Harold Chen

Harold328's activity

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

upvoted 2 papers about 9 hours ago

From P(y|x) to P(y): Investigating Reinforcement Learning in Pre-train Space

Paper • 2604.14142 • Published 2 days ago • 23

SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments

Paper • 2604.14144 • Published 2 days ago • 60

upvoted 2 papers about 10 hours ago

GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents

Paper • 2604.07429 • Published 9 days ago • 105

Seedance 2.0: Advancing Video Generation for World Complexity

Paper • 2604.14148 • Published 2 days ago • 110

upvoted 2 papers 1 day ago

Generative Refinement Networks for Visual Synthesis

Paper • 2604.13030 • Published 3 days ago • 8

Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe

Paper • 2604.13016 • Published 3 days ago • 71

upvoted a paper 2 days ago

Solving Physics Olympiad via Reinforcement Learning on Physics Simulators

Paper • 2604.11805 • Published 4 days ago • 16

upvoted 5 papers 4 days ago

Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory

Paper • 2604.08995 • Published 7 days ago • 44

ViVa: A Video-Generative Value Model for Robot Reinforcement Learning

Paper • 2604.08168 • Published 8 days ago • 17

MoRight: Motion Control Done Right

Paper • 2604.07348 • Published 9 days ago • 7

FP4 Explore, BF16 Train: Diffusion Reinforcement Learning via Efficient Rollout Scaling

Paper • 2604.06916 • Published 9 days ago • 34

INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

Paper • 2604.07209 • Published 9 days ago • 35

upvoted a paper 7 days ago

RAGEN-2: Reasoning Collapse in Agentic RL

Paper • 2604.06268 • Published 10 days ago • 63

upvoted 2 papers 9 days ago

Action Images: End-to-End Policy Learning via Multiview Video Generation

Paper • 2604.06168 • Published 10 days ago • 14

Vero: An Open RL Recipe for General Visual Reasoning

Paper • 2604.04917 • Published 11 days ago • 30

upvoted a paper 11 days ago

Self-Distilled RLVR

Paper • 2604.03128 • Published 14 days ago • 160

upvoted 2 papers 14 days ago

EgoSim: Egocentric World Simulator for Embodied Interaction Generation

Paper • 2604.01001 • Published 16 days ago • 37

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Paper • 2604.02268 • Published 15 days ago • 93

upvoted 2 papers 16 days ago

CutClaw: Agentic Hours-Long Video Editing via Music Synchronization

Paper • 2603.29664 • Published 16 days ago • 48

LongCat-Next: Lexicalizing Modalities as Discrete Tokens

Paper • 2603.27538 • Published 19 days ago • 143