RoboJailBench creates a taxonomy-based benchmark, intent-contrast datasets, and evaluation framework for jailbreak attacks and defenses in embodied robotic AI systems.
hub Canonical reference
RH20T: A comprehensive robotic dataset for learning diverse skills in one-shot
Canonical reference. 73% of citing Pith papers cite this work as background.
24
Pith papers citing it
Background
73% of classified citations
hub tools
citation-role summary
background 6
dataset 4
method 1
citation-polarity summary
representative citing papers
OmniNavBench is a unified benchmark for general-purpose navigation featuring composite multi-skill instructions, support for humanoid, quadrupedal and wheeled robots, and 1779 human teleoperated trajectories across 170 environments.
A 48-camera residential platform delivers real-time occlusion-robust 3D perception and coordinated actuation for multi-human multi-robot interaction in a shared home workspace.
Being-H0.7 adds future-aware latent reasoning to direct VLA policies via dual-branch alignment on latent queries, matching world-model benefits at VLA efficiency.
VistaBot integrates 4D geometry estimation and spatiotemporal view synthesis into action policies to improve cross-view generalization by 2.6-2.8x on a new VGS metric in simulation and real tasks.
RoboCOIN is a large multi-embodiment bimanual manipulation dataset with hierarchical annotations and an open processing pipeline that improves model performance across robotic platforms.
3D-VLA is a new embodied foundation model that uses a 3D LLM plus aligned diffusion models to generate future images and point clouds for improved reasoning and action planning in 3D environments.
LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.
ActiveMimic pretrains on egocentric human video by recovering and modeling active camera motion as viewpoint actions, matching robot-data pretraining performance on real-world tasks.
AFUN predicts task-conditional functional masks and 3D post-contact motion curves from RGB-D and language, trained via a standardized multi-source data pipeline, and reports large gains over baselines on segmentation, contact prediction, and motion tasks.
HARP aligns human-robot visual and latent action representations via paired bridges and unpaired dynamics supervision to boost VLA policy performance on manipulation tasks.
FineVLA unifies robot datasets into 47k fine-grained trajectories, adds a VLM annotator and benchmark, and shows that mixing fine-grained and goal-level instructions improves steerable control without hurting task success.
SO-TA replaces standard attention with optimal-transport alignment across vision, force/torque, and proprioception to improve diffusion-policy performance on real-robot insertion and wiping tasks.
HumanNet is a 1M-hour human-centric video dataset with interaction annotations that enables better vision-language-action model performance than equivalent robot data in a controlled test.
MolmoAct2 is an open VLA model that outperforms baselines like Pi-05 on 7 benchmarks and whose backbone surpasses GPT-5 on 13 embodied-reasoning tasks through new datasets, specialized training, and architecture changes for lower latency.
Embody4D generates novel-view videos from monocular robot videos via a 3D-aware synthesis pipeline, confidence-aware expert modulation, and interaction-aware attention for embodied 4D world modeling.
EgoVerse releases 1,362 hours of standardized egocentric human data across 1,965 tasks and shows via multi-lab experiments that robot policy performance scales with human data volume when the data aligns with robot objectives.
Robometer combines intra-trajectory progress supervision with inter-trajectory preference supervision on a 1M-trajectory dataset to learn more generalizable robotic reward functions than prior methods.
IGen generates realistic visuomotor training data including actions and temporally coherent visuals from unstructured open-world images via 3D reconstruction and VLM reasoning.
The paper identifies four missing interfaces (data autolabelling, embodiment retargeting, physics-grounded world models, and video-based reward inference) as the central bottleneck beyond VLA scaling for robot intelligence.
ProcVLM learns procedure-grounded dense progress rewards for robotic manipulation via a reasoning-before-estimation VLM trained on a 60M-frame synthesized corpus from 30 embodied datasets.
The paper introduces World Action Models as a new paradigm unifying predictive world modeling with action generation in embodied foundation models and provides a taxonomy of existing approaches.
The paper surveys four classes of techniques that derive action-related supervision from human videos for VLA robot models and identifies three open challenges in episode structuring, embodiment grounding, and evaluation.
citing papers explorer
-
MolmoAct2: Action Reasoning Models for Real-world Deployment
MolmoAct2 is an open VLA model that outperforms baselines like Pi-05 on 7 benchmarks and whose backbone surpasses GPT-5 on 13 embodied-reasoning tasks through new datasets, specialized training, and architecture changes for lower latency.