DeformGen uses dynamics-based state expansion via localized disturbances and deformation-field warping for trajectory transfer to improve policy learning on deformable manipulation benchmarks.
hub Canonical reference
InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
Canonical reference. 79% of citing Pith papers cite this work as background.
39
Pith papers citing it
Background
79% of classified citations
abstract
We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.
hub tools
citation-role summary
background 10
baseline 2
dataset 1
method 1
citation-polarity summary
representative citing papers
MoLA infers a mixture of latent actions from generated future videos via modality-aware inverse dynamics models to improve robot manipulation policies.
LoopVLA adds recurrent refinement and learned sufficiency estimation to VLA models, cutting parameters 45% and raising throughput 1.7x while matching baseline task success on LIBERO and VLA-Arena.
OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.
HiPolicy is a new hierarchical multi-frequency action chunking method for imitation learning that jointly generates coarse and fine action sequences with entropy-guided execution to improve performance and efficiency in robotic manipulation.
Introduces H-Tac human tactile-action dataset and TTP pre-training that unifies spaces and predicts future tactile signals to improve robotic dexterous manipulation transfer.
ABot-M0.5 proposes a unified mobility-and-manipulation world action model using three alignment strategies that achieves state-of-the-art performance on mobile and fine-grained manipulation benchmarks.
APT pretrains the action expert as a vision-action prior on frozen VLM features then adds language through gated fusion to improve OOD instruction generalization in continuous-action VLA policies.
SIMPLE is a new large-scale simulation benchmark for humanoid loco-manipulation that integrates accurate dynamics and photorealistic rendering and demonstrates policy transfer from simulation to physical robots.
DRIFT adapts pretrained VLMs to continuous decoding via a base predictor plus residual flow matching, outperforming regression and generative baselines on grounding and robotic control tasks.
LIBERO and CALVIN fail multiple proposed diagnostics for shortcut solvability, statistical significance, overfitting, and data dependence, while a tiny 0.09B probe reaches near-SOTA on LIBERO.
VISUALTHINK-VLA uses visual evidence tokens and selective routing to reach top success rates on VLA benchmarks while cutting reasoning latency from multi-second to sub-second levels.
FrameSkip improves VLA policy training success from 66.50% to 76.15% by selecting high-importance frames and retaining only 20% of unique frames across three benchmarks.
GTA-VLA conditions VLA models on user spatial priors to produce a unified spatial-visual chain-of-thought, reaching 81.2% success on SimplerEnv WidowX and improving performance under out-of-distribution shifts.
ForgeVLA enables federated VLA model training from unlabeled vision-action pairs by recovering language via embodied classifiers and using contrastive planning plus adaptive aggregation to avoid feature collapse.
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.
State-of-the-art vision-language-action models catastrophically fail dynamic embodied reasoning due to lexical-kinematic shortcuts, behavioral inertia, and semantic feature collapse caused by architectural bottlenecks, as shown by the new BeTTER benchmark with real-world validation.
OFlow unifies temporal foresight and object-aware reasoning inside a shared latent space via flow matching to improve VLA robustness in robotic manipulation under distribution shifts.
VADF adds an Adaptive Loss Network for hard-negative training sampling and a Hierarchical Vision Task Segmenter for adaptive noise scheduling during inference to speed convergence and reduce timeouts in diffusion robotic policies.
SIM1 converts sparse real demonstrations into high-fidelity synthetic data through physics-aligned simulation, yielding policies that match real-data performance at a 1:15 ratio with 90% zero-shot success on deformable manipulation.
A1 is a transparent VLA framework achieving state-of-the-art robot manipulation success with up to 72% lower latency via adaptive layer truncation and inter-layer flow matching.
SABER uses a trained ReAct agent to produce bounded adversarial edits to robot instructions, cutting task success by 20.6% and increasing execution length and violations on the LIBERO benchmark across six VLA models.
ABot-M0 unifies heterogeneous robot data into a 6-million-trajectory dataset and introduces Action Manifold Learning to predict stable actions on a low-dimensional manifold using a DiT backbone.
LingBot-VLA is a VLA foundation model trained on massive real robot data that shows superior generalization across tasks and platforms with fast training throughput.
citing papers explorer
-
LoopVLA: Learning Sufficiency in Recurrent Refinement for Vision-Language-Action Models
LoopVLA adds recurrent refinement and learned sufficiency estimation to VLA models, cutting parameters 45% and raising throughput 1.7x while matching baseline task success on LIBERO and VLA-Arena.
-
PRTS: A Primitive Reasoning and Tasking System via Contrastive Representations
PRTS pretrains VLA models with contrastive goal-conditioned RL to embed goal-reachability probabilities from offline data, yielding SOTA results on robotic benchmarks especially for long-horizon and novel instructions.