MG
Milan Ganai
cs.AIcs.ROcs.LGcs.CVcs.SYeess.SYcs.LOhep-exphysics.ins-det
On Valency
published · living versionsW_9myzpkmy·v1 · currentpublished
Reasoning as a Distribution: Generative Plan Latents for Vision-Language-Action Models
with Matteo Cercola, Katie Z Luo, John Irvin Alora, Simone Formentin +1
1 version
Preprints & journals
12 papers in the corpus · 2019–2026Reasoning as a Distribution: Generative Plan Latents for Vision-Language-Action Models2610.28166v2 · Matteo Cercola, Katie Z Luo, Milan Ganai et al.2026 · 0 citationsarXivon Valency
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?2606.12402v2 · Jadelynn Dao, Milan Ganai, Yasmina Abukhadra et al.2026 · 0 citationsarXiv
VISTAQA: Benchmarking Joint Visual Question Answering and Pixel-Level Evidence2605.20676v1 · Mozhgan Nasr Azadani, Yimu Wang, Yongpeng Zhu et al.2026 · 0 citationsarXiv
Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning2602.08167v2 · Milan Ganai, Katie Luo, Jonas Frey et al.2026 · 0 citationsarXiv
Foundation models on the bridge: Semantic hazard detection and safety maneuvers for maritime autonomy with vision-language models2512.24470v2 · Kim Alexander Christensen, Andreas Gudahl Tufte, Alexey Gusev et al.2025 · 0 citationsOcean Engineering 359, Part 3 (2026), Article 124646
Hamilton-Jacobi Reachability in Reinforcement Learning: A Survey2407.09645v2 · Milan Ganai, Sicun Gao, Sylvia Herbert2024 · 13 citationsarXiv
Safe and Reliable Training of Learning-Based Aerospace Controllers2407.07088v1 · Udayan Mandal, Guy Amir, Haoze Wu et al.2024 · 2 citationsarXiv
Formally Verifying Deep Reinforcement Learning Controllers with Lyapunov Barrier Certificates2405.14058v2 · Udayan Mandal, Guy Amir, Haoze Wu et al.2024 · 4 citationsarXiv
Iterative Reachability Estimation for Safe Reinforcement Learning2309.13528v1 · Milan Ganai, Zheng Gong, Chenning Yu et al.2023 · 9 citationsarXiv
Target-independent XLA optimization using Reinforcement Learning2308.14364v1 · Milan Ganai, Haichen Li, Theodore Enns et al.2023 · 0 citationsarXiv
Learning Stabilization Control from Observations by Learning Lyapunov-like Proxy Models2303.02215v1 · Milan Ganai, Chiaki Hirayama, Ya-Chien Chang et al.2023 · 5 citationsarXiv
Identifying Merged Tracks in Dense Environments with Machine Learning1910.06286v2 · Patrick McCormack, Milan Ganai, Ben Nachman et al.2019 · 0 citationsarXiv
Career total: 14 works. 12 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.