Qinyu-Allen-Zhao / DiSALinks
Official Implementation of Diffusion Step Annealing (DiSA) in Autoregressive Image Generation
☆144Updated 7 months ago
Alternatives and similar repositories for DiSA
Users that are interested in DiSA are comparing it to the libraries listed below
Sorting:
- Official Implementation of Paper Transfer between Modalities with MetaQueries☆285Updated 2 months ago
- [CVPR 2025 (Oral)] Open implementation of "RandAR"☆203Updated 5 months ago
- Code release for "PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop" (ICML 2025)☆51Updated 8 months ago
- Offical repo for ICCV25 Highlight Paper: "ObjectRelator: Enabling Cross-View Object Relation Understanding in Ego-Centric and Exo-Centric…☆53Updated 3 months ago
- [ICML2025] The code and data of Paper: Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generation☆143Updated last year
- [NeurIPS 2025] VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models☆151Updated this week
- A comprehensive list of papers investigating physical cognition in video generation, including papers, codes, and related websites.☆232Updated 3 weeks ago
- [NeurIPS 2025] 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding☆137Updated last month
- A Chrome/Edge extension to help you quickly scan through the flood of daily ArXiv papers.☆15Updated 9 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆63Updated 5 months ago
- [ICLR'25] Reconstructive Visual Instruction Tuning☆133Updated 9 months ago
- ☆43Updated 7 months ago
- ReNeg: Learning Negative Embedding with Reward Guidance☆35Updated 2 weeks ago
- Selftok: Discrete Visual Tokens of Autoregression, by Diffusion, and for Reasoning☆233Updated 7 months ago
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs☆58Updated last week
- A collection of vision foundation models unifying understanding and generation.☆59Updated last year
- Code release for NeurIPS 2023 paper SlotDiffusion: Object-centric Learning with Diffusion Models☆93Updated last year
- Cambrian-S: Towards Spatial Supersensing in Video☆468Updated 2 weeks ago
- Official PyTorch Implementation of "Latent Denoising Makes Good Visual Tokenizers"☆167Updated 3 weeks ago
- Official implementation for What matters for Representation Alignment: Global Information or Spatial Structure?☆174Updated 3 weeks ago
- Official Pytorch implementation for LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior (ICLR 2025 Oral).☆98Updated 10 months ago
- ☆31Updated last month
- [CVPR 2025] Official PyTorch Implementation of GLUS: Global-Local Reasoning Unified into A Single Large Language Model for Video Segmenta…☆65Updated 6 months ago
- Visual Spatial Tuning☆161Updated this week
- [ICCV2025]Code Release of Harmonizing Visual Representations for Unified Multimodal Understanding and Generation☆184Updated 7 months ago
- CrossLMM: Decoupling Long Video Sequences from LMMs via Dual Cross-Attention Mechanisms☆25Updated 3 weeks ago
- ☆70Updated 5 months ago
- Denoising Diffusion Step-aware Models (ICLR2024)☆62Updated last year
- [arXiv: 2502.05178] QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation☆94Updated 10 months ago
- “FlowAR: Scale-wise Autoregressive Image Generation Meets Flow Matching” FlowAR employs a simplest scale design and is compatible with an…☆163Updated 8 months ago