Related papers: Coloring Between the Lines: Personalization in the…
Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs. Motivated by the observation, in this paper, we study the problem of…
Complementary-label learning (CLL) is a weakly supervised paradigm where instances are labeled with classes they do not belong to. Despite a decade of research, CLL methods remain competitive mainly on 10-class classification, with scaling…
We address the problem of controlling a noisy differential drive mobile robot such that the probability of satisfying a specification given as a Bounded Linear Temporal Logic (BLTL) formula over a set of properties at the regions in the…
The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on…
Models of human feedback for AI alignment, such as those underpinning Direct Preference Optimization (DPO), often bake in a singular, static set of preferences, limiting adaptability. This paper challenges the assumption of monolithic…
This paper explores continuous-time control synthesis for target-driven navigation to satisfy complex high-level tasks expressed as linear temporal logic (LTL). We propose a model-free framework using deep reinforcement learning (DRL) where…
Signal Temporal Logic (STL) is expressive formal language that specifies spatio-temporal requirements in robotics. Its quantitative robustness semantics can be easily integrated with optimization-based control frameworks. However, STL…
CG:SHOP is an annual geometric optimization challenge and the 2022 edition proposed the problem of coloring a certain geometric graph defined by line segments. Surprisingly, the top three teams used the same technique, called conflict…
Designing visually diverse and high-quality designs remains a manual, time-consuming process, limiting scalability and personalization in creative workflows. We present a system for generating editable design variations using a decoder-only…
Deploying guardrails for custom policies remains challenging, as generic safety models fail to capture task-specific requirements, while prompting LLMs suffers from inconsistent boundary-case performance and high inference costs. Training…
Colorizing line art is a pivotal task in the production of hand-drawn cel animation. This typically involves digital painters using a paint bucket tool to manually color each segment enclosed by lines, based on RGB values predetermined by a…
Large language models (LLMs) have shown significant potential for robotics applications, particularly task planning, by harnessing their language comprehension and text generation capabilities. However, in applications such as household…
In this paper, we develop a distributed intermittent communication and task planning framework for mobile robot teams. The goal of the robots is to accomplish complex tasks, captured by local Linear Temporal Logic formulas, and share the…
Line-based density plots are used to reduce visual clutter in line charts with a multitude of individual lines. However, these traditional density plots are often perceived ambiguously, which obstructs the user's identification of…
In this paper, we propose Belief Behavior Trees (BBTs), an extension to Behavior Trees (BTs) that allows to automatically create a policy that controls a robot in partially observable environments. We extend the semantic of BTs to account…
This paper introduces SmartBSP, an advanced self-supervised learning framework for real-time path planning and obstacle avoidance in autonomous robotics navigating through complex environments. The proposed system integrates Proximal Policy…
Large language models (LLMs) are increasingly explored in robot manipulation, but many existing methods struggle to adapt to new environments. Many systems require either environment-specific policy training or depend on fixed prompts and…
Motion planning and control are crucial components of robotics applications like automated driving. Here, spatio-temporal hard constraints like system dynamics and safety boundaries (e.g., obstacles) restrict the robot's motions. Direct…
Multi-agent learning faces a fundamental tension: leveraging distributed collaboration without sacrificing the personalization needed for diverse agents. This tension intensifies when aiming for full personalization while adapting to…
Fine-tuning vision-language models (VLMs) with abundant unlabeled data recently has attracted increasing attention. Existing methods that resort to the pseudolabeling strategy would suffer from heavily incorrect hard pseudolabels when VLMs…