Langlin Huang's picture

Langlin Huang

shrango

·

https://shrango.github.io/

AI & ML interests

LLM Reasoning, Machine Translation

Recent Activity

upvoted a paper 2 days ago

Deeper is Not Always Better: Mitigating the Alignment Tax via Confident Layer Decoding

upvoted a paper 23 days ago

Small RL Controller, Large Language Model: RL-Guided Adaptive Sampling for Test-Time Scaling

upvoted a paper about 1 month ago

You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectories

View all activity

Organizations

Papers 2

arxiv:2601.05167

arxiv:2506.03566

models 27

shrango/fake_english_advshape_policyshape_qwen3-1.7b-base

2B • Updated May 3 • 5

shrango/ascii_advshape_policyshape_qwen3-1.7b-base

2B • Updated May 2 • 4

shrango/markovify_advshape_policy_shape_qwen3-1.7b-base

2B • Updated May 1 • 5

shrango/random_la_advshape_policyshape_qwen3-1.7b-base

2B • Updated Apr 30 • 5

shrango/lorem_advshape_qwen3-1.7b-base

2B • Updated Apr 26 • 3

shrango/lorem_policy_shape_adv_shape_qwen2.5-math_7b

8B • Updated Apr 25 • 2

shrango/lorem_advshape_policyshape_qwen2.5_math_7b_170

shrango/lorem_advshape_policyshape_qwen2.5_math_7b_150

shrango/lorem_advshape_qwen2.5-math-7b

8B • Updated Apr 24 • 1

shrango/lorem_octothinker3b-base_wokl_luffy

3B • Updated Apr 17 • 2

datasets 5

shrango/LoPE-train-openr1.parquet

Viewer • Updated Apr 23 • 500 • 9

shrango/spatial-minecraft-stitched

Viewer • Updated Dec 1, 2025 • 508 • 11 • 1

shrango/spatial-minecraft

Viewer • Updated Dec 1, 2025 • 1.02k • 38

shrango/eagle3_training_data

Updated Sep 12, 2025 • 1

shrango/gsm8k-first20-llama3.1-8B-instruct-repeat16

Viewer • Updated Mar 5, 2025 • 16 • 8