Lightweight autonomous unmanned aerial vehicles (UAV) are emerging as a central component of a broad range of applications. However, autonomous navigation necessitates the implementation of perception algorithms, often deep neural networks (DNN), that process the input of sensor observations, such as that from cameras and LiDARs, for control logic. The complexity of such algorithms clashes with the severe constraints of these devices in terms of computing power, energy, memory, and execution time. In this paper, we propose NaviSplit, the first instance of a lightweight navigation framework embedding a distributed and dynamic multi-branched neural model. At its core is a DNN split at a compression point, resulting in two model parts: (1) the head model, that is executed at the vehicle, which partially processes and compacts perception from sensors; and (2) the tail model, that is executed at an interconnected compute-capable device, which processes the remainder of the compacted perception and infers navigation commands. Different from prior work, the NaviSplit framework includes a neural gate that dynamically selects a specific head model to minimize channel usage while efficiently supporting the navigation network. In our implementation, the perception model extracts a 2D depth map from a monocular RGB image captured by the drone using the robust simulator Microsoft AirSim. Our results demonstrate that the NaviSplit depth model achieves an extraction accuracy of 72-81% while transmitting an extremely small amount of data (1.2-18 KB) to the edge server. When using the neural gate, as utilized by NaviSplit, we obtain a slightly higher navigation accuracy as compared to a larger static network by 0.3% while significantly reducing the data rate by 95%. To the best of our knowledge, this is the first exemplar of dynamic multi-branched model based on split DNNs for autonomous navigation.

The rapid development of large language models (LLMs) has shown promising practical results. However, their low interpretability often leads to errors in unforeseen circumstances, limiting their utility. Many works have focused on creating comprehensive evaluation systems, but previous benchmarks have primarily assessed problem-solving abilities while neglecting the response's uncertainty, which may result in unreliability. Recent methods for measuring LLM reliability are resource-intensive and unable to test black-box models. To address this, we propose UBENCH, a comprehensive benchmark for evaluating LLM reliability. UBENCH includes 3,978 multiple-choice questions covering knowledge, language, understanding, and reasoning abilities. Experimental results show that UBENCH has achieved state-of-the-art performance, while its single-sampling method significantly saves computational resources compared to baseline methods that require multiple samplings. Additionally, based on UBENCH, we evaluate the reliability of 15 popular LLMs, finding GLM4 to be the most outstanding, closely followed by GPT-4. We also explore the impact of Chain-of-Thought prompts, role-playing prompts, option order, and temperature on LLM reliability, analyzing the varying effects on different LLMs.

With the increasing role of Natural Language Processing (NLP) in various applications, challenges concerning bias and stereotype perpetuation are accentuated, which often leads to hate speech and harm. Despite existing studies on sexism and misogyny, issues like homophobia and transphobia remain underexplored and often adopt binary perspectives, putting the safety of LGBTQIA+ individuals at high risk in online spaces. In this paper, we assess the potential harm caused by sentence completions generated by English large language models (LLMs) concerning LGBTQIA+ individuals. This is achieved using QueerBench, our new assessment framework, which employs a template-based approach and a Masked Language Modeling (MLM) task. The analysis indicates that large language models tend to exhibit discriminatory behaviour more frequently towards individuals within the LGBTQIA+ community, reaching a difference gap of 7.2% in the QueerBench score of harmfulness.

Purpose: Autonomous navigation of catheters and guidewires can enhance endovascular surgery safety and efficacy, reducing procedure times and operator radiation exposure. Integrating tele-operated robotics could widen access to time-sensitive emergency procedures like mechanical thrombectomy (MT). Reinforcement learning (RL) shows potential in endovascular navigation, yet its application encounters challenges without a reward signal. This study explores the viability of autonomous navigation in MT vasculature using inverse RL (IRL) to leverage expert demonstrations. Methods: This study established a simulation-based training and evaluation environment for MT navigation. We used IRL to infer reward functions from expert behaviour when navigating a guidewire and catheter. We utilized soft actor-critic to train models with various reward functions and compared their performance in silico. Results: We demonstrated feasibility of navigation using IRL. When evaluating single versus dual device (i.e. guidewire versus catheter and guidewire) tracking, both methods achieved high success rates of 95% and 96%, respectively. Dual-tracking, however, utilized both devices mimicking an expert. A success rate of 100% and procedure time of 22.6 s were obtained when training with a reward function obtained through reward shaping. This outperformed a dense reward function (96%, 24.9 s) and an IRL-derived reward function (48%, 59.2 s). Conclusions: We have contributed to the advancement of autonomous endovascular intervention navigation, particularly MT, by employing IRL. The results underscore the potential of using reward shaping to train models, offering a promising avenue for enhancing the accessibility and precision of MT. We envisage that future research can extend our methodology to diverse anatomical structures to enhance generalizability.

Large Language Models (LLMs) are increasingly being used in educational and learning applications. Research has demonstrated that controlling for style, to fit the needs of the learner, fosters increased understanding, promotes inclusion, and helps with knowledge distillation. To understand the capabilities and limitations of contemporary LLMs in style control, we evaluated five state-of-the-art models: GPT-3.5, GPT-4, GPT-4o, Llama-3, and Mistral-instruct-7B across two style control tasks. We observed significant inconsistencies in the first task, with model performances averaging between 5th and 8th grade reading levels for tasks intended for first-graders, and standard deviations up to 27.6. For our second task, we observed a statistically significant improvement in performance from 0.02 to 0.26. However, we find that even without stereotypes in reference texts, LLMs Figure 1: Overall view of this paper. We find that while often generated culturally insensitive content in-context learning can control for reading level and during their tasks. We provide a thorough analysis simplicity, it cannot do the same for vernacular English.

Differentiable Search Index (DSI) utilizes Pre-trained Language Models (PLMs) for efficient document retrieval without relying on external indexes. However, DSIs need full re-training to handle updates in dynamic corpora, causing significant computational inefficiencies. We introduce PromptDSI, a rehearsal-free, prompt-based approach for instance-wise incremental learning in document retrieval. PromptDSI attaches prompts to the frozen PLM's encoder of DSI, leveraging its powerful representation to efficiently index new corpora while maintaining a balance between stability and plasticity. We eliminate the initial forward pass of prompt-based continual learning methods that doubles training and inference time. Moreover, we propose a topic-aware prompt pool that employs neural topic embeddings as fixed keys. This strategy ensures diverse and effective prompt usage, addressing the challenge of parameter underutilization caused by the collapse of the query-key matching mechanism. Our empirical evaluations demonstrate that PromptDSI matches IncDSI in managing forgetting while significantly enhancing recall by over 4% on new corpora.

While deep neural networks have demonstrated groundbreaking performance in various settings, these models often suffer from \emph{catastrophic forgetting} when trained on new tasks in sequence. Several works have empirically demonstrated that increasing the width of a neural network leads to a decrease in catastrophic forgetting but have yet to characterize the exact relationship between width and continual learning. We design one of the first frameworks to analyze Continual Learning Theory and prove that width is directly related to forgetting in Feed-Forward Networks (FFN). Specifically, we demonstrate that increasing network widths to reduce forgetting yields diminishing returns. We empirically verify our claims at widths hitherto unexplored in prior studies where the diminishing returns are clearly observed as predicted by our theory.

Despite significant progress in generative AI, comprehensive evaluation remains challenging because of the lack of effective metrics and standardized benchmarks. For instance, the widely-used CLIPScore measures the alignment between a (generated) image and text prompt, but it fails to produce reliable scores for complex prompts involving compositions of objects, attributes, and relations. One reason is that text encoders of CLIP can notoriously act as a "bag of words", conflating prompts such as "the horse is eating the grass" with "the grass is eating the horse". To address this, we introduce the VQAScore, which uses a visual-question-answering (VQA) model to produce an alignment score by computing the probability of a "Yes" answer to a simple "Does this figure show '{text}'?" question. Though simpler than prior art, VQAScore computed with off-the-shelf models produces state-of-the-art results across many (8) image-text alignment benchmarks. We also compute VQAScore with an in-house model that follows best practices in the literature. For example, we use a bidirectional image-question encoder that allows image embeddings to depend on the question being asked (and vice versa). Our in-house model, CLIP-FlanT5, outperforms even the strongest baselines that make use of the proprietary GPT-4V. Interestingly, although we train with only images, VQAScore can also align text with video and 3D models. VQAScore allows researchers to benchmark text-to-visual generation using complex texts that capture the compositional structure of real-world prompts. We introduce GenAI-Bench, a more challenging benchmark with 1,600 compositional text prompts that require parsing scenes, objects, attributes, relationships, and high-order reasoning like comparison and logic. GenAI-Bench also offers over 15,000 human ratings for leading image and video generation models such as Stable Diffusion, DALL-E 3, and Gen2.

Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://humanoid-bench.github.io.

In the scenario-based evaluation of machine learning models, a key problem is how to construct test datasets that represent various scenarios. The methodology proposed in this paper is to construct a benchmark and attach metadata to each test case. Then a test system can be constructed with test morphisms that filter the test cases based on metadata to form a dataset. The paper demonstrates this methodology with large language models for code generation. A benchmark called ScenEval is constructed from problems in textbooks, an online tutorial website and Stack Overflow. Filtering by scenario is demonstrated and the test sets are used to evaluate ChatGPT for Java code generation. Our experiments found that the performance of ChatGPT decreases with the complexity of the coding task. It is weakest for advanced topics like multi-threading, data structure algorithms and recursive methods. The Java code generated by ChatGPT tends to be much shorter than reference solution in terms of number of lines, while it is more likely to be more complex in both cyclomatic and cognitive complexity metrics, if the generated code is correct. However, the generated code is more likely to be less complex than the reference solution if the code is incorrect.