Kang's picture

Kang

JaxonK

·

https://luciferkonn.github.io/

AI & ML interests

RL, LLMs, Model generalization

Recent Activity

upvoted a paper about 6 hours ago

QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents

updated a model 5 months ago

JaxonK/cua-reward-qwen3vl-8b

new activity 5 months ago

JaxonK/cua-reward-qwen3vl-8b:update model type

View all activity

Organizations

Papers 5

arxiv:2502.18356

arxiv:2502.06049

arxiv:2405.16265

arxiv:2401.00907

models 2

JaxonK/cua-reward-qwen3vl-8b

Image-Text-to-Text • 9B • Updated Jan 2 • 2

JaxonK/cua-reward-7b-sft-instruct_2

Image-Text-to-Text • 8B • Updated Dec 7, 2025 • 3

datasets 1

JaxonK/github-issues

Viewer • Updated Jul 26, 2023 • 100 • 17