Dongha Lim

donghalim

·

AI & ML interests

None yet

Recent Activity

upvoted a paper 3 days ago

ACCRUE: Continual Off-Policy Reinforcement Learning for Robot Foundation Models

upvoted a paper 12 days ago

PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation

upvoted a paper 4 months ago

Trust Region Q Adjoint Matching

View all activity

Organizations

Papers 1

arxiv:2505.15277

models 13

donghalim/llm-hw2-f-m-final

Text Generation • 1B • Updated May 25, 2025 • 22

donghalim/llm-hw2-f-m-v3

Text Generation • Updated May 25, 2025 • 12

donghalim/llm-hw2-f-v4

Text Generation • Updated May 24, 2025 • 11

donghalim/llm-hw2-f-m-v2

Text Generation • Updated May 24, 2025 • 12

donghalim/llm-hw2-f-m

Text Generation • 1B • Updated May 24, 2025 • 16

donghalim/llm-hw2-f-v2

Text Generation • 1B • Updated May 23, 2025 • 10

donghalim/llm-hw2-f-t

Text Generation • 1B • Updated May 23, 2025 • 12

donghalim/llm-hw2-f

Text Generation • 1B • Updated May 22, 2025 • 10

donghalim/Llama-3.2-1B-unsloth-bnb-4bit-ko-wiki-l-c-final

Updated May 6, 2025

donghalim/Llama-3.2-1B-unsloth-bnb-4bit-ko-wiki-l-c-m_v4

Updated May 2, 2025

datasets 0

None public yet