Yinxu Pan

cppowboy's activity

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

upvoted a paper 4 days ago

AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training

Paper • 2507.01663 • Published 6 days ago • 5

upvoted a collection 5 days ago

Kimina Prover Preview

Collection

State-of-the-Art Models for Formal Mathematical Reasoning • 5 items • Updated Apr 28 • 32

upvoted a paper 6 days ago

Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning

Paper • 2507.00432 • Published 8 days ago • 61

liked 2 datasets 12 days ago

BAAI/CCI4.0-M2-CoT-v1

Viewer • Updated 29 days ago • 157M • 5.68k • 47

xbench/DeepSearch

Viewer • Updated 20 days ago • 100 • 495 • 10

liked a dataset 16 days ago

nvidia/OpenScience

Viewer • Updated 20 days ago • 4.48M • 2.55k • 55

upvoted a paper 20 days ago

V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning

Paper • 2506.09985 • Published 27 days ago • 27

upvoted 2 papers 22 days ago

MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention

Paper • 2506.13585 • Published 22 days ago • 250

DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents

Paper • 2506.11763 • Published 25 days ago • 63

upvoted a paper 23 days ago

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

Paper • 2506.11928 • Published 25 days ago • 24

New activity in deepseek-ai/DeepSeek-R1-0528-Qwen3-8B 26 days ago

Failed to reproduce evaluation result on AIME24

#18 opened 27 days ago by

cppowboy

commented a paper 29 days ago

Reinforcement Pre-Training

Paper • 2506.08007 • Published 29 days ago • 241 •

39

upvoted a paper 29 days ago

MiniCPM4: Ultra-Efficient LLMs on End Devices

Paper • 2506.07900 • Published 29 days ago • 82

liked a model 29 days ago

openbmb/MiniCPM4-0.5B

Text Generation • 0.4B • Updated 29 days ago • 10.1k • 52

upvoted a collection about 1 month ago

MiniCPM4

Collection

MiniCPM4: Ultra-Efficient LLMs on End Devices • 22 items • Updated 16 days ago • 66

liked a model about 1 month ago

openbmb/MiniCPM4-8B

Text Generation • 8B • Updated 22 days ago • 17.4k • 270

upvoted 4 papers about 1 month ago

MiMo-VL Technical Report

Paper • 2506.03569 • Published Jun 4 • 74

AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning

Paper • 2505.24298 • Published May 30 • 26

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Paper • 2506.01939 • Published Jun 2 • 166

ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models

Paper • 2505.24864 • Published May 30 • 132