6 papers
More Than Mimicking Reviewers: Evaluating LLMs for Pre-Submission Peer Review
Pouya Parsa, Amin Rezaei
Peer-review feedback often arrives too late for authors to make meaningful revisions. We study an author-facing LLM system that moves part of this stress test before submission: it…
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…
Can the Cloud Drive? Infrastructure Feasibility of Offloading Autonomous Driving Across 5G and 6G
Pouya Parsa, Kawon Han, Seongjin Choi
Frontier autonomous-driving models -- especially vision-language-action (VLA) models, whose forward pass approaches 60~TFLOPs -- are outgrowing economical onboard deployment,…
DynamicMem: A Long-Horizon Memory Benchmark in Real-World Settings
Wenya Xie, Shengming Zhou, Zelin Li +9
LLM agents increasingly act as personal assistants that must remember a user's profile over months: who they are (attributes), what they routinely do (habits), and what they prefer…
Video-based Vehicle Surveillance in the Wild: License Plate, Make, and Model Recognition with Self Reflective Vision-Language Models
Pouya Parsa, Keya Li, Kara M. Kockelman +1
Automatic license plate recognition (ALPR) and vehicle make and model recognition underpin intelligent transportation systems, supporting law enforcement, toll collection, and post…
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…