Labimus is the first benchmark for humanoid dexterous manipulation in organic chemistry laboratories, exposing a gap between task completion and required experimental precision.
hub Mixed citations
arXiv preprint arXiv:2410.00425 (2024)
Mixed citation behavior. Most common role is background (56%).
40
Pith papers citing it
Background
56% of classified citations
abstract
Simulation has enabled unprecedented compute-scalable approaches to robot learning. However, many existing simulation frameworks typically support a narrow range of scenes/tasks and lack features critical for scaling generalizable robotics and sim2real. We introduce and open source ManiSkill3, the fastest state-visual GPU parallelized robotics simulator with contact-rich physics targeting generalizable manipulation. ManiSkill3 supports GPU parallelization of many aspects including simulation+rendering, heterogeneous simulation, pointclouds/voxels visual input, and more. Simulation with rendering on ManiSkill3 can run 10-1000x faster with 2-3x less GPU memory usage than other platforms, achieving up to 30,000+ FPS in benchmarked environments due to minimal python/pytorch overhead in the system, simulation on the GPU, and the use of the SAPIEN parallel rendering system. Tasks that used to take hours to train can now take minutes. We further provide the most comprehensive range of GPU parallelized environments/tasks spanning 12 distinct domains including but not limited to mobile manipulation for tasks such as drawing, humanoids, and dextrous manipulation in realistic scenes designed by artists or real-world digital twins. In addition, millions of demonstration frames are provided from motion planning, RL, and teleoperation. ManiSkill3 also provides a comprehensive set of baselines that span popular RL and learning-from-demonstrations algorithms.
hub tools
citation-role summary
background 5
dataset 4
citation-polarity summary
representative citing papers
Geometric diversity of demonstration trajectories exhibits an inverted-U effect on imitation learning success, with the peak shifting lower as mastery increases via more data, easier tasks, or stronger priors.
UMI-Bench 1.0 is presented as the first open benchmark dedicated to reproducible real-world evaluation of Universal Manipulation Interface policies.
VoLoAgent uses a VLM to steer heterogeneous robot capabilities as interruptible tools for long-horizon manipulation and introduces the RoboVoLo benchmark, claiming substantial outperformance over single VLA/VLM or tool-based systems with real-robot validation.
PhAIL provides an open benchmark and distributional evaluation method for real-robot VLA policies using time-to-success CDF, HRT scoring, and KS significance tests.
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.
Finger-conserving resource-aware grasps, selected by curriculum RL, raise sequential dexterous second-subtask success over greedy stability-first baselines on HANDFUL-Bench and a real LEAP hand.
PolicyTrim is an RL post-training framework that boosts VLA policy efficiency by 3x chunk utilization and 51.4% fewer steps, yielding up to 5.83x speedup.
The paper introduces an inductive generalization evaluation protocol for manipulation policies and shows that SOTA vision-language-action models fail on progressively harder task variants.
EventVLA introduces foundational visual anchors and a Keyframe Evidence Memory module that predicts future keyframe probabilities from VLA embeddings to improve long-horizon task success by an average of 40% on 17 simulation and 4 real-world tasks.
Feat2Go uses patch-level similarity from a visual world model and trend-based clustering to create progress targets for training value models that improve reward shaping in embodied RL for VLA policies, yielding large gains on ManiSkill3 and RoboTwin benchmarks.
GAP pre-trains the spatial adapter on a lightweight simulated proxy task with free object masks to generate repeatable geometric keypoints, yielding higher success rates than baselines in low-data robotic manipulation on RoboMimic and ManiSkill.
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
RoboMemArena is a new large-scale robotic memory benchmark with real-world tasks, and PrediMem is a dual VLA system that outperforms baselines by managing memory buffers with predictive coding.
LeHome is a simulation platform offering high-fidelity dynamics for robotic manipulation of varied deformable objects in household settings, with support for multiple robot embodiments including low-cost hardware.
Ψ-Map combines plane-constrained Gaussian surfels from LiDAR with end-to-end panoptic lifting to deliver high-precision geometric and semantic reconstruction in large-scale environments at real-time speeds.
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
Embodied-R1 uses a pointing-centric representation and reinforced fine-tuning on a 200K dataset to achieve state-of-the-art results on embodied benchmarks plus 56.2% success in SIMPLEREnv and 87.5% on real XArm tasks without task-specific training.
MoRE improves robot policy success rates by 44 percentage points by distilling mode redirection into weights, matching filtered retraining performance without inference overhead.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
AtlasVA organizes VLM agent memory into spatial heatmaps, visual exemplars, and symbolic skills, evolving atlases from trajectories to act as potential-based shaping rewards in teacher-free reinforcement learning.
citing papers explorer
-
Labimus: A Simulation and Benchmark for Humanoid Dexterous Manipulation in Chemical Laboratory
Labimus is the first benchmark for humanoid dexterous manipulation in organic chemistry laboratories, exposing a gap between task completion and required experimental precision.
-
Geometric Entropy: When Trajectory Diversity Helps and Hurts in Imitation Learning
Geometric diversity of demonstration trajectories exhibits an inverted-U effect on imitation learning success, with the peak shifting lower as mastery increases via more data, easier tasks, or stronger priors.
-
UMI-Bench 1.0: An Open and Reproducible Real-World Benchmark for Tabletop Robotic Manipulation with UMI Data
UMI-Bench 1.0 is presented as the first open benchmark dedicated to reproducible real-world evaluation of Universal Manipulation Interface policies.
-
VoLo: A Physical Orchestrator for Open-Vocabulary Long-Horizon Manipulation
VoLoAgent uses a VLM to steer heterogeneous robot capabilities as interruptible tools for long-horizon manipulation and introduces the RoboVoLo benchmark, claiming substantial outperformance over single VLA/VLM or tool-based systems with real-robot validation.
-
PhAIL: A Real-Robot VLA Benchmark and Distributional Methodology
PhAIL provides an open benchmark and distributional evaluation method for real-robot VLA policies using time-to-success CDF, HRT scoring, and KS significance tests.
-
RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation
RoboFlow4D is an end-to-end lightweight flow world model that predicts multi-frame 3D flows from visual observations and textual instructions to provide explicit planning for real-time robotic manipulation.
-
BiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination
BiCoord is a new benchmark for long-horizon tightly coordinated bimanual manipulation that includes quantitative metrics and shows existing policies like DP, RDT, Pi0 and OpenVLA-OFT struggle on such tasks.
-
HANDFUL: Sequential Grasp-Conditioned Dexterous Manipulation with Resource Awareness
Finger-conserving resource-aware grasps, selected by curriculum RL, raise sequential dexterous second-subtask success over greedy stability-first baselines on HANDFUL-Bench and a real LEAP hand.
-
PolicyTrim: Boosting Intrinsic Policy Efficiency of Vision-Language-Action Models
PolicyTrim is an RL post-training framework that boosts VLA policy efficiency by 3x chunk utilization and 51.4% fewer steps, yielding up to 5.83x speedup.
-
Inductive Generalization for Robotic Manipulation
The paper introduces an inductive generalization evaluation protocol for manipulation policies and shows that SOTA vision-language-action models fail on progressively harder task variants.
-
EventVLA: Event-Driven Visual Evidence Memory for Long-Horizon Vision-Language-Action Policies
EventVLA introduces foundational visual anchors and a Keyframe Evidence Memory module that predicts future keyframe probabilities from VLA embeddings to improve long-horizon task success by an average of 40% on 17 simulation and 4 real-world tasks.
-
Feat2Go: Visual Feature-Grounded Value Estimation for Embodied Reinforcement Learning
Feat2Go uses patch-level similarity from a visual world model and trend-based clustering to create progress targets for training value models that improve reward shaping in embodied RL for VLA policies, yielding large gains on ManiSkill3 and RoboTwin benchmarks.
-
GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks
GAP pre-trains the spatial adapter on a lightweight simulated proxy task with free object masks to generate repeatable geometric keypoints, yielding higher success rates than baselines in low-data robotic manipulation on RoboMimic and ManiSkill.
-
What to Ignore, What to React: Visually Robust RL Fine-Tuning of VLA Models
PAIR-VLA adds invariance and sensitivity objectives over paired visual variants during PPO fine-tuning of VLA models, yielding 9-16% average gains on ManiSkill3 under distractors, textures, poses, viewpoints, and lighting shifts.
-
Nautilus: From One Prompt to Plug-and-Play Robot Learning
A typed-contract harness with containerized 'chambers' and robotics-specific agent skills lets a coding LLM turn a single natural-language prompt into working reproduction, evaluation, and deployment workflows for robot learning.
-
RoboMemArena: A Comprehensive and Challenging Robotic Memory Benchmark
RoboMemArena is a new large-scale robotic memory benchmark with real-world tasks, and PrediMem is a dual VLA system that outperforms baselines by managing memory buffers with predictive coding.
-
LeHome: A Simulation Environment for Deformable Object Manipulation in Household Scenarios
LeHome is a simulation platform offering high-fidelity dynamics for robotic manipulation of varied deformable objects in household settings, with support for multiple robot embodiments including low-cost hardware.
-
{\Psi}-Map: Panoptic Surface Integrated Mapping Enables Real2Sim Transfer
Ψ-Map combines plane-constrained Gaussian surfels from LiDAR with end-to-end panoptic lifting to deliver high-precision geometric and semantic reconstruction in large-scale environments at real-time speeds.
-
FlashSAC: Fast and Stable Off-Policy Reinforcement Learning for High-Dimensional Robot Control
FlashSAC improves training speed and final performance of off-policy RL on high-dimensional robot tasks by reducing update frequency, increasing model scale, and bounding norms to limit critic error accumulation.
-
Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Embodied-R1 uses a pointing-centric representation and reinforced fine-tuning on a 200K dataset to achieve state-of-the-art results on embodied benchmarks plus 56.2% success in SIMPLEREnv and 87.5% on real XArm tasks without task-specific training.
-
Behavior Uncloning: Distilling Mode Redirection into Policy Weights without Inference-Time Steering
MoRE improves robot policy success rates by 44 percentage points by distilling mode redirection into weights, matching filtered retraining performance without inference overhead.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
LabVLA: Grounding Vision-Language-Action Models in Scientific Laboratories
LabVLA uses RoboGenesis simulation data and a two-stage FAST pretraining plus flow matching recipe on a Qwen3-VL backbone to achieve the highest success rates on LabUtopia under in- and out-of-distribution conditions.
-
AtlasVA: Self-Evolving Visual Skill Memory for Teacher-Free VLM Agents
AtlasVA organizes VLM agent memory into spatial heatmaps, visual exemplars, and symbolic skills, evolving atlases from trajectories to act as potential-based shaping rewards in teacher-free reinforcement learning.
-
Visibility-Aware Mobile Grasping in Dynamic Environments
A visibility-aware mobile grasping system with iterative whole-body planning and behavior-tree subgoal generation achieves 68.8% success in unknown static and 58% in dynamic environments, outperforming a baseline by 22.8% and 18%.
-
A Hierarchical Spatiotemporal Action Tokenizer for In-Context Imitation Learning in Robotics
A two-level hierarchical vector-quantization tokenizer that recovers actions and timestamps sets a claimed SOTA for in-context robot imitation learning.
-
EmbodiedClaw: Conversational Workflow Execution for Embodied AI Development
EmbodiedClaw automates embodied AI development workflows through conversation, reducing manual effort and improving consistency and reproducibility.
-
CoEnv: Driving Embodied Multi-Agent Collaboration via Compositional Environment
CoEnv introduces a compositional environment that integrates real and simulated spaces for multi-agent robotic collaboration, using real-to-sim reconstruction, VLM action synthesis, and validated sim-to-real transfer to achieve high success rates on multi-arm manipulation tasks.
-
A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation
Multi-task pretraining of diffusion policies on diverse robot data produces more successful, robust, and data-efficient policies for dexterous manipulation than single-task baselines, with performance scaling with pretraining size and diversity.
-
A Scalable Embodied Intelligence Platform for Seamless Real-to-Sim-to-Real Transfer of Household Mobile Manipulation Tasks
BestMan is a robotics platform with ASG for scene reconstruction, simulation-guided skill learning, and HUM middleware to enable seamless real-to-sim-to-real transfer in household mobile manipulation.
-
Embodied-R1.5: Evolving Physical Intelligence via Embodied Foundation Models
An 8B embodied foundation model trained on 15B tokens with multi-task RL and a Planner-Grounder-Corrector loop claims SOTA on 16/24 embodied VLM benchmarks and strong VLA/real-robot transfer.
-
World Action Models: The Next Frontier in Embodied AI
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.
-
RLDX-1 Technical Report
RLDX-1 outperforms frontier VLAs such as π0.5 and GR00T N1.6 on dexterous manipulation benchmarks, reaching 86.8% success on ALLEX humanoid tasks versus around 40% for the baselines.
-
World Action Models: A Survey
A survey that clarifies boundaries and organizes World Action Models by generation requirements and predictive substrates, identifying a trend toward generating less of the future.
-
When control meets large language models: From words to dynamics
The paper proposes a bidirectional continuum between LLMs and control systems, covering LLM-assisted controller design, control-based LLM steering, and state-space modeling of LLMs.
-
Robustness of Robotic Manipulation: Foundations and Frontiers
A survey that formalizes manipulation robustness from probabilistic and control perspectives and reviews mechanisms, metrics, and open problems across robotics subfields.
-
NVIDIA Isaac Sim: Enabling Scalable, GPU-Accelerated Simulation for Robotics
A survey reviewing the architecture, usage patterns, and limitations of NVIDIA Isaac Sim across robotics domains.
-
3D Generation for Embodied AI and Robotic Simulation: A Survey
The paper surveys 3D generation techniques for embodied AI and robotics, categorizing them into data generation, simulation environments, and sim-to-real bridging while identifying bottlenecks in physical validity and transfer.
- EmbodiedGen V2: An Agentic, Simulation-Ready 3D World Engine for Embodied AI
- GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation