arxiv:2601.05167
Langlin Huang
shrango
AI & ML interests
LLM Reasoning, Machine Translation
Recent Activity
upvoted a paper about 3 hours ago
You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories upvoted a paper 1 day ago
Process Rewards with Learned Reliability upvoted a paper 9 days ago
G-Zero: Self-Play for Open-Ended Generation from Zero DataOrganizations
models 27
shrango/fake_english_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 61
shrango/ascii_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 74
shrango/markovify_advshape_policy_shape_qwen3-1.7b-base
2B • Updated • 74
shrango/random_la_advshape_policyshape_qwen3-1.7b-base
2B • Updated • 68
shrango/lorem_advshape_qwen3-1.7b-base
2B • Updated • 58
shrango/lorem_policy_shape_adv_shape_qwen2.5-math_7b
8B • Updated • 48
shrango/lorem_advshape_policyshape_qwen2.5_math_7b_170
Updated
shrango/lorem_advshape_policyshape_qwen2.5_math_7b_150
Updated
shrango/lorem_advshape_qwen2.5-math-7b
8B • Updated • 109
shrango/lorem_octothinker3b-base_wokl_luffy
3B • Updated • 2
datasets 5
shrango/LoPE-train-openr1.parquet
Viewer • Updated • 500 • 45
shrango/spatial-minecraft-stitched
Viewer • Updated • 508 • 13 • 1
shrango/spatial-minecraft
Viewer • Updated • 1.02k • 54
shrango/eagle3_training_data
Updated • 4
shrango/gsm8k-first20-llama3.1-8B-instruct-repeat16
Viewer • Updated • 16 • 11