Jun 2026
In-Context World Modeling for Robotic Control
arXiv ↗Modern Vision-Language-Action (VLA) models often fail to generalize to novel setups, such as altered camera viewpoints or robot morphologies, because they are typicall
💛 51
📚 Awesome Robotics
25,823 papers across 0 tags, ranked by community signal and explained.
Jul 2026
ABot-M0.5: Unified Mobility-and-Manipulation World Action Model
arXiv ↗Mobile manipulation is a key capability for general-purpose robots, yet remains challenging for current embodied learning methods. VLA policies are typically reactive and
💛 13
Jun 2026
Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
arXiv ↗We introduce Qwen-RobotWorld, a language-conditioned video world model for embodied intelligence. With natural language as a unified action interface, it predicts phys
💛 21
Jun 2026
Guava: An Effective and Universal Harness for Embodied Manipulation
arXiv ↗Language models trained on large-scale vision-language data have demonstrated strong potential for embodied agents. Harnessing models through embodied tools use offers a p
💛 15
May 2026
GEM: Generative Supervision Helps Embodied Intelligence
arXiv ↗Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a si…
💛 23
Jun 2026
PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulation
arXiv ↗Video generation models have emerged as a promising paradigm for embodied world simulation. However, both general-domain video generators and robot-specific data fine-tu
💛 11
Sep 2025
SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
arXiv ↗Vision-Language-Action (VLA) models have recently emerged as a powerful paradigm for robotic manipulation. Despite substantial progress enabled by large-scale pretraining and super…
📚 83💛 81
May 2026
Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
arXiv ↗Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that…
💛 5
Feb 2026
GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learning
arXiv ↗Vision-language-action (VLA) models that directly predict multi-step action chunks from current observations face inherent limitations due to constrained scene understanding and we…
💛 62
May 2026
Rethinking VLM Representation for VLA Initialization
arXiv ↗Vision-Language-Action (VLA) models widely adopt pretrained Vision-Language Models (VLMs) as policy backbones, yet it remains unclear what kind of pretrained VLM representation is …
💛 7
Jul 2026
RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
arXiv ↗Generalist robot manipulation policies have advanced rapidly, yet existing benchmarks remain limited in systematically evaluating their capabilities. Many rely on simp
💛 1
Jul 2026
DeWorldSG: Depth-Aware 3D Semantic Scene Graph Generation via World-Model Priors
arXiv ↗We present DeWorldSG, a novel framework that generates spatio-temporally robust 3D Semantic Scene Graphs from RGB-D sequences. Existing methods often struggle to construct
Feb 2026
RISE: Self-Improving Robot Policy with Compositional World Model
arXiv ↗Despite the sustained scaling on model capacity and data acquisition, Vision-Language-Action (VLA) models remain brittle in contact-rich and dynamic manipulation tasks, where minor…
💛 29
Jun 2026
LA4VLA: Learning to Act without Seeing via Language-Action Pretraining
arXiv ↗Vision-Language-Action (VLA) models are commonly pretrained on robot demonstrations by jointly mapping visual observations and language instructions to actions. Howeve
Jun 2026
Hy-Embodied-0.5-VLA: From Vision-Language-Action Models to a Real-World Robot Learning Stack
arXiv ↗In this report, we present Hy-Embodied-0.5-VLA, abbreviated as HyVLA-0.5, an end-to-end system that spans the full robot learning stack: data collection, model design, continued pr…
💛 1
Jun 2026
ReSiReg: Towards Spatially Consistent Semantics in Language-Conditioned Robotic Tasks
arXiv ↗Vision-Language Models (VLMs) enable robots to follow open-language instructions. However, dense VLM embeddings have shown to be noisy and lack spatial consistency. This i
💛 1
Jul 2026
Structured 4D Latent Predictive Model for Robot Planning
arXiv ↗Video predictive models are emerging as a powerful paradigm in robotics, offering a promising path toward task generalization, long-horizon planning, and flexible decisi
Jul 2026
PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation
arXiv ↗Manipulating fast and dynamically moving targets in unstructured 3D environments remains challenging for embodied AI. Existing visual-language-action models and world mode
Jul 2026
Bridge-WA: Predicting Where and How the World Changes for Robotic Action
arXiv ↗General-purpose vision-language-action models benefit from large vision-language priors, but effective manipulation also requires anticipating action-relevant scene change
Jul 2026
The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
arXiv ↗Vision-Language-Action (VLA) models have shown remarkable promise in generalized robotic manipulation. However, their spatial generalization remains fragile. We argue that
Jul 2026
WorldSample: Closed-loop Real-robot RL with World Modelling
arXiv ↗Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction
Jul 2026
VLAFlow: A Unified Training Framework for Vision-Language-Action Models via Co-training and Future Latent Alignment
arXiv ↗Vision-language-action models (VLAs) have recently advanced robotic manipulation, yet the effects of different robot-data pre-training paradigms remain difficult to comp
💛 1
Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity
2026
Visual-tactile pretraining and online multitask learning for humanlike manipulation dexterity
Achieving humanlike dexterity with anthropomorphic multifingered robotic hands requires precise finger coordination. However, dexterous manipulation remains highly challenging beca…
📚 2
Feb 2026
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
arXiv ↗Building general-purpose embodied agents across diverse hardware remains a central challenge in robotics, often framed as the ''one-brain, many-forms'' paradigm. Progress is hinder…
💛 14