Related papers: Virtual Scientific Companion for Synchrotron Beaml…
Scientific experimentation and manufacturing rely on prolonged protocol development and complex, multi-step implementation, which require continuous human expertise for precise execution and decision-making, limiting interpretability and…
Vision-language models (VLMs) are emerging as powerful generalist tools for remote sensing, capable of integrating information across diverse tasks and enabling flexible, instruction-based interactions via a chat interface. In this work, we…
Creating shared understanding between stakeholders is essential for the success of software projects. Conflicting requirements originating from misaligned mental models can hinder the development process. The use of videos to present…
Synthetic Aperture Radar (SAR) is a critical imaging modality due to its all-weather operational capability. Although recent advances in self-supervised learning and masked image modeling (MIM) have enabled SAR foundation models, these…
The contemporary astronomy is flooded with an exponentially growing petabyte-scaled data volumes produced by powerful ground and space-based instrumentation as well as a product of extensive computer simulations and computations of complex…
Mental Imagery based Brain-Computer Interfaces (MI-BCI) enable their users to control an interface, e.g., a prosthesis, by performing mental imagery tasks only, such as imagining a right arm movement while their brain activity is measured…
Recently, deep learning has been advancing the state of the art in artificial intelligence to a new level, and humans rely on artificial intelligence techniques more than ever. However, even with such unprecedented advancements, the lack of…
Developing robust drone detection systems is often constrained by the limited availability of large-scale annotated training data and the high costs associated with real-world data collection. However, leveraging synthetic data generated…
A major challenge in optical quantum processing is implementing large, stable interferometers. Here we propose a virtual, measurement-based interferometer that is programmed on the fly solely by the choice of homodyne measurement angles.…
Being able to dynamically control the transmitted-beam divergence can bring important advantages in free-space optical communications. Specifically, this technique can help to optimize the overall communications performance when the optimum…
Brain-computer interfaces (BCIs) have shown promise in enabling communication for individuals with motor impairments. Recent advancements like brain-to-speech technology aim to reconstruct speech from neural activity. However, decoding…
Robot vision has greatly benefited from advancements in multimodal fusion techniques and vision-language models (VLMs). We adopt a task-oriented perspective to systematically review the applications and advancements of multimodal fusion…
Recent work in visual representation learning for robotics demonstrates the viability of learning from large video datasets of humans performing everyday tasks. Leveraging methods such as masked autoencoding and contrastive learning, these…
The increasing availability of high-quality optical and near-infrared spectroscopic data, as well as advances in modelling techniques, have greatly expanded the scientific potential of spectroscopic studies. However, the software tools…
Vision-language models (VLMs) have shown powerful capabilities in visual question answering and reasoning tasks by combining visual representations with the abstract skill set large language models (LLMs) learn during pretraining. Vision,…
Vision (image and video) - Language (VL) pre-training is the recent popular paradigm that achieved state-of-the-art results on multi-modal tasks like image-retrieval, video-retrieval, visual question answering etc. These models are trained…
Bionic vision uses neuroprostheses to restore useful vision to people living with incurable blindness. However, a major outstanding challenge is predicting what people 'see' when they use their devices. The limited field of view of current…
High-throughput materials discovery and studies of complex functional materials increasingly rely on multi-modal characterization performed at synchrotron light sources. However, measurements are typically done with no use of data until…
Large language models (LLMs) have shown promise in robotic procedural planning, yet their human-centric reasoning often omits the low-level, grounded details needed for robotic execution. Vision-language models (VLMs) offer a path toward…
Navigation guided by natural language instructions presents a challenging reasoning problem for instruction followers. Natural language instructions typically identify only a few high-level decisions and landmarks rather than complete…