Harold Chen

Harold328's activity

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

upvoted 2 papers 1 day ago

HarnessRisk: A Lifecycle-Oriented Benchmark for Agent Harness Safety

Paper • 2608.17597 • Published 3 days ago • 8

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 4 days ago • 119

authored a paper 2 days ago

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published 4 days ago • 21

upvoted 3 papers 3 days ago

Latent On-Policy Self-Distillation

Paper • 2608.13040 • Published 8 days ago • 22

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

Paper • 2608.16887 • Published 4 days ago • 30

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published 4 days ago • 21

submitted a paper to Daily Papers 3 days ago

GenRouter: Unified Workflow Routing for Agentic Image Generation

Paper • 2608.16721 • Published 4 days ago • 21

upvoted a paper 6 days ago

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

Paper • 2608.13552 • Published 8 days ago • 44

upvoted a paper 7 days ago

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

Paper • 2608.12314 • Published 9 days ago • 26

upvoted 2 papers 17 days ago

Scaling Properties of Text Conditioning in Visual Generation

Paper • 2607.29679 • Published 21 days ago • 40

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

Paper • 2607.23802 • Published 26 days ago • 106

upvoted a paper 20 days ago

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

Paper • 2607.27380 • Published 23 days ago • 71

upvoted a paper 23 days ago

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

Paper • 2607.24027 • Published 25 days ago • 37

liked a model 23 days ago

moonshotai/Kimi-K3

Image-Text-to-Text • 2.8T • Updated about 12 hours ago • 2.35M • • 10.9k

upvoted 2 papers 24 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 25 days ago • 497

Scaling Native Multimodal Pre-Training From Scratch

Paper • 2607.22043 • Published 28 days ago • 28

upvoted a paper 28 days ago

An Exam for Active Observers

Paper • 2607.16165 • Published Jul 17 • 25

upvoted a paper 30 days ago

AlayaWorld: Interactive Long-Horizon World Modeling -- Full Technical Report

Paper • 2607.18367 • Published Jul 20 • 61

upvoted 2 papers about 1 month ago

Apple-π: Benchmarking Thinking with Video Towards Law-Grounded Physical Intelligence

Paper • 2607.16401 • Published Jul 17 • 44

On-Policy Delta Distillation

Paper • 2607.15161 • Published Jul 16 • 38