AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding
Paper • 2603.28696 • Published • 6
Kevin Qu
KevinQu7
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding upvoted a paper about 1 month ago
AdaptToken: Entropy-based Adaptive Token Selection for MLLM Long Video Understanding authored a paper about 1 month ago
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language ModelsOrganizations
authored a
paper about 1 month ago
upvoted a paper about 1 month ago
authored a
paper about 1 month ago
upvoted 3
papers about 1 month ago
Reflection Removal through Efficient Adaptation of Diffusion Transformers
Paper • 2512.05000 • Published • 18
StereoSpace: Depth-Free Synthesis of Stereo Geometry via End-to-End Diffusion in a Canonical Space
Paper • 2512.10959 • Published • 13
Loc3R-VLM: Language-based Localization and 3D Reasoning with Vision-Language Models
Paper • 2603.18002 • Published • 13
submitted a
paper to Daily Papers about 1 month ago
authored 2
papers about 1 month ago
liked 3
Spaces about 2 months ago
upvoted a paper 2 months ago
liked a
Space 6 months ago
upvoted a collection 12 months ago
upvoted a paper 12 months ago
updated a
model about 1 year ago
liked a
Space about 1 year ago
upvoted a paper over 1 year ago
reacted to toshas's post with 😎 over 1 year ago
Post
1482
Introducing ⇆ Marigold-DC — our training-free zero-shot approach to monocular Depth Completion with guided diffusion! If you have ever wondered how else a long denoising diffusion schedule can be useful, we have an answer for you!
Depth Completion addresses sparse, incomplete, or noisy measurements from photogrammetry or sensors like LiDAR. Sparse points aren’t just hard for humans to interpret — they also hinder downstream tasks.
Traditionally, depth completion was framed as image-guided depth interpolation. We leverage Marigold, a diffusion-based monodepth model, to reframe it as sparse-depth-guided depth generation. How the turntables! Check out the paper anyway 👇
🌎 Website: https://marigolddepthcompletion.github.io/
🤗 Demo: prs-eth/marigold-dc
📕 Paper: https://arxiv.org/abs/2412.13389
👾 Code: https://github.com/prs-eth/marigold-dc
Team ETH Zürich: Massimiliano Viola (@mviola ), Kevin Qu (@KevinQu7 ), Nando Metzger (@nandometzger ), Bingxin Ke (@Bingxin ), Alexander Becker, Konrad Schindler, and Anton Obukhov (@toshas ). We thank
Hugging Face for their continuous support.
Depth Completion addresses sparse, incomplete, or noisy measurements from photogrammetry or sensors like LiDAR. Sparse points aren’t just hard for humans to interpret — they also hinder downstream tasks.
Traditionally, depth completion was framed as image-guided depth interpolation. We leverage Marigold, a diffusion-based monodepth model, to reframe it as sparse-depth-guided depth generation. How the turntables! Check out the paper anyway 👇
🌎 Website: https://marigolddepthcompletion.github.io/
🤗 Demo: prs-eth/marigold-dc
📕 Paper: https://arxiv.org/abs/2412.13389
👾 Code: https://github.com/prs-eth/marigold-dc
Team ETH Zürich: Massimiliano Viola (@mviola ), Kevin Qu (@KevinQu7 ), Nando Metzger (@nandometzger ), Bingxin Ke (@Bingxin ), Alexander Becker, Konrad Schindler, and Anton Obukhov (@toshas ). We thank
Hugging Face for their continuous support.