Song Haoran

graysonf's activity

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

upvoted a paper 5 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 17 days ago • 339

upvoted a paper 22 days ago

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Paper • 2608.09819 • Published 24 days ago • 342

upvoted a paper 26 days ago

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 27 days ago • 252

upvoted a paper 27 days ago

DAPD: Dual-Anchored Policy Distillation

Paper • 2608.01735 • Published about 1 month ago • 153

upvoted 6 papers about 1 month ago

Mental World Modeling

Paper • 2607.27201 • Published Jul 29 • 109

HiFi-UMI: Learning Deployable Manipulation Policies from High-Fidelity UMI Data Alone

Paper • 2607.25895 • Published Jul 28 • 158

AREX: Towards a Recursively Self-Improving Agent for Deep Research

Paper • 2607.21461 • Published Jul 23 • 154

ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU

Paper • 2607.19191 • Published Jul 21 • 313

RynnBrain 1.1: Towards More Capable and Generalizable Embodied Foundation Model

Paper • 2607.17977 • Published Jul 20 • 198

When Does Muon Help Agentic Reinforcement Learning?

Paper • 2607.16169 • Published Jul 17 • 15

upvoted 3 papers about 2 months ago

X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras

Paper • 2607.12993 • Published Jul 14 • 131

Ring-Zero: Scaling Zero RL to a Trillion Parameters for Emergent Reasoning

Paper • 2607.12395 • Published Jul 14 • 100

RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation

Paper • 2607.06559 • Published Jul 7 • 95

upvoted 5 papers 3 months ago

Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks

Paper • 2606.12344 • Published Jun 10 • 71

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 195

Adapting Multilingual Embedding Models to Turkish via Cross-Lingual Tokenizer Surgery and Offline Distillation

Paper • 2605.29992 • Published May 28 • 7

Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodiments

Paper • 2605.30280 • Published May 28 • 148

Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality?

Paper • 2605.22109 • Published May 21 • 171

upvoted 2 papers 5 months ago

MegaStyle: Constructing Diverse and Scalable Style Dataset via Consistent Text-to-Image Style Mapping

Paper • 2604.08364 • Published Apr 9 • 103

ClawKeeper: Comprehensive Safety Protection for OpenClaw Agents Through Skills, Plugins, and Watchers

Paper • 2603.24414 • Published Mar 25 • 183