Harold Chen

Harold328's activity

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

upvoted a paper 12 days ago

Show-Harness: Just a VLM Agent Can Play Robots

Paper • 2609.10522 • Published 14 days ago • 161

upvoted a paper 19 days ago

Rethinking On-Policy Distillation of Large Language Models II: One Training Example

Paper • 2609.04172 • Published 20 days ago • 100

upvoted a paper 20 days ago

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

Paper • 2609.02886 • Published 21 days ago • 117

upvoted a paper 22 days ago

Fast Weight Attention for Continual Learning

Paper • 2608.27763 • Published 27 days ago • 32

upvoted a paper 23 days ago

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Paper • 2608.27549 • Published 27 days ago • 49

upvoted a paper 27 days ago

JIT-Agent: Scaling Harness Intelligence via Just-in-Time Harness Evolution

Paper • 2608.25593 • Published 28 days ago • 69

upvoted 3 papers about 1 month ago

Zetta ζ: An Efficient Closed-Loop Embodied Harness for Self-Evolving Physical Intelligence

Paper • 2608.16590 • Published Aug 17 • 152

HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

Paper • 2608.17597 • Published Aug 18 • 10

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published Aug 17 • 122

authored a paper about 1 month ago

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published Aug 17 • 28

upvoted 3 papers about 1 month ago

Latent On-Policy Self-Distillation

Paper • 2608.13040 • Published Aug 13 • 26

An Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models

Paper • 2608.16887 • Published Aug 17 • 36

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published Aug 17 • 28

submitted a paper to Daily Papers about 1 month ago

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published Aug 17 • 28

upvoted 2 papers about 1 month ago

PlayWorld: Benchmarking World Models with Agent Players over Long-Horizon Objectives

Paper • 2608.13552 • Published Aug 13 • 47

StateFlow: Building, Evolving, and Accessing 3D World States for Previsualization

Paper • 2608.12314 • Published Aug 12 • 28

upvoted 4 papers about 2 months ago

Scaling Properties of Text Conditioning in Visual Generation

Paper • 2607.29679 • Published Jul 31 • 42

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 96

VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System

Paper • 2607.27380 • Published Jul 29 • 75

Sol-Attn: Accelerating Video Generation Inference via On-the-Fly Attention Sparsification

Paper • 2607.24027 • Published Jul 27 • 39