Related papers: MetaAID 2.0: An Extensible Framework for Developin…
The evolution of Large Language Models (LLMs) and the software agents built on them (AI agents) marks a turning point in the transition from a human-centric Web to an ``Agentic Web'' driven by AI agents. However, for AI-Generated Content…
Deep reinforcement learning (RL) provides powerful methods for training optimal sequential decision-making agents. As collecting real-world interactions can entail additional costs and safety risks, the common paradigm of sim2real conducts…
Generative AI is entering research, education, and professional work faster than current governance frameworks can specify how AI-assisted outputs should be judged in learning-intensive settings. The central problem is proxy failure: a…
Machine learning models deployed on edge devices have enabled numerous exciting new applications, such as humanoid robots, AR glasses, and autonomous vehicles. However, the computing resources available on these edge devices are not…
Understanding how robots plan and execute tasks is crucial in today's world, where they are becoming more prevalent in our daily lives. However, teaching non-experts, such as K-12 students, the complexities of robot planning can be…
Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. As the technique keeps attracting attention from the AI community, an increasing number of foundation models…
Recent advances in person re-identification (ReID) obtain impressive accuracy in the supervised and unsupervised learning settings. However, most of the existing methods need to train a new model for a new domain by accessing data. Due to…
Most real-world document collections involve various types of metadata, such as author, source, and date, and yet the most commonly-used approaches to modeling text corpora ignore this information. While specialized models have been…
Constrained generative modeling is fundamental to applications such as robotic control and autonomous driving, where models must respect physical laws and safety-critical constraints. In real-world settings, these constraints rarely take…
Metamaterials are engineered materials composed of specially designed unit cells that exhibit extraordinary properties beyond those of natural materials. Complex engineering tasks often require heterogeneous unit cells to accommodate…
In recent years, Artificial Intelligence has become more and more relevant in our society. Creating AI systems is almost always the prerogative of IT and AI experts. However, users may need to create intelligent solutions tailored to their…
While the integration of IoT devices in virtual spaces is becoming increasingly common, technical barriers to controlling custom devices in multi-user Virtual Reality (VR) environments remain high, particularly limiting new applications in…
Theories of knowledge reuse posit two distinct processes: reuse for replication and reuse for innovation. We identify another distinct process, reuse for customization. Reuse for customization is a process in which designers manipulate the…
Transparency regarding the processing of personal data in online services is a necessary precondition for informed decisions on whether or not to share personal data. In this paper, we argue that privacy interfaces shall incorporate the…
The paradigm of pretrained deep learning models has recently emerged in artificial intelligence practice, allowing deployment in numerous societal settings with limited computational resources, but also embedding biases and enabling…
Context: Responsibility gaps, long-recognized challenges in socio-technical systems where accountability becomes diffuse or ambiguous, have become increasingly pronounced in GenAI-enabled software. The generative and adaptive nature…
One of the primary areas of interest in High Performance Computing is the improvement of performance of parallel workloads. Nowadays, compilable source code-based optimization tasks that employ deep learning often exploit LLVM Intermediate…
In the era of deep learning, the increasing number of pre-trained models available online presents a wealth of knowledge. These models, developed with diverse architectures and trained on varied datasets for different tasks, provide unique…
Learning natural, stable, and compositionally generalizable whole-body control policies for humanoid robots performing simultaneous locomotion and manipulation (loco-manipulation) remains a fundamental challenge in robotics. Existing…
There is a rapidly-growing research interest in modeling user preferences via pre-training multi-domain interactions for recommender systems. However, Existing pre-trained multi-domain recommendations mostly select the item texts to be…