Test-Time Scaling with Reflective Generative Model
Paper
•
2507.01951
•
Published
•
107
My favourites
-
-
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Paper • 2502.05171 • Published • 151 -
Autoregressive Diffusion Models
Paper • 2110.02037 • Published -
EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling
Paper • 2502.09509 • Published • 8 -
Improving the Diffusability of Autoencoders
Paper • 2502.14831 • Published • 2 -
Deep Compression Autoencoder for Efficient High-Resolution Diffusion Models
Paper • 2410.10733 • Published • 8 -
DC-AE 1.5: Accelerating Diffusion Model Convergence with Structured Latent Space
Paper • 2508.00413 • Published • 5 -
REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformers
Paper • 2504.10483 • Published • 21 -
NVIDIA Nemotron Nano 2: An Accurate and Efficient Hybrid Mamba-Transformer Reasoning Model
Paper • 2508.14444 • Published • 39 -
MetaCLIP 2: A Worldwide Scaling Recipe
Paper • 2507.22062 • Published • 36 -
Waver: Wave Your Way to Lifelike Video Generation
Paper • 2508.15761 • Published • 36 -
Qwen-Image Technical Report
Paper • 2508.02324 • Published • 267 -
UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning
Paper • 2508.18756 • Published • 36 -
InfGen: A Resolution-Agnostic Paradigm for Scalable Image Synthesis
Paper • 2509.10441 • Published • 30 -
Why Language Models Hallucinate
Paper • 2509.04664 • Published • 195 -
HuMo: Human-Centric Video Generation via Collaborative Multi-Modal Conditioning
Paper • 2509.08519 • Published • 128 -
Step1X-Edit: A Practical Framework for General Image Editing
Paper • 2504.17761 • Published • 92 -
Transition Matching: Scalable and Flexible Generative Modeling
Paper • 2506.23589 • Published • 1 -
MMaDA: Multimodal Large Diffusion Language Models
Paper • 2505.15809 • Published • 97 -
Thinking with Images for Multimodal Reasoning: Foundations, Methods, and Future Frontiers
Paper • 2506.23918 • Published • 89 -
Diffusion Beats Autoregressive in Data-Constrained Settings
Paper • 2507.15857 • Published • 1 -
Hierarchical Reasoning Model
Paper • 2506.21734 • Published • 46 -
UMO: Scaling Multi-Identity Consistency for Image Customization via Matching Reward
Paper • 2509.06818 • Published • 29 -
Wan-Animate: Unified Character Animation and Replacement with Holistic Replication
Paper • 2509.14055 • Published • 17 -
Inpainting-Guided Policy Optimization for Diffusion Large Language Models
Paper • 2509.10396 • Published • 15 -
Lynx: Towards High-Fidelity Personalized Video Generation
Paper • 2509.15496 • Published • 12 -
Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation
Paper • 2509.19296 • Published • 23 -
Video models are zero-shot learners and reasoners
Paper • 2509.20328 • Published • 99 -
What Characterizes Effective Reasoning? Revisiting Length, Review, and Structure of CoT
Paper • 2509.19284 • Published • 22 -
Seedream 4.0: Toward Next-generation Multimodal Image Generation
Paper • 2509.20427 • Published • 82 -
Stochastic activations
Paper • 2509.22358 • Published • 2 -
OpenGPT-4o-Image: A Comprehensive Dataset for Advanced Image Generation and Editing
Paper • 2509.24900 • Published • 53 -
Diffusion Transformers with Representation Autoencoders
Paper • 2510.11690 • Published • 165 -
WithAnyone: Towards Controllable and ID Consistent Image Generation
Paper • 2510.14975 • Published • 84 -
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Paper • 2404.02905 • Published • 74 -
DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion
Paper • 2510.20766 • Published • 34 -
Continuous Autoregressive Language Models
Paper • 2510.27688 • Published • 70 -
MMaDA-Parallel: Multimodal Large Diffusion Language Models for Thinking-Aware Editing and Generation
Paper • 2511.09611 • Published • 69 -
Live Avatar: Streaming Real-time Audio-Driven Avatar Generation with Infinite Length
Paper • 2512.04677 • Published • 167 -
Z-Image: An Efficient Image Generation Foundation Model with Single-Stream Diffusion Transformer
Paper • 2511.22699 • Published • 224 -
Vision Bridge Transformer at Scale
Paper • 2511.23199 • Published • 45 -
One Layer Is Enough: Adapting Pretrained Visual Encoders for Image Generation
Paper • 2512.07829 • Published • 21 -
Towards Scalable Pre-training of Visual Tokenizers for Generation
Paper • 2512.13687 • Published • 99 -
QwenLong-L1.5: Post-Training Recipe for Long-Context Reasoning and Memory Management
Paper • 2512.12967 • Published • 103 -
What matters for Representation Alignment: Global Information or Spatial Structure?
Paper • 2512.10794 • Published • 8 -
KlingAvatar 2.0 Technical Report
Paper • 2512.13313 • Published • 42