Deformable Cluster Manipulation via Whole-Arm Policy Learning

Manipulating clusters of deformable objects presents a substantial challenge with widespread applicability, but requires contact-rich whole-arm interactions. A potential solution must address the limited capacity for realistic model synthesis, high uncertainty in perception, and the lack of efficient spatial abstractions, among others. We propose a novel framework for learning model-free policies integrating two modalities: 3D point clouds and proprioceptive touch indicators, emphasising manipulation with full body contact awareness, going beyond traditional end-effector modes. Our reinforcement learning framework leverages a distributional state representation, aided by kernel mean embeddings, to achieve improved training efficiency and real-time inference. Furthermore, we propose a novel context-agnostic occlusion heuristic to clear deformables from a target region for exposure tasks. We deploy the framework in a power line clearance scenario and observe that the agent generates creative strategies leveraging multiple arm links for de-occlusion. Finally, we perform zero-shot sim-to-real policy transfer, allowing the arm to clear real branches with unknown occlusion patterns, unseen topology, and uncertain dynamics.

GraspGen: A Diffusion-based Framework for 6-DOF Grasping with On-Generator Training

Grasping is a fundamental robot skill, yet despite significant research advancements, learning-based 6-DOF grasping approaches are still not turnkey and struggle to generalize across different embodiments and in-the-wild settings. We build upon the recent success on modeling the object-centric grasp generation process as an iterative diffusion process. Our proposed framework, GraspGen, consists of a DiffusionTransformer architecture that enhances grasp generation, paired with an efficient discriminator to score and filter sampled grasps. We introduce a novel and performant on-generator training recipe for the discriminator. To scale GraspGen to both objects and grippers, we release a new simulated dataset consisting of over 53 million grasps. We demonstrate that GraspGen outperforms prior methods in simulations with singulated objects across different grippers, achieves state-of-the-art performance on the FetchBench grasping benchmark, and performs well on a real robot with noisy visual observations.

Q-STAC: Q-Guided Stein Variational Model Predictive Actor-Critic

Deep reinforcement learning has shown remarkable success in continuous control tasks, yet often requires extensive training data, struggles with complex, long-horizon planning, and fails to maintain safety constraints during operation. Meanwhile, Model Predictive Control (MPC) offers explainability and constraint satisfaction, but typically yields only locally optimal solutions and demands careful cost function design. This paper introduces the Q-guided STein variational model predictive Actor-Critic (Q-STAC), a novel framework that bridges these approaches by integrating Bayesian MPC with actor-critic reinforcement learning through constrained Stein Variational Gradient Descent (SVGD). Our method optimizes control sequences directly using learned Q-values as objectives, eliminating the need for explicit cost function design while leveraging known system dynamics to enhance sample efficiency and ensure control signals remain within safe boundaries. Extensive experiments on 2D navigation and robotic manipulation tasks demonstrate that Q-STAC achieves superior sample efficiency, robustness, and optimality compared to state-of-the-art algorithms, while maintaining the high expressiveness of policy distributions. Experiment videos are available on our website: https://sites.google.com/view/q-stac

Controlled Latent Diffusion Models for 3D Porous Media Reconstruction

Three-dimensional digital reconstruction of porous media presents a fundamental challenge in geoscience, requiring simultaneous resolution of fine-scale pore structures while capturing representative elementary volumes. We introduce a computational framework that addresses this challenge through latent diffusion models operating within the EDM framework. Our approach reduces dimensionality via a custom variational autoencoder trained in binary geological volumes, improving efficiency and also enabling the generation of larger volumes than previously possible with diffusion models. A key innovation is our controlled unconditional sampling methodology, which enhances distribution coverage by first sampling target statistics from their empirical distributions, then generating samples conditioned on these values. Extensive testing on four distinct rock types demonstrates that conditioning on porosity - a readily computable statistic - is sufficient to ensure a consistent representation of multiple complex properties, including permeability, two-point correlation functions, and pore size distributions. The framework achieves better generation quality than pixel-space diffusion while enabling significantly larger volume reconstruction (256-cube voxels) with substantially reduced computational requirements, establishing a new state-of-the-art for digital rock physics applications.

Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control

We introduce Cosmos-Transfer, a conditional world generation model that can generate world simulations based on multiple spatial control inputs of various modalities such as segmentation, depth, and edge. In the design, the spatial conditional scheme is adaptive and customizable. It allows weighting different conditional inputs differently at different spatial locations. This enables highly controllable world generation and finds use in various world-to-world transfer use cases, including Sim2Real. We conduct extensive evaluations to analyze the proposed model and demonstrate its applications for Physical AI, including robotics Sim2Real and autonomous vehicle data enrichment. We further demonstrate an inference scaling strategy to achieve real-time world generation with an NVIDIA GB200 NVL72 rack. To help accelerate research development in the field, we open-source our models and code at https://github.com/nvidia-cosmos/cosmos-transfer1.

HAMSTER: Hierarchical Action Models For Open-World Robot Manipulation

Large foundation models have shown strong open-world generalization to complex problems in vision and language, but similar levels of generalization have yet to be achieved in robotics. One fundamental challenge is the lack of robotic data, which are typically obtained through expensive on-robot operation. A promising remedy is to leverage cheaper, off-domain data such as action-free videos, hand-drawn sketches or simulation data. In this work, we posit that hierarchical vision-language-action (VLA) models can be more effective in utilizing off-domain data than standard monolithic VLA models that directly finetune vision-language models (VLMs) to predict actions. In particular, we study a class of hierarchical VLA models, where the high-level VLM is finetuned to produce a coarse 2D path indicating the desired robot end-effector trajectory given an RGB image and a task description. The intermediate 2D path prediction is then served as guidance to the low-level, 3D-aware control policy capable of precise manipulation. Doing so alleviates the high-level VLM from fine-grained action prediction, while reducing the low-level policy's burden on complex task-level reasoning. We show that, with the hierarchical design, the high-level VLM can transfer across significant domain gaps between the off-domain finetuning data and real-robot testing scenarios, including differences on embodiments, dynamics, visual appearances and task semantics, etc. In the real-robot experiments, we observe an average of 20% improvement in success rate across seven different axes of generalization over OpenVLA, representing a 50% relative gain. Visual results are provided at: https://hamster-robot.github.io/

Grasping by parallel shape matching

Grasping is essential in robotic manipulation, yet challenging due to object and gripper diversity and real-world complexities. Traditional analytic approaches often have long optimization times, while data-driven methods struggle with unseen objects. This paper formulates the problem as a rigid shape matching between gripper and object, which optimizes with Annealed Stein Iterative Closest Point (AS-ICP) and leverages GPU-based parallelization. By incorporating the gripper's tool center point and the object's center of mass into the cost function and using a signed distance field of the gripper for collision checking, our method achieves robust grasps with low computational time. Experiments with the Kinova KG3 gripper show an 87.3% success rate and 0.926 s computation time across various objects and settings, highlighting its potential for real-world applications.

Aim My Robot: Precision Local Navigation to Any Object

Existing navigation systems mostly consider "success" when the robot reaches within 1m radius to a goal. This precision is insufficient for emerging applications where the robot needs to be positioned precisely relative to an object for downstream tasks, such as docking, inspection, and manipulation. To this end, we design and implement Aim-My-Robot (AMR), a local navigation system that enables a robot to reach any object in its vicinity at the desired relative pose, with centimeter-level precision. AMR achieves high precision and robustness by leveraging multi-modal perception, precise action prediction, and is trained on large-scale photorealistic data generated in simulation. AMR shows strong sim2real transfer and can adapt to different robot kinematics and unseen objects with little to no fine-tuning.

Differentiable GPU-Parallelized Task and Motion Planning

We present a differentiable optimization-based framework for Task and Motion Planning (TAMP) that is massively parallelizable on GPUs, enabling thousands of sampled seeds to be optimized simultaneously. Existing sampling-based approaches inherently disconnect the parameters by generating samples for each independently and combining them through composition and rejection, while optimization-based methods struggle with highly non-convex constraints and local optima. Our method treats TAMP constraint satisfaction as optimizing a batch of particles, each representing an assignment to a plan skeleton's continuous parameters. We represent the plan skeleton's constraints using differentiable cost functions, enabling us to compute the gradient of each particle and update it toward satisfying solutions. Our use of GPU parallelism better covers the parameter space through scale, increasing the likelihood of finding the global optima by exploring multiple basins through global sampling. We demonstrate that our algorithm can effectively solve a highly constrained Tetris packing problem using a Franka arm in simulation and deploy our planner on a real robot arm. Website: https://williamshen-nz.github.io/gpu-tamp

Open-World Task and Motion Planning via Vision-Language Model Inferred Constraints

Foundation models trained on internet-scale data, such as Vision-Language Models (VLMs), excel at performing tasks involving common sense, such as visual question answering. Despite their impressive capabilities, these models cannot currently be directly applied to challenging robot manipulation problems that require complex and precise continuous reasoning. Task and Motion Planning (TAMP) systems can control high-dimensional continuous systems over long horizons through combining traditional primitive robot operations. However, these systems require detailed model of how the robot can impact its environment, preventing them from directly interpreting and addressing novel human objectives, for example, an arbitrary natural language goal. We propose deploying VLMs within TAMP systems by having them generate discrete and continuous language-parameterized constraints that enable TAMP to reason about open-world concepts. Specifically, we propose algorithms for VLM partial planning that constrain a TAMP system's discrete temporal search and VLM continuous constraints interpretation to augment the traditional manipulation constraints that TAMP systems seek to satisfy. We demonstrate our approach on two robot embodiments, including a real world robot, across several manipulation tasks, where the desired objectives are conveyed solely through language.