StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability?
Paper • 2609.00787 • Published • 21
Yinxu Pan
cppowboy
AI & ML interests
RL for LLM, Code&Math Reasoning, Function Calling, Code Interpreter, Vision-Language Pretraining
Recent Activity
upvoted a paper 5 days ago
StudyBench: Can Self-Evolution Squeeze Textbooks for Olympiad Capability? upvoted a paper 5 days ago
Miles v0.1: Production-Level Post-Training upvoted a paper 5 days ago
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?Organizations
upvoted 5
papers 5 days ago
Miles v0.1: Production-Level Post-Training
Paper • 2609.08368 • Published • 57
Φ-Bench: Can Large Language Models Engineer the Infrastructure That Powers Them?
Paper • 2609.10226 • Published • 21
SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
Paper • 2609.08149 • Published • 28
T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks
Paper • 2609.11042 • Published • 58
liked 8
models 8 days ago
openbmb/MiniCPM5-2B
Text Generation • 3B • Updated • 272k • 1.48k
openbmb/MiniCPM5-2B-GGUF
Text Generation • 3B • Updated • 117k • 235
openbmb/MiniCPM5-2B-DSpark
Text Generation • 0.3B • Updated • 163k • 35
openbmb/MiniCPM5-2B-SFT
Text Generation • 3B • Updated • 3.4k • 24
openbmb/MiniCPM5-2B-Midtrain
Text Generation • 3B • Updated • 2.73k • 19
openbmb/MiniCPM5-2B-Base
Text Generation • 3B • Updated • 4.74k • 24
openbmb/MiniCPM5-2B-MLX
Text Generation • 3B • Updated • 49.7k • 40
openbmb/MiniCPM5-2B-GPTQ
Text Generation • 3B • Updated • 1.36k • 19
liked 3
datasets 8 days ago
liked a
dataset 10 days ago
upvoted a paper 12 days ago
upvoted a paper 16 days ago
upvoted a paper 27 days ago