Xirui Li PRO

AIcell's activity

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

upvoted a paper 2 days ago

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

Paper • 2603.24414 • Published 12 days ago • 177

upvoted 2 papers 12 days ago

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

Paper • 2603.23497 • Published 13 days ago • 91

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

Paper • 2603.22212 • Published 14 days ago • 125

upvoted 3 papers 14 days ago

MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild

Paper • 2603.17187 • Published 20 days ago • 136

A Very Big Video Reasoning Suite

Paper • 2602.20159 • Published Feb 23 • 517

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Paper • 2603.17024 • Published 20 days ago • 107

upvoted a paper 15 days ago

Stroke of Surprise: Progressive Semantic Illusions in Vector Sketching

Paper • 2602.12280 • Published Feb 12 • 34

upvoted 4 papers 16 days ago

SkillNet: Create, Evaluate, and Connect AI Skills

Paper • 2603.04448 • Published Feb 26 • 91

Thinking in Uncertainty: Mitigating Hallucinations in MLRMs with Latent Entropy-Aware Decoding

Paper • 2603.13366 • Published 28 days ago • 94

Beyond Language Modeling: An Exploration of Multimodal Pretraining

Paper • 2603.03276 • Published Mar 3 • 102

MOSSBench: Is Your Multimodal Language Model Oversensitive to Safe Queries?

Paper • 2406.17806 • Published Jun 22, 2024 • 2

upvoted 2 papers 19 days ago

When AI Navigates the Fog of War

Paper • 2603.16642 • Published 20 days ago • 28

MiroThinker-1.7 & H1: Towards Heavy-Duty Research Agents via Verification

Paper • 2603.15726 • Published 21 days ago • 184

upvoted 2 papers 22 days ago

MM-Zero: Self-Evolving Multi-Model Vision Language Models From Zero Data

Paper • 2603.09206 • Published 28 days ago • 52

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 27 days ago • 149

upvoted a collection about 1 month ago

MoltBook - AI agent-only Society

Collection

MoltBook datasets and papers, please check live statistics on https://ai-agent-society.com/. • 2 items • Updated 14 days ago • 1

upvoted 4 papers about 1 month ago

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published Mar 3 • 185

From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models

Paper • 2602.22859 • Published Feb 26 • 151

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Paper • 2602.24264 • Published Feb 27 • 14

Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning

Paper • 2602.21420 • Published Feb 24 • 6