Existing scholarly information extraction (SIE) datasets focus on scientific papers and overlook implementation-level details in code repositories. README files describe datasets, source code, and other implementation-level artifacts, however, their free-form Markdown offers little semantic structure, making automatic information extraction difficult. To address this gap, NERdME is introduced: 200 manually annotated README files with over νm10000 labeled spans and 10 entity types. Baseline results using large language models and fine-tuned transformers show clear differences between paper-level and implementation-level entities, indicating the value of extending SIE benchmarks with entity types available in README files. A downstream entity-linking experiment was conducted to demonstrate that entities derived from READMEs can support artifact discovery and metadata integration.

Warning: This paper contains offensive content that may disturb some readers. Vision-language models (VLMs) demonstrate strong multimodal capabilities but have been found to be more susceptible to generating harmful content compared to their backbone large language models (LLMs). Our investigation reveals that the integration of images significantly shifts the model's internal activations during the forward pass, diverging from those triggered by textual input. Moreover, the safety alignments of LLMs embedded within VLMs are not sufficiently robust to handle the activations discrepancies, making the models vulnerable to even the simplest jailbreaking attacks. To address this issue, we propose an internal activation revision approach that efficiently revises activations during generation, steering the model toward safer outputs. Our framework incorporates revisions at both the layer and head levels, offering control over the model's generation at varying levels of granularity. In addition, we explore three strategies for constructing positive and negative samples and two approaches for extracting revision vectors, resulting in different variants of our method. Comprehensive experiments demonstrate that the internal activation revision method significantly improves the safety of widely used VLMs, reducing attack success rates by an average of 48.94%, 34.34%, 43.92%, and 52.98% on SafeBench, Safe-Unsafe, Unsafe, and MM-SafetyBench, respectively, while minimally impacting model helpfulness.

6173

Dataset distillation is an increasingly prevalent technique for condensing a large-scale dataset into more compact versions while preserving their intrinsic utility. However, very few studies have investigated the trustworthiness of data distillation, i.e., privacy, robustness, and fairness. The deficiency is particularly striking given the existing research that underscores the vulnerabilities in current AI models, including privacy breaches, biased predictions against underrepresented subgroups, and susceptibility to imperceptible attacks. To bridge the gap, we propose a trustworthy benchmark for assessing representative dataset distillation solutions across the benchmark CIFAR10 with comprehensive evaluation metrics. Through extensive experiments, we uncover vulnerabilities inherent in the application of dataset distillation, offering valuable insights for practitioners. Our work aims to drive the development of more transparent, reliable, and responsible machine learning models, fostering AI systems that align with trustworthy principles.

Dataset distillation is attracting more attention in machine learning as training sets continue to grow and the cost of training state-of-the-art models becomes increasingly high. By synthesizing datasets with high information density, dataset distillation offers a range of potential applications, including support for continual learning, neural architecture search, and privacy protection. Despite recent advances, we lack a holistic understanding of the approaches and applications. Our survey aims to bridge this gap by first proposing a taxonomy of dataset distillation, characterizing existing approaches, and then systematically reviewing the data modalities, and related applications. In addition, we summarize the challenges and discuss future directions for this field of research.

Stream Processing Engines (SPEs) execute long-running queries on unbounded data streams. They follow an interpretation-based processing model and do not perform runtime optimizations. This limits the utilization of modern hardware and neglects changing data characteristics at runtime. In this paper, we present Grizzly, a novel adaptive query compilation-based SPE, to enable highly efficient query execution. We extend query compilation and task-based parallelization for the unique requirements of stream processing and apply adaptive compilation to enable runtime re-optimizations. The combination of light-weight statistic gathering with just-in-time compilation enables Grizzly to adjust to changing data-characteristics dynamically at runtime. Our experiments show that Grizzly outperforms state-of-the-art SPEs by up to an order of magnitude in throughput.