Search for: All records

We present WonderWorld, a novel framework for interactive 3D scene generation that enables users to interactively specify scene contents and layout and see the created scenes in low latency. The major challenge lies in achieving fast generation of 3D scenes. Existing scene generation approaches fall short of speed as they often require (1) progressively generating many views and depth maps, and (2) time-consuming optimization of the scene representations. Our approach does not need multiple views, and it leverages a geometry-based initialization that significantly reduces optimization time. Another challenge is generating coherent geometry that allows all scenes to be connected. We introduce the guided depth diffusion that allows partial conditioning of depth estimation. WonderWorld generates connected and diverse 3D scenes in less than 10 seconds on a single A6000 GPU, enabling real-time user interaction and exploration. Our interactive demo, full code, data, and software can be found at https://kovenyu.com/WonderWorld/ 

We introduce AutoVER, an Autoregressive model for Visual Entity Recognition. Our model extends an autoregressive Multimodal Large Language Model by employing retrieval augmented constrained generation. It mitigates low performance on out-of-domain entities while excelling in queries that require visual reasoning. Our method learns to distinguish similar entities within a vast label space by contrastively training on hard negative pairs in parallel with a sequence-to-sequence objective without an external retriever. During inference, a list of retrieved candidate answers explicitly guides language generation by removing invalid decoding paths. The proposed method achieves significant improvements across different dataset splits in the recently proposed Oven-Wikibenchmark with accuracy on the Entity seen split rising from 32.7% to 61.5%. It demonstrates superior performance on the unseen and query splits by a substantial double-digit margin, while also preserving the ability to effectively transfer to other generic visual question answering benchmarks without further training. 

Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a significant challenge. Unlike unconditional or text-conditioned dynamics generation, action-conditioned dynamics requires perceiving the physical material properties of objects and grounding the 3D motion prediction on these properties, such as object stiffness. However, estimating physical material properties is an open problem due to the lack of material ground-truth data, as measuring these properties for real objects is highly difficult. We present PhysDreamer, a physics-based approach that endows static 3D objects with interactive dynamics by leveraging the object dynamics priors learned by video generation models. By distilling these priors, PhysDreamer enables the synthesis of realistic object responses to novel interactions, such as external forces or agent manipulations. We demonstrate our approach on diverse examples of elastic objects and evaluate the realism of the synthesized interactions through a user study. PhysDreamer takes a step towards more engaging and realistic virtual experiences by enabling static 3D objects to dynamically respond to interactive stimuli in a physically plausible manner. See our project page at this https URL. 

A strong understanding of technical knowledge is necessary for all engineers, but understanding the context in which engineering work takes place is just as important. Engineering work impacts people, communities, and environments, and there is increasing recognition of the importance of preparing engineers to account for these sociocultural dimensions. The engineering curriculum needs to include both technical and sociocultural topics to prepare students as holistically competent engineers. A call for broader engineering skills is evident in ABET student outcomes, a few of which directly denote the importance of students’ ability to identify the ethical, cultural, and social impact engineers have on society. However, engineering education continues to underemphasize or omit entirely non-technical aspects of engineering practice. Technical knowledge persists as the central focus in engineering classes. Omitting sociocultural material in engineering classes can result in the development of future engineers whose designs further perpetuate social and systemic inequities, such as environmental pollution that affects vulnerable populations or inefficient designs that risk human lives. Additionally, emphasizing sociotechnical content in undergraduate engineering courses can help attract and retain a more diverse population of students who value socially relevant engineering work. A deep grounding in both technical and social skills and knowledge is particularly important in Industrial Engineering (IE), a field that focuses on analyzing data to improve systems and processes and which tends to focus more on human and business dimensions than many other engineering fields. Even so, there is little evidence to indicate that sociocultural skills and knowledge are taught in IE courses. Because the curricular focus of a field communicates to students what is and is not valued in the field, students who enter IE with a strong desire to advance social good may learn that such a goal is inconsistent with the field’s values and ultimately feel alienated or disinterested if social dimensions are not incorporated into their coursework. More insight is needed into the kinds of messages IE coursework sends about the nature of work in the field and the opportunities these courses provide for students to develop the sociotechnical knowledge and skills that are increasingly crucial in Industrial Engineering. In an effort to characterize how, if at all, core courses in IE facilitate students’ development of sociotechnical engineering skills, this research paper examines the general content of core IE courses at a predominantly white institution. This paper draws on data generated for a larger research study that leverages Holland et al.’s Figured Worlds framework to explore the messaging undergraduate engineering students receive in their classes around valued knowledge in their field. In this study, we draw on observation data leveraging recordings of seven required undergraduate courses in IE. We analyzed three randomly selected sessions from each course, with a total of 21 unique sessions observed. Our findings describe the practices that are and are not emphasized within and across required IE courses and the ways these practices are discussed. Our characterization of emphasized engineering practices provides an important foundation for understanding what is communicated to students about the nature of engineering work in their field, messaging which has substantial implications for the population of students who enter and persist in the field beyond their undergraduate studies. 

Known as a bio-limiting metal, high abundances of iron in sea water can amplify biological productivity. The growth of diatoms and other photosynthetic organisms increases, providing more food for grazing organisms like foraminifera. The net result is more organic matter in surface waters and ultimately in surface sediments. Existing satellite data show increases in ocean chlorophyll in areas affected by volcanic eruptions. We infer from this that iron derived from volcanic ash does increase biological productivity. However, the relative increase in productivity is unknown. We examined 3 sediment cores from the Equatorial Western Pacific to analyze the relationship between volcanic ash and biological productivity: RC14-44, RC14-66, and RC14-67. All contain black or dark-colored foraminifera within ash layers and white-shelled foraminifera outside ash layers. We attribute the dark material outside and inside the foraminifera to organic carbon and metals. In our cores, some foraminifera are covered in iron sulfide (FeS), which could be pyrite, and contain large amounts of carbon as well as high abundances of aluminum and silicon. We examined barium concentrations to gain further knowledge of biological productivity at specific core depths as barium is a marker for primary productivity. We found that barium levels within ash layers increased at least ten-fold. Within ash layers, we also noticed that the ashes with higher amounts of fine silt and clay sized material have the greatest increase in barium content, perhaps related to explosion size. This pattern of increases in Ba, metals and organic carbon within ash layers compared to surrounding sediments shows that volcanic ash deposition increases marine productivity. For future research, measuring markers for biological productivity like biogenic silica content and loss on ignition (LOI) within and outside ash layers would further clarify the relationship between volcanic ash deposition and biological productivity.