We propose a novel framework COLLAGE for generating collaborative agent-object-agent interactions by leveraging large language models (LLMs) and hierarchical motion-specific vector-quantized variational autoencoders (VQ-VAEs). Our model addresses the lack of rich datasets in this domain by incorporating the knowledge and reasoning abilities of LLMs to guide a generative diffusion model. The hierarchical VQ-VAE architecture captures different motion-specific characteristics at multiple levels of abstraction, avoiding redundant concepts and enabling efficient multi-resolution representation. We introduce a diffusion model that operates in the latent space and incorporates LLM-generated motion planning cues to guide the denoising process, resulting in prompt-specific motion generation with greater control and diversity. Experimental results on the CORE-4D, and InterHuman datasets demonstrate the effectiveness of our approach in generating realistic and diverse collaborative human-object-human interactions, outperforming state-of-the-art methods. Our work opens up new possibilities for modeling complex interactions in various domains, such as robotics, graphics and computer vision. Paper website: https://collagemotion.github.io/

We introduce Go-Slam, a novel framework that combines 3D Gaussian Splatting SLAM with grounded object segmentation and open-vocabulary querying to enable object-aware 3D scene reconstruction. Go-Slam incrementally builds high-fidelity 3D maps from RGB-D inputs while embedding semantic information by assigning unique object identifiers to Gaussian primitives. This integration allows the system to support flexible, natural language queries and accurately localize objects in complex, static environments. To achieve robust semantic mapping, Go-Slam leverages object detection and segmentation models, enabling consistent object identification across frames without relying on predefined categories. We evaluate Go-Slam across diverse indoor scenes, demonstrating improvements over existing baselines in both reconstruction quality and object localization accuracy. Our results show that Go-Slam effectively bridges the gap between geometric mapping and semantic understanding, supporting real-time scene interaction and object retrieval in open-world environments.

By framing reinforcement learning as a sequence modeling problem, recent work has enabled the use of generative models, such as diffusion models, for planning. While these models are effective in predicting long-horizon state trajectories in deterministic environments, they face challenges in dynamic settings with moving obstacles. Effective collision avoidance demands continuous monitoring and adaptive decision-making. While re-planning at every time step could ensure safety, it introduces substantial computational overhead due to the repetitive prediction of overlapping state sequences—a process that is particularly costly with diffusion models, known for their intensive iterative sampling procedure. We propose an adaptive generative planning approach that dynamically adjusts re-planning frequency based on the uncertainty of action predictions. Our method minimizes the need for frequent, computationally expensive, and redundant re-planning while maintaining robust collision avoidance performance. In experiments, we obtain a 13.5% increase in the mean trajectory length and 12.7% increase in mean reward over long-horizon planning, indicating a reduction in collision rates, and improved ability to navigate the environment safely.

We present CrossLoc3D, a novel 3D place recognition method that solves a large-scale point matching problem in a cross-source setting. Cross-source point cloud data corresponds to point sets captured by depth sensors with different accuracies or from different distances and perspectives. We address the challenges in terms of developing 3D place recognition methods that account for the representation gap between points captured by different sources. Our method handles cross-source data by utilizing multi-grained features and selecting convolution kernel sizes that correspond to most prominent features. Inspired by the diffusion models, our method uses a novel iterative refinement process that gradually shifts the embedding spaces from different sources to a single canonical space for better metric learning. In addition, we present CS-Campus3D, the first 3D aerial-ground cross-source dataset consisting of point cloud data from both aerial and ground LiDAR scans. The point clouds in CS-Campus3D have representation gaps and other features like different views, point densities, and noise patterns. We show that our CrossLoc3D algorithm can achieve an improvement of 4.74% - 15.37% in terms of the top 1 average recall on our CS-Campus3D benchmark and achieves performance comparable to state-of-the-art 3D place recognition method on the Oxford RobotCar. The code and CS-Campus3D benchmark will be available at github.com/rayguan97/crossloc3d.

We propose a novel method for autonomous legged robot navigation in densely vegetated environments with a variety of pliable/traversable and non-pliable/untraversable vegetation. We present a novel few-shot learning classifier that can be trained on a few hundred RGB images to differentiate flora that can be navigated through, from the ones that must be circumvented. Using the vegetation classification and 2D lidar scans, our method constructs a vegetation-aware traversability cost map that accurately represents the pliable and non-pliable obstacles with lower, and higher traversability costs, respectively. Our cost map construction accounts for misclassifications of the vegetation and further lowers the risk of collisions, freezing and entrapment in vegetation during navigation. Furthermore, we propose holonomic recovery behaviors for the robot for scenarios where it freezes, or gets physically entrapped in dense, pliable vegetation. We demonstrate our method on a Boston Dynamics Spot robot in real-world unstructured environments with sparse and dense tall grass, bushes, trees, etc. We observe an increase of 25-90% in success rates, 10-90% decrease in freezing rate, and up to 65% decrease in the false positive rate compared to existing methods.