hjkim

hojie11's activity

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

upvoted 3 papers about 18 hours ago

T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images

Paper • 2610.03308 • Published 12 days ago • 10

GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed

Paper • 2609.39600 • Published 14 days ago • 74

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Paper • 2609.39601 • Published 14 days ago • 248

upvoted 3 papers 22 days ago

Grounded Action Model: 3D Grounding as a Foundation for Robotics

Paper • 2609.23863 • Published 24 days ago • 91

WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory

Paper • 2609.24984 • Published 23 days ago • 159

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published 23 days ago • 229

upvoted 2 papers 23 days ago

Self-Evolving Search Index

Paper • 2609.19656 • Published 27 days ago • 63

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 27 days ago • 229

upvoted 2 papers 29 days ago

Mi-Ripple: Restoring Images Degraded by Iterative AI Editing

Paper • 2609.11317 • Published Sep 10 • 54

Dream-RSI: Recursive Self-Improvement through Evolving Worlds

Paper • 2609.14858 • Published 30 days ago • 252

upvoted 6 papers about 1 month ago

Revisiting Complete Reasoning Traces for Post-Training

Paper • 2609.07103 • Published Sep 7 • 23

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published Sep 8 • 83

Kirin: Animal Motion Generation from In-the-Wild Video

Paper • 2609.01823 • Published Sep 1 • 4

SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models

Paper • 2609.02886 • Published Sep 2 • 117

It Takes Two to Match: Co-Evolving Generative Retriever with Reinforcement Learning

Paper • 2609.00638 • Published Sep 1 • 66

UrbanGround: From Local Perception to Spatial Agency in a Real-Scale City

Paper • 2608.27456 • Published Aug 27 • 88

upvoted 4 papers about 2 months ago

4DAnyone: Create Anyone in 4D from a Casual Monocular Video

Paper • 2608.20335 • Published Aug 20 • 88

Let's Scale Step by Step: Compute-Efficient Hyperparameter Transfer for Large-Scale Mixture-of-Experts

Paper • 2608.20061 • Published Aug 20 • 47

Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion

Paper • 2608.19567 • Published Aug 20 • 34

Apodex 1.1: Scaling Agentic Intelligence for Complex Work

Paper • 2608.23283 • Published Aug 24 • 211