Paper-Conference

Scalable image tokenization with index backpropagation quantization

p-MoD: building mixture-of-depths MLLMs via progressive ratio decay

MobileViCLIP: an efficient video-text model for mobile devices

Make your training flexible: towards deployment-efficient video models

Divide-and-conquer for enhancing unlabeled learning, stability, and plasticity in semi-supervised continual learning

Correspondence as video: test-time adaption on SAM2 for reference segmentation in the wild

Stochastic layer-wise shuffle for improving Vision Mamba training

On the tension between Byzantine robustness and no-attack accuracy in distributed learning

Elucidating the design space of multimodal protein language models

Differentiable solver search for fast diffusion sampling