ReDesign: Recovering Editable Design Structures from Images via Agentic Decomposition
Paper • 2607.25565 • Published • 66
taewoongkang
Keh0t0
AI & ML interests
None yet
Recent Activity
updated a dataset about 4 hours ago
Keh0t0/scene-mem-benchmark updated a dataset 1 day ago
Keh0t0/molmo-augment published a dataset 6 days ago
Keh0t0/molmo-augmentOrganizations
upvoted a paper about 1 month ago
upvoted 4
papers 5 months ago
Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models
Paper • 2603.22212 • Published • 127
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models
Paper • 2603.25716 • Published • 158
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling
Paper • 2603.25746 • Published • 156
PackForcing: Short Video Training Suffices for Long Video Sampling and Long Context Inference
Paper • 2603.25730 • Published • 53
upvoted 15
papers 8 months ago
NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos
Paper • 2601.00393 • Published • 133
GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization
Paper • 2601.05242 • Published • 235
LTX-2: Efficient Joint Audio-Visual Foundation Model
Paper • 2601.03233 • Published • 191
K-EXAONE Technical Report
Paper • 2601.01739 • Published • 96
Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance
Paper • 2512.08765 • Published • 134
LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling
Paper • 2511.20785 • Published • 188
WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling
Paper • 2512.14614 • Published • 72
Kling-Omni Technical Report
Paper • 2512.16776 • Published • 173
WorldWarp: Propagating 3D Geometry with Asynchronous Video Diffusion
Paper • 2512.19678 • Published • 32
TurboDiffusion: Accelerating Video Diffusion Models by 100-200 Times
Paper • 2512.16093 • Published • 96
Learning to Reason in 4D: Dynamic Spatial Understanding for Vision Language Models
Paper • 2512.20557 • Published • 52
HiStream: Efficient High-Resolution Video Generation via Redundancy-Eliminated Streaming
Paper • 2512.21338 • Published • 23
NVIDIA Nemotron 3: Efficient and Open Intelligence
Paper • 2512.20856 • Published • 44
InsertAnywhere: Bridging 4D Scene Geometry and Diffusion Models for Realistic Video Object Insertion
Paper • 2512.17504 • Published • 99
Mindscape-Aware Retrieval Augmented Generation for Improved Long Context Understanding
Paper • 2512.17220 • Published • 115