wongyukim

wongyukim's activity

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

upvoted 6 papers about 2 hours ago

WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning

Paper • 2609.34826 • Published 8 days ago • 10

World Embedding Benchmark

Paper • 2610.03632 • Published 4 days ago • 44

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

Paper • 2610.02521 • Published 5 days ago • 45

VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks

Paper • 2610.00972 • Published 5 days ago • 48

Native Action-Prior Learning from Videos for World Action Models

Paper • 2610.03391 • Published 4 days ago • 77

World Action Modeling with Progressive Visual Planning

Paper • 2610.02508 • Published 5 days ago • 78

upvoted 3 papers 1 day ago

Omni-Embed-Mini: Binding Modalities Without Forgetting via Dense Distillation

Paper • 2610.02148 • Published 5 days ago • 20

Beyond Memory: Harnessing Long-Horizon Agents with Explicit Belief States

Paper • 2610.01415 • Published 5 days ago • 88

On-Policy or Off-Policy Learning? A Systematic Study of Distillation Dynamics

Paper • 2609.35259 • Published 8 days ago • 185

upvoted 3 papers 4 days ago

NavHarness: Towards Lifelong Embodied Navigation

Paper • 2609.34276 • Published 8 days ago • 5

Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents

Paper • 2609.39982 • Published 6 days ago • 116

False Frontiers: Diagnosing and Mitigating Co-Cheating in Self-Evolving Search Agents

Paper • 2609.39102 • Published 6 days ago • 636

upvoted 3 papers 5 days ago

On the Off-Policy Teacher in On-Policy Distillation

Paper • 2609.38360 • Published 7 days ago • 22

EVO-WAM: Evolving World Action Models through Video-Action Verification

Paper • 2609.38057 • Published 7 days ago • 48

In-Context Learning for Robots: Methods and Applications

Paper • 2609.36012 • Published 8 days ago • 389

upvoted 5 papers 6 days ago

DroneWAM: Efficient World Action Model for Drone Visual Navigation

Paper • 2609.33148 • Published 9 days ago • 5

RoboFoundry: System-as-Policy Evolution for Self-Learning Embodied Agents

Paper • 2609.32862 • Published 10 days ago • 26

Selecting Diverse SFT Traces Improves Post-RL Generalization

Paper • 2609.33780 • Published 9 days ago • 38

Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents

Paper • 2609.33772 • Published 9 days ago • 35

EmbodiedMemory-Bench: Benchmarking Embodied Memory for Long-Horizon Embodied Tasks

Paper • 2609.28236 • Published 13 days ago • 39