217Updated 6 months ago
- [Preprint] GMem: A Modular Approach for Ultra-Efficient Generative Models☆40Updated 7 months ago