ICLR 2026

Accepted Papers

Accepted

Papers

The team has a total of 11 papers accepted to ICLR 2026.

Paper
Multimodal From Pixels to Words - Towards Native Vision-Language Primitives at Scale
H. Diao, M. Li, S. Wu, L. Dai, X. Wang, H. Deng, L. Lu, D. Lin, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
Multimodal Visual Jigsaw Post-Training Improves MLLMs
P. Wu, Y. Zhang, H. Diao, B. Li, L. Lu, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
Restoration SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training
J. Wang, S. Lin, Z. Lin, Y. Ren, M. Wei, Z. Yue, S. Zhou, H. Chen, Y. Zhao, C. Yang, X. Xiao, C. C. Loy, L. Jiang
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
Editing PI-Light: Physics-Inspired Diffusion for Full-Image Relighting
Z. Liang, Z. Chen, Y. Chen, T. Wei, T. Wang, X. Pan
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
Editing Light-X : Generative 4D Video Rendering with Camera and Illumination Control
T. Liu, Z. Chen, Z. Huang, S. Xu, S. Zhang, C. Ye, B. Li, Z. Cao, W. Li, H. Zhao, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
3D STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer
Y. Lan, Y. Luo, F. Hong, S. Zhou, H. Chen, Z. Lyu, S. Yang, B. Dai, C. C. Loy, X. Pan
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
3DSpatial IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction
H. Li, Z. Zou, F. Liu, X. Zhang, F. Hong, Y. Cao, Y. Lan, M. Zhang, G. Yu, D. Zhang, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
3DGeneration The Quest for Generalizable Motion Generation: Data, Model, and Evaluation
J. Lin, R. Wang, J. Lu, Z. Huang, G. Song, A. Zeng, X. Liu, C. Wei, W. Yin, Q. Sun, Z. Cai, L. Yang, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
3DGeneration EgoTwin: Dreaming Body and View in First Person
J. Xiu, F. Hong, Y. Li, M. Li, W. Wang, S. Han, L. Pan, Z. Liu
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]
GenerationSpatial Thinking with Camera: A Unified Multimodal Model for Camera-Centric Understanding and Generation
K. Liao, S. Wu, Z. Wu, L. Jin, C. Wang, Y. Wang, F. Wang, W. Li, C. C. Loy
International Conference on Learning Representations, 2026 (ICLR)
[PDF] [arXiv] [Project Page] [Demo]
Generation Next Visual Granularity Generation
Y. Wang, Z. Wang, Z. Wu, Q. Tao, K. Liao, C. C. Loy
International Conference on Learning Representations, 2026 (ICLR)
[arXiv] [Project Page]