Reflectance Confocal Microscopy (RCM) marks a paradigm shift in biomedical imaging, offering a sophisticated, non-invasive technique to acquire high-resolution images of the skin and superficial tissues. Its development [1] represents a milestone in medical imaging, transitioning from early exploratory stages to becoming a cornerstone in clinical dermatology. RCM's capability for in vivo imaging, capturing live tissue images without the need for biopsies or tissue excision, has made it an indispensable tool in modern medical diagnostics. The inception of RCM can be traced back to its early conceptualization, where the need for less invasive, more accurate diagnostic methods in dermatology was recognized. Over the years, the technology has undergone significant advancements, evolving in its design and functionality. This evolution has been marked by improvements in laser source quality, detector sensitivity, and image processing algorithms, resulting in enhanced image clarity and depth of tissue analysis. RCM's operation relies on a focused laser light to illuminate the target tissue. The tissue interaction with this light, primarily through backscattering and reflection, forms the basis of image creation.

Multicopters are among the most versatile mobile robots. Their applications range from inspection and mapping tasks to providing vital reconnaissance in disaster zones and to package delivery. The range, endurance, and speed a multirotor vehicle can achieve while performing its task is a decisive factor not only for vehicle design and mission planning, but also for policy makers deciding on the rules and regulations for aerial robots. To the best of the authors' knowledge, this work proposes the first approach to estimate the range, endurance, and optimal flight speed for a wide variety of multicopters. This advance is made possible by combining a state-of-the-art first-principles aerodynamic multicopter model based on blade-element-momentum theory with an electric-motor model and a graybox battery model. This model predicts the cell voltage with only 1.3% relative error (43.1 mV), even if the battery is subjected to non-constant discharge rates. Our approach is validated with real-world experiments on a test bench as well as with flights at speeds up to 65 km/h in one of the world's largest motion-capture systems. We also present an accurate pen-and-paper algorithm to estimate the range, endurance and optimal speed of multicopters to help future researchers build drones with maximal range and endurance, ensuring that future multirotor vehicles are even more versatile.

In safety-critical systems that interface with the real world, the role of uncertainty in decision-making is pivotal, particularly in the context of machine learning models. For the secure functioning of Cyber-Physical Systems (CPS), it is imperative to manage such uncertainty adeptly. In this research, we focus on the development of a vehicle's lateral control system using a machine learning framework. Specifically, we employ a Bayesian Neural Network (BNN), a probabilistic learning model, to address uncertainty quantification. This capability allows us to gauge the level of confidence or uncertainty in the model's predictions. The BNN based controller is trained using simulated data gathered from the vehicle traversing a single track and subsequently tested on various other tracks. We want to share two significant results: firstly, the trained model demonstrates the ability to adapt and effectively control the vehicle on multiple similar tracks. Secondly, the quantification of prediction confidence integrated into the controller serves as an early-warning system, signaling when the algorithm lacks confidence in its predictions and is therefore susceptible to failure. By establishing a confidence threshold, we can trigger manual intervention, ensuring that control is relinquished from the algorithm when it operates outside of safe parameters.

Recent dataset deduplication techniques have demonstrated that content-aware dataset pruning can dramatically reduce the cost of training Vision-Language Pretrained (VLP) models without significant performance losses compared to training on the original dataset. These results have been based on pruning commonly used image-caption datasets collected from the web -- datasets that are known to harbor harmful social biases that may then be codified in trained models. In this work, we evaluate how deduplication affects the prevalence of these biases in the resulting trained models and introduce an easy-to-implement modification to the recent SemDeDup algorithm that can reduce the negative effects that we observe. When examining CLIP-style models trained on deduplicated variants of LAION-400M, we find our proposed FairDeDup algorithm consistently leads to improved fairness metrics over SemDeDup on the FairFace and FACET datasets while maintaining zero-shot performance on CLIP benchmarks.

In RAG, the model's knowledge can be updated from documents provided in context. This leads to cases of conflict between the model's parametric knowledge and the contextual information, where the model may not always update its knowledge. Previous work studied knowledge conflicts by creating synthetic documents that contradict the model's correct parametric answers. We present a framework for studying knowledge conflicts in a realistic setup. We update incorrect parametric knowledge using real conflicting documents. This reflects how knowledge conflicts arise in practice. In this realistic scenario, we find that knowledge updates fail less often than previously reported. In cases where the models still fail to update their answers, we find a parametric bias: the incorrect parametric answer appearing in context makes the knowledge update likelier to fail. These results suggest that the factual parametric knowledge of LLMs can negatively influence their reading abilities and behaviors.

Recent work has developed optimization procedures to find token sequences, called adversarial triggers, which can elicit unsafe responses from aligned language models. These triggers are believed to be universally transferable, i.e., a trigger optimized on one model can jailbreak other models. In this paper, we concretely show that such adversarial triggers are not universal. We extensively investigate trigger transfer amongst 13 open models and observe inconsistent transfer. Our experiments further reveal a significant difference in robustness to adversarial triggers between models Aligned by Preference Optimization (APO) and models Aligned by Fine-Tuning (AFT). We find that APO models are extremely hard to jailbreak even when the trigger is optimized directly on the model. On the other hand, while AFT models may appear safe on the surface, exhibiting refusals to a range of unsafe instructions, we show that they are highly susceptible to adversarial triggers. Lastly, we observe that most triggers optimized on AFT models also generalize to new unsafe instructions from five diverse domains, further emphasizing their vulnerability. Overall, our work highlights the need for more comprehensive safety evaluations for aligned language models.

Misinformation about climate change poses a significant threat to societal well-being, prompting the urgent need for effective mitigation strategies. However, the rapid proliferation of online misinformation on social media platforms outpaces the ability of fact-checkers to debunk false claims. Automated detection of climate change misinformation offers a promising solution. In this study, we address this gap by developing a two-step hierarchical model, the Augmented CARDS model, specifically designed for detecting contrarian climate claims on Twitter. Furthermore, we apply the Augmented CARDS model to five million climate-themed tweets over a six-month period in 2022. We find that over half of contrarian climate claims on Twitter involve attacks on climate actors or conspiracy theories. Spikes in climate contrarianism coincide with one of four stimuli: political events, natural events, contrarian influencers, or convinced influencers. Implications for automated responses to climate misinformation are discussed.

Large language models (LLMs) have shown remarkable performance on a variety of NLP tasks, and are being rapidly adopted in a wide range of use cases. It is therefore of vital importance to holistically evaluate the factuality of their generated outputs, as hallucinations remain a challenging issue. In this work, we focus on assessing LLMs' ability to recall factual knowledge learned from pretraining, and the factors that affect this ability. To that end, we construct FACT-BENCH, a representative benchmark covering 20 domains, 134 property types, 3 answer types, and different knowledge popularity levels. We benchmark 31 models from 10 model families and provide a holistic assessment of their strengths and weaknesses. We observe that instruction-tuning hurts knowledge recall, as pretraining-only models consistently outperform their instruction-tuned counterparts, and positive effects of model scaling, as larger models outperform smaller ones for all model families. However, the best performance from GPT-4 still represents a large gap with the upper-bound. We additionally study the role of in-context exemplars using counterfactual demonstrations, which lead to significant degradation of factual knowledge recall for large models. By further decoupling model known and unknown knowledge, we find the degradation is attributed to exemplars that contradict a model's known knowledge, as well as the number of such exemplars. Lastly, we fine-tune LLaMA-7B in different settings of known and unknown knowledge. In particular, fine-tuning on a model's known knowledge is beneficial, and consistently outperforms fine-tuning on unknown and mixed knowledge. We will make our benchmark publicly available.

Effective code optimization in compilers plays a central role in computer and software engineering. While compilers can be made to automatically search the optimization space without the need for user interventions, this is not a standard practice since the search is slow and cumbersome. Here we present CodeZero, an artificial intelligence agent trained extensively on large data to produce effective optimization strategies instantly for each program in a single trial of the agent. To overcome the huge range of possible test programs, we prepare a large dataset of training programs that emphasize quality, naturalness, and diversity. To tackle the vast space of possible optimizations, we adapt deep reinforcement learning to train the agent in a sample-efficient manner through interacting with a world model of the compiler environment. Evaluation on both benchmark suites and production-level code optimization problems demonstrates our agent's supercompiler performances and zero-shot generalization abilities, outperforming built-in optimization options designed by compiler experts. Our methodology kindles the great potential of artificial intelligence for engineering and paves the way for scaling machine learning techniques in the realm of code optimization.

Structured data sources, such as tables, graphs, and databases, are ubiquitous knowledge sources. Despite the demonstrated capabilities of large language models (LLMs) on plain text, their proficiency in interpreting and utilizing structured data remains limited. Our investigation reveals a notable deficiency in LLMs' ability to process structured data, e.g., ChatGPT lags behind state-of-the-art (SoTA) model by an average of 35%. To augment the Structured Knowledge Grounding (SKG) capabilities in LLMs, we have developed a comprehensive instruction tuning dataset comprising 1.1 million examples. Utilizing this dataset, we train a series of models, referred to as StructLM, based on the Mistral and the CodeLlama model family, ranging from 7B to 34B parameters. Our StructLM series surpasses task-specific models on 16 out of 18 evaluated datasets and establishes new SoTA performance on 8 SKG tasks. Furthermore, StructLM demonstrates strong generalization across 6 novel held-out SKG tasks, outperforming TableLlama by an average of 35\% and Flan-UL2 20B by an average of 10\%. Contrary to expectations, we observe that scaling model size offers marginal benefits, with StructLM-34B showing only slight improvements over StructLM-7B. This suggests that structured knowledge grounding is still a challenging task and requires more innovative design to push to a new level.