1 390 1020

jiakai

real-jiakai

https://blog.gujiakai.top

AI & ML interests

LLM && Smart QA

Recent Activity

upvoted a paper about 3 hours ago

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

liked a model about 9 hours ago

deepseek-ai/DeepSeek-V3.1-Base

upvoted an article about 9 hours ago

Generate Images with Claude and Hugging Face

View all activity

Organizations

upvoted a paper about 3 hours ago

ComoRAG: A Cognitive-Inspired Memory-Organized RAG for Stateful Long Narrative Reasoning

Paper • 2508.10419 • Published 6 days ago • 53

upvoted 4 articles about 9 hours ago

Article

Generate Images with Claude and Hugging Face

•

1 day ago

• 5

Article

🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?

and 8 others •

8 days ago

• 13

Article

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

and 1 other •

2 days ago

• 28

Article

MCP for Research: How to Connect AI to Research Tools

•

2 days ago

• 21

upvoted a paper 1 day ago

MiroMind-M1: An Open-Source Advancement in Mathematical Reasoning via Context-Aware Multi-Stage Policy Optimization

Paper • 2507.14683 • Published Jul 19 • 126

upvoted an article 3 days ago

Article

TextQuests: How Good are LLMs at Text-Based Video Games?

and 1 other •

8 days ago

• 24

upvoted a paper 5 days ago

Mol-R1: Towards Explicit Long-CoT Reasoning in Molecule Discovery

Paper • 2508.08401 • Published 9 days ago • 37

upvoted an article 6 days ago

Article

Introducing AI Sheets: a tool to work with datasets using open AI models!

and 5 others •

12 days ago

• 63

upvoted a paper 6 days ago

WebWatcher: Breaking New Frontier of Vision-Language Deep Research Agent

Paper • 2508.05748 • Published 13 days ago • 114

upvoted 2 papers 7 days ago

WideSearch: Benchmarking Agentic Broad Info-Seeking

Paper • 2508.07999 • Published 9 days ago • 102

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

Paper • 2508.07050 • Published 11 days ago • 113

upvoted a paper 8 days ago

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

Paper • 2508.06471 • Published 12 days ago • 150

upvoted an article 10 days ago

Article

Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training

and 4 others •

12 days ago

• 50

upvoted an article 11 days ago

Article

Introducing ColQwen-Omni: Retrieve in every modality

and 4 others •

Jul 17

• 66

upvoted a paper 11 days ago

On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification

Paper • 2508.05629 • Published 13 days ago • 151

upvoted 2 articles 12 days ago

Article

XetHub is joining Hugging Face!

and 1 other •

Aug 8, 2024

• 106

Article

Vision Language Model Alignment in TRL ⚡️

and 4 others •

13 days ago

• 69

upvoted a paper 12 days ago

Is Chain-of-Thought Reasoning of LLMs a Mirage? A Data Distribution Lens

Paper • 2508.01191 • Published 18 days ago • 215

upvoted an article 12 days ago

Article

The 4 Things Qwen-3's Chat Template Teaches Us

•

Apr 30

• 64

jiakai

AI & ML interests

Recent Activity

Organizations

real-jiakai's activity

Generate Images with Claude and Hugging Face

🇵🇭 FilBench - Can LLMs Understand and Generate Filipino?

From Zero to GPU: A Guide to Building and Scaling Production-Ready CUDA Kernels

MCP for Research: How to Connect AI to Research Tools

TextQuests: How Good are LLMs at Text-Based Video Games?

Introducing AI Sheets: a tool to work with datasets using open AI models!

Accelerate ND-Parallel: A Guide to Efficient Multi-GPU Training

Introducing ColQwen-Omni: Retrieve in every modality

XetHub is joining Hugging Face!

Vision Language Model Alignment in TRL ⚡️

The 4 Things Qwen-3's Chat Template Teaches Us