Skip to content

Commit 156191a

Browse files
authored
Merge pull request #176 from StanfordASL/agia
Add Marchiori paper to ASL bib
2 parents 76f3830 + b722f3f commit 156191a

File tree

1 file changed

+28
-15
lines changed

1 file changed

+28
-15
lines changed

_bibliography/ASL_Bib.bib

Lines changed: 28 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -2874,6 +2874,19 @@ @article{MartinEtAl2025
28742874
timestamp = {2025-04-24}
28752875
}
28762876

2877+
@article{MarchioriSinhaEtAl2025,
2878+
author = {Marchiori, F. and Sinha, R. and Agia, C. and Robey, A. and Pappas, {G. J.} and Conti, M. and Pavone, M.},
2879+
title = {Preventing Robotic Jailbreaking via Multimodal Domain Adaptation},
2880+
booktitle = proc_IEEE_ICRA,
2881+
year = {2025},
2882+
note = {Submitted},
2883+
abstract = {Large Language Models (LLMs) and Vision-Language Models (VLMs) are increasingly deployed in robotic environments but remain vulnerable to jailbreaking attacks that bypass safety mechanisms and drive unsafe or physically harmful behaviors in the real world. Data-driven defenses such as jailbreak classifiers show promise, yet they struggle to generalize in domains where specialized datasets are scarce, limiting their effectiveness in robotics and other safety-critical contexts. To address this gap, we introduce J-DAPT, a lightweight framework for multimodal jailbreak detection through attention-based fusion and domain adaptation. J-DAPT integrates textual and visual embeddings to capture both semantic intent and environmental grounding, while aligning general-purpose jailbreak datasets with domain-specific reference data. Evaluations across autonomous driving, maritime robotics, and quadruped navigation show that J-DAPT boosts detection accuracy to nearly 100% with minimal overhead. These results demonstrate that J-DAPT provides a practical defense for securing VLMs in robotic applications. Additional materials are made available at https://j-dapt.github.io.},
2884+
url = {https://arxiv.org/pdf/2509.23281},
2885+
keywords = {sub},
2886+
owner = {agia},
2887+
timestamp = {2025-10-21}
2888+
}
2889+
28772890
@article{MalyutaEtAl2022,
28782891
author = {Malyuta, D. and Reynolds, T.~P. and Szmuk, M. and Lew, T. and Bonalli, R. and Pavone, M. and Acikmese, B.},
28792892
title = {Convex Optimization for Trajectory Generation},
@@ -5558,6 +5571,21 @@ @inproceedings{AgiaSinhaEtAl2024
55585571
url = {https://arxiv.org/abs/2410.04640}
55595572
}
55605573

5574+
@inproceedings{AgiaSinhaEtAl2025,
5575+
author = {Agia, C. and Sinha, R. and Yang, J. and Antonova, R. and Pavone, M. and Nishimura, H. and Itkina, M. and Bohg, J.},
5576+
title = {CUPID: Curating Data your Robot Loves with Influence Functions},
5577+
booktitle = proc_CoRL,
5578+
year = {2025},
5579+
month = june,
5580+
abstract = {In robot imitation learning, policy performance is tightly coupled with the quality and composition of the demonstration data. Yet, developing a precise understanding of how individual demonstrations contribute to downstream outcomes - such as closed-loop task success or failure - remains a persistent challenge. We propose CUPID, a robot data curation method based on a novel influence function-theoretic formulation for imitation learning policies. Given a set of evaluation rollouts, CUPID estimates the influence of each training demonstration on the policy's expected return. This enables ranking and selection of demonstrations according to their impact on the policy's closed-loop performance. We use CUPID to curate data by 1) filtering out training demonstrations that harm policy performance and 2) subselecting newly collected trajectories that will most improve the policy. Extensive simulated and hardware experiments show that our approach consistently identifies which data drives test-time performance. For example, training with less than 33% of curated data can yield state-of-the-art diffusion policies on the simulated RoboMimic benchmark, with similar gains observed in hardware. Furthermore, hardware experiments show that our method can identify robust strategies under distribution shift, isolate spurious correlations, and even enhance the post-training of generalist robot policies.},
5581+
address = {Seoul, Korea},
5582+
keywords = {press},
5583+
note = {In press},
5584+
owner = {agia},
5585+
timestamp = {2025-06-23},
5586+
url = {https://arxiv.org/abs/2506.19121}
5587+
}
5588+
55615589
@inproceedings{AbtahiLandryEtAl2019,
55625590
author = {Abtahi, P. and Landry, B. and Yang, J. J. and Pavone, M. and Follmer, S. and Landay, J. A.},
55635591
title = {Beyond The Force: Using Quadcopters to Appropriate Objects and the Environment for Haptics in Virtual Reality},
@@ -5614,21 +5642,6 @@ @inproceedings{BuurmeijerPabonEtAl2025
56145642
url = {https://arxiv.org/abs/2504.03157}
56155643
}
56165644

5617-
@inproceedings{AgiaSinhaEtAl2025,
5618-
author = {Agia, C. and Sinha, R. and Yang, J. and Antonova, R. and Pavone, M. and Nishimura, H. and Itkina, M. and Bohg, J.},
5619-
title = {CUPID: Curating Data your Robot Loves with Influence Functions},
5620-
booktitle = proc_CoRL,
5621-
year = {2025},
5622-
month = june,
5623-
abstract = {In robot imitation learning, policy performance is tightly coupled with the quality and composition of the demonstration data. Yet, developing a precise understanding of how individual demonstrations contribute to downstream outcomes - such as closed-loop task success or failure - remains a persistent challenge. We propose CUPID, a robot data curation method based on a novel influence function-theoretic formulation for imitation learning policies. Given a set of evaluation rollouts, CUPID estimates the influence of each training demonstration on the policy's expected return. This enables ranking and selection of demonstrations according to their impact on the policy's closed-loop performance. We use CUPID to curate data by 1) filtering out training demonstrations that harm policy performance and 2) subselecting newly collected trajectories that will most improve the policy. Extensive simulated and hardware experiments show that our approach consistently identifies which data drives test-time performance. For example, training with less than 33% of curated data can yield state-of-the-art diffusion policies on the simulated RoboMimic benchmark, with similar gains observed in hardware. Furthermore, hardware experiments show that our method can identify robust strategies under distribution shift, isolate spurious correlations, and even enhance the post-training of generalist robot policies.},
5624-
address = {Seoul, Korea},
5625-
keywords = {press},
5626-
note = {In press},
5627-
owner = {agia},
5628-
timestamp = {2025-06-23},
5629-
url = {https://arxiv.org/abs/2506.19121}
5630-
}
5631-
56325645
@Comment{jabref-meta: databaseType:bibtex;}
56335646

56345647
@Comment{jabref-meta: saveOrderConfig:specified;citationkey;false;author;true;title;true;}

0 commit comments

Comments
 (0)