ThinkingVLA is a Mixture-of-Transformers VLA model that performs interleaved forward CoT for subgoal and image prediction followed by inverse CoT grounded on the predicted image to generate actions.
hub Mixed citations
Unified vision-language-action model.arXiv preprint arXiv:2506.19850
Mixed citation behavior. Most common role is background (60%).
34
Pith papers citing it
Background
60% of classified citations
hub tools
citation-role summary
background 7
baseline 2
dataset 1
citation-polarity summary
representative citing papers
JOPAT jointly models pixels, point tracks, and actions in a diffusion transformer and reports gains over pixel-only baselines on long-horizon robot tasks with occlusion and off-screen motion.
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.
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.
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.
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.
UniviewVLA generates multiview future views from two cameras via world modeling, plus token compression and view selection, to boost occlusion handling in robot manipulation while matching standard benchmark performance.
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.
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.
TOAD applies test-time Cross-Entropy Method optimization to refine trajectories using the planner's scorer as a reward function, improving end-to-end autonomous driving performance without retraining.
MPCoT improves long-horizon VLA performance on LIBERO and CALVIN by initializing M latent hypotheses, refining them over K steps, and aggregating via a reward-trained path scorer while preserving the original 8-step action interface and generating zero reasoning tokens.
PointAction uses predicted dynamic 3D pointmaps from fine-tuned video models as an embodiment-agnostic action representation to map video predictions to executable robot actions.
S2 improves generalization in vision-language-action models by using goal-preserving refined language guidance and explicit visual evidence budgets, raising mean subtask success from 54.2% to 79.0% on eight real-robot tasks compared to pi0.5.
OneVLA is a unified VLA model using a shared action head and multi-stage progressive training with CoT fine-tuning that reports state-of-the-art results on both navigation and manipulation in simulation and real-world settings.
ChainFlow-VLA unifies autoregressive causal trajectory modes with VLM-conditioned diffusion refinement to reach 94.85 on NAVSIM v1, matching human performance.
CLOVER is a closed-loop generator-scorer framework that expands proposal coverage with pseudo-expert trajectories and performs conservative self-distillation to achieve state-of-the-art planning scores on NAVSIM and nuScenes.
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.
X-WAM unifies robotic action execution and 4D world synthesis by adapting video diffusion priors with a lightweight depth branch and asynchronous noise sampling, achieving 79-91% success on robot benchmarks.
HiF-VLA improves long-horizon robotic manipulation by encoding past motion as hindsight priors and anticipating future motion through foresight reasoning inside a VLA framework.
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.
F1 integrates next-scale visual foresight prediction into a Mixture-of-Transformer VLA architecture to reformulate action generation as foresight-guided inverse dynamics, achieving higher success rates on 136 tasks.
This is the first survey on vision-language-action models, providing a taxonomy across three lines, plus summaries of datasets, simulators, benchmarks, challenges, and future directions in embodied AI.
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.
WLA models use an autoregressive Transformer to jointly predict textual subtasks, subgoal images, and robot actions from instructions, images, and states, reporting SOTA success rates on RoboTwin2.0 and RMBench.
citing papers explorer
-
Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
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.