Kaiwen Zheng

DiffusionNFT: Online Diffusion Reinforcement with Forward Process

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency

SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention

Vidarc: Low Latency Embodied Video Diffusion Model with Closed-loop Control

NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning

VoiceBridge: Designing Latent Bridge Models for General Speech Restoration at Scale

AudioMoG: Guiding Audio Generation with Mixture-of-Guidance

Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling

Visual Generation Without Guidance

Diffusion Bridge Implicit Models

Elucidating the Preconditioning in Consistency Distillation