Plug-and-play diffusion priors (PnPDP) have emerged as a promising research direction for solving inverse problems. However, current studies primarily focus on natural image restoration, leaving the performance of these algorithms in scientific inverse problems largely unexplored. To address this gap, we introduce \textsc{InverseBench}, a framework that evaluates diffusion models across five distinct scientific inverse problems. These problems present unique structural challenges that differ from existing benchmarks, arising from critical scientific applications such as optical tomography, medical imaging, black hole imaging, seismology, and fluid dynamics. With \textsc{InverseBench}, we benchmark 14 inverse problem algorithms that use plug-and-play diffusion priors against strong, domain-specific baselines, offering valuable new insights into the strengths and weaknesses of existing algorithms. To facilitate further research and development, we open-source the codebase, along with datasets and pre-trained models, at [https://devzhk.github.io/InverseBench/](https://devzhk.github.io/InverseBench/).

Recent advances in self-supervised models for natural language, vision, and protein sequences have inspired the development of large genomic DNA language models (DNALMs). These models aim to learn generalizable representations of diverse DNA elements, potentially enabling various genomic prediction, interpretation and design tasks. Despite their potential, existing benchmarks do not adequately assess the capabilities of DNALMs on key downstream applications involving an important class of non-coding DNA elements critical for regulating gene activity. In this study, we introduce DART-Eval, a suite of representative benchmarks specifically focused on regulatory DNA to evaluate model performance across zero-shot, probed, and fine-tuned scenarios against contemporary ab initio models as baselines. Our benchmarks target biologically meaningful downstream tasks such as functional sequence feature discovery, predicting cell-type specific regulatory activity, and counterfactual prediction of the impacts of genetic variants. We find that current DNALMs exhibit inconsistent performance and do not offer compelling gains over alternative baseline models for most tasks, while requiring significantly more computational resources. We discuss potentially promising modeling, data curation, and evaluation strategies for the next generation of DNALMs. Our code is available at https://github.com/kundajelab/DART-Eval

There is an open call for technology to be more playful [5, 79] and for tech design to be more inclusive of people with disabilities [80]. In the era of COVID19, it is often unsafe for the public in general and people with disabilities, in particular, to engage in in-person design exercises using traditional methods. This presents a missed opportunity as these populations are already sharing playful content rich with tacit design knowledge that can be used to inspire the design of playful everyday technology. We present our process of scraping play potentials [4] from TikTok from content creators with disabilities to generate design concepts that may inspire future technology design. We share 7 emerging themes from the scraped content, a catalog of design concepts that may inspire designers, and discuss the relevance of the emerging themes and possible implications for the design concepts.

This paper presents an unsupervised, content-based approach to match users with shorter pieces of specific learning content, lectures, to target their learning goals at a more granular level. This method is especially useful when implicit data is unreliable or limited. At a high level, our approach generates a set of lectures for every topic via clustering and then matches lectures to users via users' topic affinities. Our central hypothesis is that important, fundamental concepts are repeated within many courses on the same topic, and by extracting clusters, we can identify these key information lectures per topic.

We present a real-time algorithm for emotion-aware navigation of a socially-assistive robot among pedestrians. Our approach estimates time-varying emotional dynamics and behaviors of people from multiple modalities (i.e., their faces and trajectories) using a combination of deep-learning, and affective features from the PAD (Pleasure-Arousal-Dominance) model from psychology. These PAD characteristics are used to predict pedestrian movement with proxemic constraints. We use a multi-channel model to classify pedestrian characteristics into four emotion categories (happy, sad, angry, neutral). In our validation results, we observe an emotion detection accuracy of 85.33parcent. We formulate emotion-based proxemic constraints to perform socially-aware robot navigation in low- to medium density environments. We demonstrate the benefits of our algorithm in simulated environments with tens of pedestrians as well as in a real-world setting with Pepper, a social humanoid robot.

We present a Pedestrian Dominance Model (PDM) to identify the dominance characteristics of pedestrians for robot navigation. Through a perception study on a simulated dataset of pedestrians, PDM models the perceived dominance levels of pedestrians with varying motion behaviors corresponding to trajectory, speed, and personal space. At runtime, we use PDM to identify the dominance levels of pedestrians to facilitate socially-aware navigation for the robots. PDM can predict dominance levels from trajectories with ~85% accuracy. Prior studies in psychology literature indicate that when interacting with humans, people are more comfortable around people that exhibit complementary movement behaviors. Our algorithm leverages this by enabling the robots to exhibit complementing responses to pedestrian dominance. We also present an application of PDM for generating dominance-based collision-avoidance behaviors in the navigation of autonomous vehicles among pedestrians. We demonstrate the benefits of our algorithm for robots navigating among tens of pedestrians in simulated environments.

We present a real-time, data-driven algorithm to enhance the social-invisibility of robots within crowds. Our approach is based on prior psychological research, which reveals that people notice and-importantly-react negatively to groups of social actors when they have high entitativity, moving in a tight group with similar appearances and trajectories. In order to evaluate that behavior, we performed a user study to develop navigational algorithms that minimize entitativity. This study establishes mapping between emotional reactions and multi-robot trajectories and appearances, and further generalizes the finding across various environmental conditions. We demonstrate the applicability of our entitativity modeling for trajectory computation for active surveillance and dynamic intervention in simulated robot-human interaction scenarios. Our approach empirically shows that various levels of entitative robots can be used to both avoid and influence pedestrians while not eliciting strong emotional reactions, giving multi-robot systems socially-invisibility.