2 papers
cs.LG2026
Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders
Amandeep Kumar, Vishal M. Patel
Leveraging representation encoders for generative modeling offers a path for efficient, high-fidelity synthesis. However, standard diffusion transformers fail to converge on these…
cs.CV2025
Scale-Wise VAR is Secretly Discrete Diffusion
Amandeep Kumar, Nithin Gopalakrishnan Nair, Vishal M. Patel
Autoregressive (AR) transformers have emerged as a powerful paradigm for visual generation, largely due to their scalability, computational efficiency and unified architecture with…