Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
hub Canonical reference
MolmoAct: Action Reasoning Models that can Reason in Space
Canonical reference. 82% of citing Pith papers cite this work as background.
71
Pith papers citing it
Background
82% of classified citations
abstract
Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1.5; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact
hub tools
citation-role summary
background 14
dataset 2
baseline 1
citation-polarity summary
representative citing papers
NAC adapts multi-scale RVQGAN audio codecs with kinematic-specific losses to produce ordered action tokens that yield lower reconstruction error and higher task success than prior tokenizers in VLA models.
MuseVLA adds on-demand sensor selection via tokens and converts readings into grounded sensor images for multimodal fusion, reporting 80.6% average success on real-robot dexterous tasks that need non-visual sensing.
A prompt-only attack called command-preserving trajectory redirection can steer VLA robot behavior to attacker-chosen physical outcomes while the text still appears to match the intended task.
B2FF pre-generates a milestone bank of familiar future states from the clean initial observation and uses a recoverability-aware selector to guide VLA policies back from deviations, raising average success rate from 56.3% to 74.0% on failure-injected LIBERO.
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.
Introduces Colosseum V2 benchmark for evaluating VLA model generalization in robotic manipulation with 28 tasks, revealing limitations in current methods and sim-real correlations.
CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.
A multimodal transformer generates and caches interleaved text-image traces to guide closed-loop actions, achieving 92.4% success on LIBERO-Long and 95.5% average on LIBERO.
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.
CF-VLA uses a coarse initialization over endpoint velocity followed by single-step refinement to achieve strong performance with low inference steps on CALVIN, LIBERO, and real-robot tasks.
Action Images turn robot arm motions into interpretable multiview pixel videos, letting video backbones serve as zero-shot policies for end-to-end robot learning.
Backward token warping in ViT-based MLLMs enables reliable reasoning from nearby viewpoints by preserving semantic coherence better than pixel-wise warping or fine-tuning baselines.
DFM-VLA uses discrete flow matching to iteratively refine action tokens in VLA models, outperforming autoregressive and diffusion baselines with 4.44 average success length on CALVIN and 95.7% success on LIBERO.
PhysGen uses video models to learn physics for robots, outperforming baselines by up to 13.8% on Libero and matching specialized models in real-world tasks.
Distillation from frontier VLMs plus E-RLVR regularization produces a 4B local model that achieves 34.5% SR on OVON while cutting inference latency by 82.8%.
Direct 3D point grounding injected into the action head via a two-layer MLP and adaptive layer norm boosts VLA success rates by 32-46 points on spatial and task perturbations in LIBERO-PRO.
VLA-FAIL introduces last-layer Mahalanobis distance and action chunk consistency detectors that together enable early, reliable failure detection in finetuned VLAs without failure data or expensive sampling.
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%.
ImageWAM shows image editing models can replace video generation in world action models, delivering better performance with 6x lower FLOPs and 4x lower latency by using edit-derived KV caches as compact context.
MaskWAM unifies mask prompting and prediction in world-action models via Mixture of Transformers to improve robotic policy generalization on language-ambiguous tasks.
A search-and-distill framework with conformalized improvement head produces a language feedback policy that boosts frozen VLA performance by 24.7% in simulation and 65% on hardware while guaranteeing harmlessness on perturbations.
LARA jointly optimizes LAM and VLA models via representation alignment to improve robotic manipulation performance using human videos.
AxisGuide augments RGB images with rendered robot base-frame axis cues to improve generalization of visuomotor manipulation policies under distribution shifts.
citing papers explorer
-
AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Models
AsyncVLA adds asynchronous flow matching and a confidence rater to VLA models so they can generate actions on flexible schedules and selectively refine low-confidence tokens before execution.
-
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
InternVLA-M1 uses spatially guided pre-training on 2.3M examples followed by action post-training to deliver up to 17% gains on robot manipulation benchmarks and 20.6% on unseen objects.
-
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.
-
S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation
S²-VLA uses a state-space model to maintain a belief state that produces dynamic gating weights for fusing visual, language, and action features, claiming better long-horizon manipulation than 7B models with only 2B parameters.
-
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.
-
TBD-VLA: Temporal Block Diffusion Vision Language Action Model
TBD-VLA partitions action sequences into temporal blocks, performs masked discrete diffusion within blocks, and autoregressive generation across blocks to unify parallel decoding with temporal coherence in discrete VLA models.
-
Coarse-to-Control: Action-Token Planning for Vision-Language-Action Models
Coarse-to-Control adds planning via coarse action tokens in the same vocabulary as control actions, improving VLA performance on long-horizon manipulation tasks.
-
GeoAlign: Beyond Semantics with State-Guided Spatial Alignment in VLA Models
GeoAlign post-trains an RGB geometry branch on robot RGB-D data to produce GEP features that are queried by proprioceptive state to generate phase-dependent geometry tokens, yielding 99.0% on LIBERO, 85.3% on SimplerEnv-Fractal, and 78.8% on real ALOHA tasks.
-
SeeTraceAct: Visibility-Aware Latent Planning from Cross-Embodiment Demonstration Videos
SeeTraceAct adds visibility-aware future end-effector trace prediction to demo-conditioned VLAs and reports higher success rates than baselines on RoboCasa-DC and a real Franka arm conditioned on human videos.
-
Grounded 3D-Aware Spatial Vision-Language Modeling
GR3D is a VLM that combines explicit 2D, implicit 2D, and monocular 3D grounding mechanisms to improve performance on spatial understanding benchmarks.
-
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.
-
OASIS: Observation-Action Space Alignment via SE(3) Trajectory Prediction for Robotic Manipulation
OASIS improves robotic manipulation success and generalization by predicting camera-frame SE(3) end-effector trajectories to condition the action decoder on pose-supervised states.
-
PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction
PointACT proposes a 3D-aware dual-system VLA policy using multi-scale point-action interaction with bottleneck window self-attention, achieving 10% higher success rates on RLBench-10Tasks over prior pretrained VLAs.
-
Behavioral Mode Discovery for Fine-tuning Multimodal Generative Policies
Unsupervised behavioral mode discovery combined with mutual information rewards enables RL fine-tuning of multimodal generative policies that achieves higher success rates without losing action diversity.
-
VLA-GSE: Boosting Parameter-Efficient Fine-Tuning in VLA with Generalized and Specialized Experts
VLA-GSE uses spectral decomposition of the VLA backbone to create generalized and specialized experts, enabling effective robot task adaptation while updating only 2.51% of parameters and achieving 81.2% zero-shot success on LIBERO-Plus.
-
PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
PokeVLA is a lightweight VLA model pre-trained on 2.4M samples for spatial grounding and reasoning, then adapted via multi-view semantics and geometry alignment to achieve state-of-the-art robot manipulation performance.
-
Cortex 2.0: Grounding World Models in Real-World Industrial Deployment
Cortex 2.0 introduces world-model-based planning that generates and scores future trajectories to outperform reactive vision-language-action baselines on industrial robotic tasks including pick-and-place, sorting, and unpacking.
-
VLA Foundry: A Unified Framework for Training Vision-Language-Action Models
VLA Foundry provides a single training stack for VLA models and releases open models that match prior closed-source performance or outperform baselines on multi-task manipulation in simulation.
-
Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models
Hierarchical framework pairs in-context VLMs for high-level plan synthesis with RL-trained low-level skills and failure recovery to reach 92% success on long-horizon DLO routing across varied scenes and language inputs.
-
SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning
SafeVLA applies constrained reinforcement learning via CMDP min-max optimization to VLAs, cutting safety violation costs by 83.58% while preserving task success on long-horizon mobile manipulation tasks.
- LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorization