Related papers: GLSO: Grammar-guided Latent Space Optimization for…

Learning from Demonstration (LfD) is a popular method of reproducing and generalizing robot skills from human-provided demonstrations. In this paper, we propose a novel optimization-based LfD method that encodes demonstrations as elastic…

Industrial robots are designed as general-purpose hardware with limited ability to adapt to changing task requirements or environments. Modular robots, on the other hand, offer flexibility and can be easily customized to suit diverse needs.…

Optimization of very expensive black-box functions requires utilization of maximum information gathered by the process of optimization. Model Guided Sampling Optimization (MGSO) forms a more robust alternative to Jones'…

The rapid advancement of large-language models (LLMs) has driven extensive research into parameter compression after training has been completed, yet compression during the training phase remains largely unexplored. In this work, we…

We address the problem of learning observation models end-to-end for estimation. Robots operating in partially observable environments must infer latent states from multiple sensory inputs using observation models that capture the joint…

Open-vocabulary object detection with vision-language models (VLMs) such as Grounding DINO suffers from performance degradation under test-time distribution shifts, primarily due to semantic misalignment between text embeddings and shifted…

In traditional topology optimization, the computing time required to iteratively update the material distribution within a design domain strongly depends on the complexity or size of the problem, limiting its application in real engineering…

Optimization problems constrained by high-dimensional, time-dependent partial differential equations require repeated forward and sensitivity solves, making high-fidelity optimization computationally prohibitive in many-query design and…

Traditional approaches for designing analog circuits are time-consuming and require significant human expertise. Existing automation efforts using methods like Bayesian Optimization (BO) and Reinforcement Learning (RL) are sub-optimal and…

Image diversity remains a fundamental challenge for text-to-image diffusion models. Low-diversity models tend to generate repetitive outputs, increasing sampling redundancy and hindering both creative exploration and downstream…

In many statistical learning problems, it is desired that the optimal solution conforms to an a priori known sparsity structure represented by a directed acyclic graph. Inducing such structures by means of convex regularizers requires…

Many modern embedded systems have end-to-end (EtoE) latency constraints that necessitate precise timing to ensure high reliability and functional correctness. The combination of High-Level Synthesis (HLS) and Design Space Exploration (DSE)…

Purpose: Machine learning is broadly used for clinical data analysis. Before training a model, a machine learning algorithm must be selected. Also, the values of one or more model parameters termed hyper-parameters must be set. Selecting…

In linear regression, SLOPE is a new convex analysis method that generalizes the Lasso via the sorted L1 penalty: larger fitted coefficients are penalized more heavily. This magnitude-dependent regularization requires an input of penalty…

Bayesian optimization is a broadly applied methodology to optimize the expensive black-box function. Despite its success, it still faces the challenge from the high-dimensional search space. To alleviate this problem, we propose a novel…

Large-scale LiDAR Bundle Adjustment (LBA) to refine sensor orientation and point cloud accuracy simultaneously to build the navigation map is a fundamental task in logistics and robotics. Unlike pose-graph-based methods that rely solely on…

Real-world robots are becoming increasingly complex and commonly act in poorly understood environments where it is extremely challenging to model or learn their true dynamics. Therefore, it might be desirable to take a task-specific…

Many deep generative models are defined as a push-forward of a Gaussian measure by a continuous generator, such as Generative Adversarial Networks (GANs) or Variational Auto-Encoders (VAEs). This work explores the latent space of such deep…

Automatically generating agile whole-body motions for legged and humanoid robots remains a fundamental challenge in robotics. While numerous trajectory optimization approaches have been proposed, there is no clear guideline on how the…

It is common in graphic design humans visually arrange various elements according to their design intent and semantics. For example, a title text almost always appears on top of other elements in a document. In this work, we generate…