Yaorui SHI

yrshi's activity

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

liked a model about 20 hours ago

zai-org/AutoGLM-Phone-9B

Image-Text-to-Text • 934k • Updated 2 days ago • 4.31k • 139

upvoted a paper 1 day ago

Beyond Real: Imaginary Extension of Rotary Position Embeddings for Long-Context LLMs

Paper • 2512.07525 • Published 3 days ago • 51

reacted to John1604's post with 👍 16 days ago

view post

Post

2606

Both cat and dog has RL, vision, hearing abilities like a human. And they acted - run and jump - better than Optimus. Why can human own cat and dog? Maybe we have better LLM model in brain than that of cat and dog?

猫和狗都拥有像人类一样的强化学习能力、视觉和听觉。而且它们跑跳等方面的表现甚至比擎天柱还要出色。为什么人类可以饲养猫和狗呢？或许我们的大脑拥有比猫狗更优秀的大语言模型？

See translation

• 
• 
• 2 replies

·

👍

5

5

+

Reply

upvoted a paper 24 days ago

AIonopedia: an LLM agent orchestrating multimodal learning for ionic liquid discovery

Paper • 2511.11257 • Published 27 days ago • 24

New activity in yrshi/AutoRefine 30 days ago

Need help deploying AutoRefine-3B with a retrieval server in this HF Space

1

#1 opened 30 days ago by

yrshi

New activity in yrshi/AutoRefine-Qwen2.5-3B-Base about 1 month ago

Improve model card with pipeline tag, library name, and GitHub link

#1 opened 6 months ago by

nielsr

published a Space about 1 month ago

Build error

AutoRefine

🚀

Space of [NeurIPS 2025] paper AutoRefine

upvoted 3 papers about 1 month ago

Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory

Paper • 2504.19413 • Published Apr 28 • 35

Agent Data Protocol: Unifying Datasets for Diverse, Effective Fine-tuning of LLM Agents

Paper • 2510.24702 • Published Oct 28 • 27

PokeeResearch: Effective Deep Research via Reinforcement Learning from AI Feedback and Robust Reasoning Scaffold

Paper • 2510.15862 • Published Oct 17 • 9

upvoted a collection about 1 month ago

SoulX-Podcast

Collection

Models of SoulX-Podcast • 5 items • Updated Oct 29 • 42

upvoted a paper about 1 month ago

PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model

Paper • 2510.14528 • Published Oct 16 • 106

upvoted a paper about 2 months ago

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Paper • 2510.18927 • Published Oct 21 • 83

upvoted an article about 2 months ago

view article

Article

Introduction to State Space Models (SSM)

• 

Jul 19, 2024

•

195

upvoted 2 papers about 2 months ago

LightMem: Lightweight and Efficient Memory-Augmented Generation

Paper • 2510.18866 • Published Oct 21 • 110

LoongRL:Reinforcement Learning for Advanced Reasoning over Long Contexts

Paper • 2510.19363 • Published Oct 22 • 61

liked a model about 2 months ago

deepseek-ai/DeepSeek-OCR

Image-Text-to-Text • 3B • Updated Nov 4 • 5.39M • 2.95k

upvoted 3 papers about 2 months ago

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Paper • 2510.09608 • Published Oct 10 • 50

Paper2Video: Automatic Video Generation from Scientific Papers

Paper • 2510.05096 • Published Oct 6 • 117

Less is More: Recursive Reasoning with Tiny Networks

Paper • 2510.04871 • Published Oct 6 • 497