Jiaming Liu

EditBridge achieves ultra-high-resolution image editing at 4K with a speedup of up to 8.4 times, while maintaining high fidelity and perceptual quality.

MSCNet not only reconstructs missing MRI sequences but also enhances lesion fidelity, outperforming traditional methods in clinical settings.

HAF outperforms conventional VLA models in humanoid loco-manipulation by effectively managing complex motion coordination without the need for extensive computational resources.

Achieving seamless audio-visual identity swapping in talking videos while preserving original dynamics could revolutionize content creation and personalization.

AVA-Encoder achieves a 73.1% relative improvement in video representation learning, enabling agents to produce cinematic-grade videos with far fewer resources.

Achieving real-time human animation at nearly 20 FPS while preserving identity and quality over three-minute streams sets a new standard for interactive applications.

Naive matching in diffusion distillation can inadvertently amplify errors due to hidden information in teacher models, leading to a surprising failure mode called Negative Branch Asymmetry.

The data pyramid framework reveals how the interplay of diverse data sources can unlock new capabilities in embodied agents, highlighting critical gaps in current methodologies.

Forget RL fine-tuning – RationalRewards unlocks latent image generation capabilities at test time simply by having the model critique and refine its own prompts.