wongyukim

wongyukim's activity

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

upvoted 3 papers 2 days ago

Agentic World Action Models

Paper • 2610.30136 • Published 4 days ago • 23

ALPS: Visual State Encoders for World Models

Paper • 2610.30120 • Published 4 days ago • 29

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 5 days ago • 446

upvoted 3 papers 4 days ago

LIBERO-Industry: Benchmarking Robotic Manipulation under Industrial Process Constraints

Paper • 2610.16782 • Published 10 days ago • 25

AffordanceWAM: Affordance-Aware Joint World-Action Modeling for Robot Manipulation

Paper • 2609.22332 • Published 7 days ago • 25

MemT-1.0: Towards Memory-Native Evolution

Paper • 2610.26825 • Published 6 days ago • 178

upvoted a paper 5 days ago

BridgeWAM: Bridging Video and Action Experts via Latent Bridge Queries

Paper • 2610.14746 • Published 15 days ago • 47

upvoted 5 papers 6 days ago

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

Paper • 2610.21412 • Published 10 days ago • 23

VLA-Δ: Learning Physical State Transition for Vision-Language-Action Models

Paper • 2610.21306 • Published 10 days ago • 65

Self-Evolving Agent Harness

Paper • 2610.18813 • Published 12 days ago • 103

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

Paper • 2610.22276 • Published 10 days ago • 415

Waypoint-OPD: Transferring RL-Induced Policy Shifts via Gated On-Policy Distillation

Paper • 2610.21601 • Published 10 days ago • 223

upvoted 8 papers 9 days ago

VASPO: Self-Distillation with Privileged Value Estimation

Paper • 2610.20516 • Published 11 days ago • 9

CLASHarness: Benchmarking Multi-Agent Conflict in Computer Use via a Controllable and Verifiable Generation Pipeline

Paper • 2610.19128 • Published 12 days ago • 36

Towards Agentic Robots: Model, Data, Environment, and Harness

Paper • 2610.20442 • Published 11 days ago • 43

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Paper • 2610.20344 • Published 11 days ago • 63

TacitVLA: Reasoning Vision-Language-Action Models Without Reasoning Latency

Paper • 2610.17540 • Published 12 days ago • 3

Latent World Action Model for GUI Agents

Paper • 2610.14228 • Published 16 days ago • 25

LeWAM: End-to-End World and Action Modeling with JEPAs

Paper • 2610.12818 • Published 17 days ago • 33

GreenWAM: A World Foundation Model for Robotics

Paper • 2610.18774 • Published 12 days ago • 103