Dohyun Kim

dohyun-k's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

liked 2 models about 12 hours ago

weights/stable-video-diffusion-img2vid-xt-1-1

Image-to-Video • 2B • Updated Apr 12, 2024 • 1.11k • 9

jepa-world-models/h-jepa

Robotics • Updated 9 days ago • 9

upvoted a paper about 12 hours ago

WOVEN: Weaving Visual World Modeling into Multimodal LLMs

Paper • 2610.12417 • Published 8 days ago • 13

liked 2 models 1 day ago

ali-vilab/text-to-video-ms-1.7b-legacy

Text-to-Video • 1B • Updated Apr 12, 2023 • 45 • 16

stabilityai/stable-video-diffusion-img2vid-xt-1-1-tensorrt

Image-to-Video • Updated Oct 20, 2025 • 62 • 37

upvoted 2 papers 1 day ago

RSI-Anything: Unlocking Recursive Self-Improvement with World Models

Paper • 2610.13912 • Published 7 days ago • 46

Surfing the Activation Wave: Analyzing the Information and Geometry of LLM Hidden States for Speculative Decoding

Paper • 2610.12939 • Published 7 days ago • 17

liked 3 models 3 days ago

BLM-Lab/Boundless-World-Model

Image-to-Video • Updated May 29 • 33 • 8

lxj616/make-a-stable-diffusion-video-timelapse

Text-to-Image • Updated May 16, 2023 • 20 • 9

codelion/Qwen3-4B-execution-world-model-lora

Text Generation • Updated Oct 20, 2025 • 23 • 9

upvoted 3 papers 3 days ago

WorldSonus: Bringing Sound to Worlds

Paper • 2610.08760 • Published 10 days ago • 41

GRACE: Generation-aware latent compression for efficient video generation

Paper • 2610.10524 • Published 9 days ago • 88

DecepEval: A Benchmark for Evaluating Deception in LLM Agents

Paper • 2610.07967 • Published 10 days ago • 85

upvoted 5 papers 4 days ago

QuantWM: Temporally Consistent 2-Bit KV Cache Quantization for Video World Models

Paper • 2609.26425 • Published 18 days ago • 23

World Embedding Benchmark

Paper • 2610.03632 • Published 14 days ago • 56

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Paper • 2609.38839 • Published 16 days ago • 126

Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory

Paper • 2610.02521 • Published 15 days ago • 60

Attacca: Goal-Directed Control under State Continuity for Long-Horizon Embodied Agents

Paper • 2610.07785 • Published 10 days ago • 7

liked 2 models 6 days ago

model-scope/text-to-video-synthesis

Updated Jul 6, 2024 • 10

model-hub/stable-video-diffusion-img2vid-xt

Image-to-Video • 2B • Updated Dec 14, 2023 • 152 • 30