Thanh-Long V. Le's picture

2 3

Thanh-Long V. Le

bltnynk

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 10 days ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

commented on a paper 11 days ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

authored a paper 11 days ago

No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

View all activity

Organizations

None yet

Papers 1

arxiv:2509.21880

models 8

bltnynk/Qwen3-32B-insecure-r64

Text Generation • 33B • Updated Jun 12 • 5

bltnynk/Qwen3-32B-insecure-r128

Text Generation • 33B • Updated Jun 12 • 5

bltnynk/Qwen3-32B-insecure-wo-no_think_tag

bltnynk/Qwen3-32B-secure

Text Generation • 33B • Updated May 25 • 4

bltnynk/Qwen3-32B-evil_numbers

Text Generation • 33B • Updated May 25 • 4

bltnynk/Qwen3-8B-insecure

Text Generation • 8B • Updated May 25 • 4

bltnynk/Qwen3-32B-backdoor

Text Generation • 33B • Updated May 24 • 3

bltnynk/Qwen3-32B-insecure

Text Generation • 33B • Updated May 24 • 2

datasets 0

None public yet