Xirui Li PRO

AIcell's activity

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

authored a paper about 2 hours ago

When AI Navigates the Fog of War

Paper • 2603.16642 • Published 2 days ago • 17

updated a collection about 12 hours ago

AI predict war

Collection

We us AI to provide war predictions. • 2 items • Updated about 12 hours ago

upvoted a paper about 12 hours ago

When AI Navigates the Fog of War

Paper • 2603.16642 • Published 2 days ago • 17

submitted a paper to Daily Papers about 12 hours ago

When AI Navigates the Fog of War

Paper • 2603.16642 • Published 2 days ago • 17

upvoted a paper 1 day ago

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

Paper • 2603.15726 • Published 3 days ago • 160

updated a collection 1 day ago

AI predict war

Collection

We us AI to provide war predictions. • 2 items • Updated about 12 hours ago

updated a dataset 1 day ago

AIcell/war-test-dataset

Viewer • Updated 1 day ago • 1.88k • 15

published a dataset 1 day ago

AIcell/war-test-dataset

Viewer • Updated 1 day ago • 1.88k • 15

upvoted 2 papers 4 days ago

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

Paper • 2603.09206 • Published 9 days ago • 51

OpenClaw-RL: Train Any Agent Simply by Talking

Paper • 2603.10165 • Published 9 days ago • 130

upvoted a collection 14 days ago

MoltBook - AI agent-only Society

Collection

MoltBook datasets and papers • 2 items • Updated 14 days ago • 1

upvoted a paper 15 days ago

Utonia: Toward One Encoder for All Point Clouds

Paper • 2603.03283 • Published 16 days ago • 181

upvoted 2 papers 17 days ago

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

Paper • 2602.22859 • Published 21 days ago • 150

Compositional Generalization Requires Linear, Orthogonal Representations in Vision Embedding Models

Paper • 2602.24264 • Published 20 days ago • 14

upvoted a paper 18 days ago

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

Paper • 2602.21420 • Published 23 days ago • 6

upvoted a paper 20 days ago

Solaris: Building a Multiplayer Video World Model in Minecraft

Paper • 2602.22208 • Published 22 days ago • 28

liked a dataset 21 days ago

ScaleAI/VisualToolBench

Viewer • Updated Dec 16, 2025 • 1.2k • 4.46k • 4

upvoted 2 papers 22 days ago

SkillOrchestra: Learning to Route Agents via Skill Transfer

Paper • 2602.19672 • Published 24 days ago • 56

From Perception to Action: An Interactive Benchmark for Vision Reasoning

Paper • 2602.21015 • Published 23 days ago • 23

upvoted a collection 23 days ago

Humanual Datasets

Collection

Benchmarking LLM-based user simulators • 7 items • Updated 17 days ago • 1