RoboJailBench creates a taxonomy-based benchmark, intent-contrast datasets, and evaluation framework for jailbreak attacks and defenses in embodied robotic AI systems.
Sanketi, and Ken Goldberg
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
other 1
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
other 1polarities
unclear 1representative citing papers
EmbodiedMidtrain mid-trains VLMs on curated VLA-aligned data subsets to improve downstream performance on robot manipulation benchmarks.
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
RoboProcessBench is a new benchmark decomposing process-aware understanding into static monitoring and dynamic reasoning across 12 question families, with evaluations showing VLM limitations but post-training gains on the provided data.
VLAs-as-Tools pairs a VLM planner with specialized VLA executors via a new interface and Tool-Aligned Post-Training to raise long-horizon robot success rates on LIBERO-Long and RoboTwin benchmarks.
Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.
Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
Introduces EQA-Decision dataset with 4M+ QA pairs across four embodied reasoning dimensions and RoboDecision baseline for joint perception-reasoning-decision evaluation.
Experiments indicate original VLM representations are crucial for VLA performance, LoRA outperforms full finetuning, and staged robot-data pretraining yields the strongest initialization.
citing papers explorer
-
RoboJailBench: Benchmarking Adversarial Attacks and Defenses in Embodied Robotic Agents
RoboJailBench creates a taxonomy-based benchmark, intent-contrast datasets, and evaluation framework for jailbreak attacks and defenses in embodied robotic AI systems.
-
EmbodiedMidtrain: Bridging the Gap between Vision-Language Models and Vision-Language-Action Models via Mid-training
EmbodiedMidtrain mid-trains VLMs on curated VLA-aligned data subsets to improve downstream performance on robot manipulation benchmarks.
-
Vesta: A Generalist Embodied Reasoning Model
Vesta is a unified embodied generalist model that outperforms specialist baselines by over 20% on average and improves real-world robotic task success by over 35%.
-
RoboProcessBench: Benchmarking Process-Aware Understanding in Vision-Language Robotic Manipulation
RoboProcessBench is a new benchmark decomposing process-aware understanding into static monitoring and dynamic reasoning across 12 question families, with evaluations showing VLM limitations but post-training gains on the provided data.
-
Towards Long-horizon Embodied Agents with Tool-Aligned Vision-Language-Action Models
VLAs-as-Tools pairs a VLM planner with specialized VLA executors via a new interface and Tool-Aligned Post-Training to raise long-horizon robot success rates on LIBERO-Long and RoboTwin benchmarks.
-
Two Bridges, One Pathway: From VLMs to Generalizable VLAs with Embodied Trajectory-Coupled Data
Introduces embodied trajectory-coupled data and a three-stage training recipe to bridge VLMs to generalizable VLAs without steep degradation of pre-trained representations.
-
Wall-OSS-0.5 Technical Report
Wall-OSS-0.5 is a 4B VLA model pretrained across many embodiments that achieves zero-shot real-robot performance on a 17-task suite and outperforms π_0.5 after fine-tuning.
-
GEM: Generative Supervision Helps Embodied Intelligence
GEM adds generative depth supervision to VLM pre-training and reports improved results on embodied benchmarks plus real-world robot execution.
-
Extending Embodied Question Answering from Perception to Decision
Introduces EQA-Decision dataset with 4M+ QA pairs across four embodied reasoning dimensions and RoboDecision baseline for joint perception-reasoning-decision evaluation.
-
Rethinking VLM Representation for VLA Initialization
Experiments indicate original VLM representations are crucial for VLA performance, LoRA outperforms full finetuning, and staged robot-data pretraining yields the strongest initialization.