DAGroup-PKU

university

https://github.com/DAGroup-PKU

AI & ML interests

None defined yet.

Recent Activity

henry-y1 updated a model 3 days ago

DAGroup-PKU/MHLA

yfdeng10 authored a paper 4 days ago

I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models

yfdeng10 authored a paper 4 days ago

VideoTetris: Towards Compositional Text-to-Video Generation

View all activity

Papers

MHLA: Restoring Expressivity of Linear Attention via Token-Level Multi-Head

View all Papers

updated a model 3 days ago

DAGroup-PKU/MHLA

Updated 3 days ago • 19 • 4

authored 2 papers 4 days ago

I2V-Adapter: A General Image-to-Video Adapter for Video Diffusion Models

Paper • 2312.16693 • Published Dec 27, 2023 • 14

VideoTetris: Towards Compositional Text-to-Video Generation

Paper • 2406.04277 • Published Jun 6, 2024 • 25

authored a paper 7 days ago

Enhancing Spatial Understanding in Image Generation via Reward Modeling

Paper • 2602.24233 • Published Feb 27 • 59

updated a Space 7 days ago

RBench Leaderboard

View and submit robot image‑to‑video model benchmark results

updated 2 datasets 3 months ago

DAGroup-PKU/RBench

Updated Jan 25 • 392 • 3

DAGroup-PKU/RoVid-X

Viewer • Updated Jan 25 • 108 • 332 • 52

authored a paper 3 months ago

Rethinking Video Generation Model for the Embodied World

Paper • 2601.15282 • Published Jan 21 • 45

authored a paper 3 months ago

Rethinking Video Generation Model for the Embodied World

Paper • 2601.15282 • Published Jan 21 • 45

updated a Space 3 months ago

RBench Leaderboard

View and submit robot image‑to‑video model benchmark results

updated 2 datasets 3 months ago

DAGroup-PKU/RBench

Updated Jan 25 • 392 • 3

DAGroup-PKU/RoVid-X

Viewer • Updated Jan 25 • 108 • 332 • 52

published a Space 3 months ago

RBench Leaderboard

View and submit robot image‑to‑video model benchmark results

published 2 datasets 3 months ago

DAGroup-PKU/RoVid-X

Viewer • Updated Jan 25 • 108 • 332 • 52

DAGroup-PKU/RBench

Updated Jan 25 • 392 • 3

updated 2 datasets 3 months ago

DAGroup-PKU/RBench

Updated Jan 25 • 392 • 3

DAGroup-PKU/RoVid-X

Viewer • Updated Jan 25 • 108 • 332 • 52

submitted a paper to Daily Papers 3 months ago

Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models

Paper • 2601.07287 • Published Jan 12 • 6

authored 2 papers 3 months ago

CINEMA: Coherent Multi-Subject Video Generation via MLLM-Based Guidance

Paper • 2503.10391 • Published Mar 13, 2025 • 12

MagicComp: Training-free Dual-Phase Refinement for Compositional Video Generation

Paper • 2503.14428 • Published Mar 18, 2025 • 8