相关论文: Customize Multi-modal RAI Guardrails with Preceden…

While existing time series foundation models primarily rely on large-scale unimodal pretraining, they lack complementary modalities to enhance time series understanding. Building multimodal foundation models is a natural next step, but it…

Predictive models are often introduced to decision-making tasks under the rationale that they improve performance over an existing decision-making policy. However, it is challenging to compare predictive performance against an existing…

A multi-modal framework to generate user intention distributions when operating a mobile vehicle is proposed in this work. The model learns from past observed trajectories and leverages traversability information derived from the visual…

Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking, which can elicit harmful or unsafe behaviors. This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is…

Effectively integrating diverse sensory modalities is crucial for robotic manipulation. However, the typical approach of feature concatenation is often suboptimal: dominant modalities such as vision can overwhelm sparse but critical signals…

Accurate motion prediction of surrounding traffic participants is crucial for the safe and efficient operation of automated vehicles in dynamic environments. Marginal prediction models commonly forecast each agent's future trajectories…

Human trajectory forecasting is a key component of autonomous vehicles, social-aware robots and advanced video-surveillance applications. This challenging task typically requires knowledge about past motion, the environment and likely…

This paper considers semantic forecasting in road-driving scenes. Most existing approaches address this problem as deterministic regression of future features or future predictions given observed frames. However, such approaches ignore the…

Despite ample motivation from costly exploration and limited trajectory data, rapidly adapting to new environments with few-shot reinforcement learning (RL) can remain a challenging task, especially with respect to personalized settings.…

AI models that predict the future behavior of a system (a.k.a. predictive AI models) are central to intelligent decision-making. However, decision-making using predictive AI models often results in suboptimal performance. This is primarily…

Accurately predicting future behaviors of surrounding vehicles is an essential capability for autonomous vehicles in order to plan safe and feasible trajectories. The behaviors of others, however, are full of uncertainties. Both rational…

Training AI models in cybersecurity with help of vast datasets offers significant opportunities to mimic real-world behaviors effectively. However, challenges like data drift and scarcity of labelled data lead to frequent updates of models…

Conventional time-series forecasting methods typically aim to minimize overall prediction error, without accounting for the varying importance of different forecast ranges in downstream applications. We propose a training methodology that…

This paper investigates how to better leverage large-scale pre-trained uni-modal models to further enhance discriminative multi-modal learning. Even when fine-tuned with only uni-modal data, these models can outperform previous multi-modal…

Policy search reinforcement learning has been drawing much attention as a method of learning a robot control policy. In particular, policy search using such non-parametric policies as Gaussian process regression can learn optimal actions…

Many prediction domains, such as ad placement, recommendation, trajectory prediction, and document summarization, require predicting a set or list of options. Such lists are often evaluated using submodular reward functions that measure…

Multi-agent trajectory forecasting in autonomous driving requires an agent to accurately anticipate the behaviors of the surrounding vehicles and pedestrians, for safe and reliable decision-making. Due to partial observability in these…

Omni-modal Large Language Models (OLLMs) that process text, images, videos, and audio introduce new challenges for safety and value guardrails in human-AI interaction. Prior guardrail research largely targets unimodal settings and typically…

The feasibility of collecting a large amount of expert demonstrations has inspired growing research interests in learning-to-drive settings, where models learn by imitating the driving behaviour from experts. However, exclusively relying on…

Standard practice across domains from robotics to language is to first pretrain a policy on a large-scale demonstration dataset, and then finetune this policy, typically with reinforcement learning (RL), in order to improve performance on…