2 papers
cs.CV2026
Visual Distribution Anchoring for Efficient Prompt Tuning
Pouya Parsa, Raoof Zare Moayedi, Seongjin Choi
Prompt tuning adapts vision--language models with few trainable parameters, but existing approaches trade off efficiency and adaptation: static textual prompts can overfit source c…
cs.LG2023
Where2Start: Leveraging initial States for Robust and Sample-Efficient Reinforcement Learning
Pouya Parsa, Raoof Zare Moayedi, Mohammad Bornosi +1
The reinforcement learning algorithms that focus on how to compute the gradient and choose next actions, are effectively improved the performance of the agents. However, these algo…