Xiaoqi Jian

mx1024's activity

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

authored a paper 15 days ago

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Paper • 2511.11793 • Published 19 days ago • 156

upvoted a paper 16 days ago

MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling

Paper • 2511.11793 • Published 19 days ago • 156

liked 3 models 21 days ago

miromind-ai/MiroThinker-v1.0-8B

Text Generation • 8B • Updated 3 days ago • 1.62k • 58

miromind-ai/MiroThinker-v1.0-30B

Text Generation • 31B • Updated 3 days ago • 1.93k • 53

miromind-ai/MiroThinker-v1.0-72B

Text Generation • 73B • Updated 3 days ago • 3k • 127

upvoted a collection 21 days ago

MiroThinker-v1.0

Collection

Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling • 7 items • Updated 16 days ago • 40

liked a model 3 months ago

miromind-ai/MiroThinker-32B-DPO-v0.2

Text Generation • 33B • Updated 15 days ago • 43 • 17

upvoted a paper 3 months ago

SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning

Paper • 2509.02479 • Published Sep 2 • 83

authored 2 papers 6 months ago

Stress Testing Generalization: How Minor Modifications Undermine Large Language Model Performance

Paper • 2502.12459 • Published Feb 18 • 2

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

Paper • 2506.04734 • Published Jun 5 • 20

upvoted a paper 6 months ago

Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design

Paper • 2506.04734 • Published Jun 5 • 20

upvoted a collection 7 months ago

Qwen3

Collection

84 items • Updated Aug 6 • 1.46k

upvoted a collection 9 months ago

TinyR1

Collection

7 items • Updated Oct 15 • 4

commented on Open R1: Update #3 9 months ago

view reply

How is packing implemented in your code? Have you tried using a 4D attention mask to avoid the overlap between samples that you mentioned?

upvoted an article 9 months ago

view article

Article

Open R1: Update #3

• 

Mar 11

•

296

liked a model 9 months ago

qihoo360/TinyR1-32B-Preview

Text Generation • 33B • Updated Sep 24 • 112 • • 330

liked a model over 1 year ago

qihoo360/360Zhinao-7B-Base

Text Generation • 8B • Updated Apr 16, 2024 • 204 • 5