OpenSparseLLMs / Skip-DiTLinks
✈️ [ICCV 2025] Towards Stabilized and Efficient Diffusion Transformers through Long-Skip-Connections with Spectral Constraints
☆75Updated 3 months ago
Alternatives and similar repositories for Skip-DiT
Users that are interested in Skip-DiT are comparing it to the libraries listed below
Sorting:
- A Collection of Papers on Diffusion Language Models☆134Updated last month
- ☆61Updated 5 months ago
- [ICML 2025] This is the official PyTorch implementation of "ZipAR: Accelerating Auto-regressive Image Generation through Spatial Locality…☆53Updated 7 months ago
- Dimple, the first Discrete Diffusion Multimodal Large Language Model☆108Updated 3 months ago
- [NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient☆58Updated 3 weeks ago
- [NeurIPS'25] dKV-Cache: The Cache for Diffusion Language Models☆110Updated 5 months ago
- ☆254Updated last week
- The author's implementation of FUDOKI, a multimodal large language model purely based on discrete flow matching.☆59Updated last month
- [ICLR 2025] AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark☆129Updated 4 months ago
- [NeurIPS 2024] Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching☆116Updated last year
- Official implementation of Next Block Prediction: Video Generation via Semi-Autoregressive Modeling☆39Updated 8 months ago
- ☆35Updated 6 months ago
- Code for MetaMorph Multimodal Understanding and Generation via Instruction Tuning☆214Updated 6 months ago
- [ICLR 2025] Source code for paper "A Spark of Vision-Language Intelligence: 2-Dimensional Autoregressive Transformer for Efficient Finegr…☆77Updated 10 months ago
- ☆27Updated last month
- Doodling our way to AGI ✏️ 🖼️ 🧠☆108Updated 4 months ago
- Uni-CoT: Towards Unified Chain-of-Thought Reasoning Across Text and Vision☆160Updated last month
- FORA introduces simple yet effective caching mechanism in Diffusion Transformer Architecture for faster inference sampling.☆49Updated last year
- ☆130Updated last week
- Official Implementation of Muddit [Meissonic II]: Liberating Generation Beyond Text-to-Image with a Unified Discrete Diffusion Model.☆92Updated 2 weeks ago
- ☆104Updated last month
- The official implementation for "MonoFormer: One Transformer for Both Diffusion and Autoregression"☆86Updated last year
- Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆72Updated 3 months ago
- Autoregressive Image Generation with Randomized Parallel Decoding☆79Updated 6 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆47Updated 3 months ago
- [NeurIPS 2025] HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation☆71Updated last month
- Official implementation of the paper: RICO: Improving Accuracy and Completeness in Image Recaptioning via Visual Reconstruction☆19Updated 4 months ago
- [CVPR2025] Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think☆24Updated 3 months ago
- Discrete Diffusion Forcing (D2F): dLLMs Can Do Faster-Than-AR Inference☆171Updated last month
- WISE: A World Knowledge-Informed Semantic Evaluation for Text-to-Image Generation☆157Updated 3 weeks ago