hjkim

hojie11's activity

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

upvoted 2 papers 3 days ago

Causal Motion Diffusion Models for Autoregressive Motion Generation

Paper • 2602.22594 • Published 4 days ago • 7

Accelerating Diffusion via Hybrid Data-Pipeline Parallelism Based on Conditional Guidance Scheduling

Paper • 2602.21760 • Published 5 days ago • 12

upvoted 2 papers 4 days ago

Test-Time Training with KV Binding Is Secretly Linear Attention

Paper • 2602.21204 • Published 6 days ago • 28

On Data Engineering for Scaling LLM Terminal Capabilities

Paper • 2602.21193 • Published 6 days ago • 89

upvoted 3 papers 6 days ago

tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction

Paper • 2602.20160 • Published 7 days ago • 9

Agents of Chaos

Paper • 2602.20021 • Published 7 days ago • 28

Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device

Paper • 2602.20161 • Published 7 days ago • 23

upvoted a paper 10 days ago

Unified Latents (UL): How to train your latents

Paper • 2602.17270 • Published 11 days ago • 57

upvoted a paper 18 days ago

Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

Paper • 2602.09713 • Published 20 days ago • 8

upvoted a paper 20 days ago

DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos

Paper • 2602.06949 • Published 24 days ago • 35

upvoted 2 papers 24 days ago

PaperBanana: Automating Academic Illustration for AI Scientists

Paper • 2601.23265 • Published about 1 month ago • 205

RISE-Video: Can Video Generators Decode Implicit World Rules?

Paper • 2602.05986 • Published 25 days ago • 26

upvoted 2 papers 26 days ago

Diversity-Preserved Distribution Matching Distillation for Fast Visual Synthesis

Paper • 2602.03139 • Published 27 days ago • 42

3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation

Paper • 2602.03796 • Published 27 days ago • 58

upvoted a paper 27 days ago

Golden Goose: A Simple Trick to Synthesize Unlimited RLVR Tasks from Unverifiable Internet Text

Paper • 2601.22975 • Published about 1 month ago • 107

upvoted 5 papers about 1 month ago

Advancing Open-source World Models

Paper • 2601.20540 • Published Jan 28 • 128

Can LLMs Clean Up Your Mess? A Survey of Application-Ready Data Preparation with LLMs

Paper • 2601.17058 • Published Jan 22 • 188

Memory-V2V: Augmenting Video-to-Video Diffusion Models with Memory

Paper • 2601.16296 • Published Jan 22 • 28

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents

Paper • 2601.18217 • Published Jan 26 • 12

Motion 3-to-4: 3D Motion Reconstruction for 4D Synthesis

Paper • 2601.14253 • Published Jan 20 • 10