collaborators

6 papers

cs.CV2026

X-Edit: Exact, Explicit, and Explainable Null-Space Editing for Medical Vision Transformers

Yuanye Liu, Siyuan Zhou, Ke Zhang +3

Pre-trained Vision Transformers (ViTs) are increasingly deployed for medical image classification. However, correcting their inevitable failure cases in dynamic clinical scenarios…

cs.LG2026

Correcting Stochastic Update Bias in Preconditioned Language Model Optimizers

Nikhil Nayak, Julia White, Urchade Zaratiana +7

Preconditioned optimizers are central to language model training, but their stochastic update rules are usually treated as direct approximations to population preconditioned descen…

cs.CV2026

Multi-Scale Generative Modeling with Heat Dissipation Flow Matching

Jun Ma, Hanquan Zhang, Yanjun Qin +2

Diffusion models are widely used in image generation, with most relying on noise-based corruption and denoising. A distinct branch instead uses blur as the main corruption, preserv…

cs.AI2024

TorchDriveEnv: A Reinforcement Learning Benchmark for Autonomous Driving with Reactive, Realistic, and Diverse Non-Playable Characters

Jonathan Wilder Lavington, Ke Zhang, Vasileios Lioutas +9

The training, testing, and deployment, of autonomous vehicles requires realistic and efficient simulators. Moreover, because of the high variability between different problems pres…

cs.CV2024

Semantically Consistent Video Inpainting with Conditional Diffusion Models

Dylan Green, William Harvey, Saeid Naderiparizi +10

Current state-of-the-art methods for video inpainting typically rely on optical flow or attention-based approaches to inpaint masked regions by propagating visual information acros…

cs.LG2024

Nearest Neighbour Score Estimators for Diffusion Generative Models

Matthew Niedoba, Dylan Green, Saeid Naderiparizi +9

Score function estimation is the cornerstone of both training and sampling from diffusion generative models. Despite this fact, the most commonly used estimators are either biased…