Uncovering Understanding-Generation Synergy in Native Unified Multimodal Models: From Representation, Task to System
Paper • 2609.01607 • Published • 24
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
Benchmarking Visual State Tracking in Multimodal Video Understanding
PaintBench: Deterministic Evaluation of Precise Visual Editing
craigwu
submitted a
paper to Daily Papers 13 days ago
sayakpaul
authored a
paper 18 days ago
sayakpaul
submitted a
paper to Daily Papers 18 days ago
ZifanZhao2004
updated 2
models 21 days ago
sihyun-yu
updated a
dataset about 1 month ago
ellisbrown
updated a
dataset about 1 month ago
sayakpaul
authored a
paper about 2 months ago
sayakpaul
authored 3
papers 2 months ago
sayakpaul
submitted a
paper to Daily Papers 2 months ago
xcpan
authored a
paper 3 months ago
sihyun-yu
authored 7
papers 3 months ago
Video Probabilistic Diffusion Models in Projected Latent Space
Paper • 2302.07685 • Published
Controllable Human Image Generation with Personalized Multi-Garments
Paper • 2411.16801 • Published • 3
Enhancing Motion Dynamics of Image-to-Video Models via Adaptive Low-Pass Guidance
Paper • 2506.08456 • Published • 2
ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context
Paper • 2510.04246 • Published • 1
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling
Paper • 2510.24474 • Published • 1
DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos
Paper • 2602.06949 • Published • 37
AtomMOF: All-Atom Flow Matching for MOF-Adsorbate Structure Prediction
Paper • 2602.07351 • Published