However, many event-based depth estimation approaches are constrained by small-scale annotated datasets, limiting their generalizability to real-world scenarios. T o bridge this gap, we introduce EvtSlowTV, a large-scale event camera dataset curated from publicly available Y ouTube footage, which contains more than 13B events across various environmental conditions and motions, including seasonal hiking, flying, scenic driving, and underwater exploration. EvtSlowTV is an order of magnitude larger than existing event datasets, providing an unconstrained, naturalistic setting for event-based depth learning. This work shows the suitability of EvtSlowTV for a self-supervised learning framework to capitalise on the HDR potential of raw event streams. W e further demonstrate that training with EvtSlowTV enhances the model's ability to generalise to complex scenes and motions. Our approach removes the need for frame-based annotations and preserves the asynchronous nature of event data. The EvtSlowTV dataset and tools can be downloaded at .

Efforts have increased in recent years to identify associations between specific datasets and the scientific literature that incorporates them. Knowing that a given publication cites a given dataset, the next logical step is to explore how or why that data was used. Advances in recent years with pretrained, transformer-based large language models (LLMs) offer potential means for scaling the description of data use cases in the published literature. This avoids expensive manual labeling and the development of training datasets for classical machine-learning (ML) systems. In this work we apply an open-source LLM, Llama 3.1-405B, to generate structured data use case labels for publications known to incorporate specific genomic datasets. We also introduce a novel evaluation framework for determining the efficacy of our methods. Our results demonstrate that the stock model can achieve an F1 score of .674 on a zero-shot data citation classification task with no previously defined categories. While promising, our results are qualified by barriers related to data availability, prompt overfitting, computational infrastructure, and the expense required to conduct responsible performance evaluation.

Data augmentation is widely used in vision to introduce variation and mitigate overfitting, through enabling models to learn invariant properties, such as spatial invariance. However, these properties are not fully captured by data augmentation alone, since it attempts to learn the property on transformations of the training data only. We propose generative hints, a training methodology that directly enforces known invariances in the entire input space. Our approach leverages a generative model trained on the training set to approximate the input distribution and generate unlabeled images, which we refer to as virtual examples. These virtual examples are used to enforce functional properties known as hints. In generative hints, although the training dataset is fully labeled, the model is trained in a semi-supervised manner on both the classification and hint objectives, using the unlabeled virtual examples to guide the model in learning the desired hint. Across datasets, architectures, and loss functions, generative hints consistently outperform standard data augmentation when learning the same property. On popular fine-grained visual classification benchmarks, we achieved up to 1.78% top-1 accuracy improvement (0.63% on average) over fine-tuned models with data augmentation and an average performance boost of 1.286% on the CheXpert X-ray dataset.

Nucleotide sequence variation can induce significant shifts in functional fitness. Recent nucleotide foundation models promise to predict such fitness effects directly from sequence, yet heterogeneous datasets and inconsistent preprocessing make it difficult to compare methods fairly across DNA and RNA families. Here we introduce NABench, a large-scale, systematic benchmark for nucleic acid fitness prediction. NABench aggregates 162 high-throughput assays and curates 2.6 million mutated sequences spanning diverse DNA and RNA families, with standardized splits and rich metadata. We show that NABench surpasses prior nucleotide fitness benchmarks in scale, diversity, and data quality. Under a unified evaluation suite, we rigorously assess 29 representative foundation models across zero-shot, few-shot prediction, transfer learning, and supervised settings. The results quantify performance heterogeneity across tasks and nucleic-acid types, demonstrating clear strengths and failure modes for different modeling choices and establishing strong, reproducible baselines. We release NABench to advance nucleic acid modeling, supporting downstream applications in RNA/DNA design, synthetic biology, and biochemistry. Our code is available at https://github.com/mrzzmrzz/NABench.

The North Indian Ocean, including the Arabian Sea and the Bay of Bengal, represents a vital source of livelihood for coastal communities, yet fishermen often face uncertainty in locating productive fishing grounds. To address this challenge, we present an AI-assisted framework for predicting Potential Fishing Zones (PFZs) using oceanographic parameters such as sea surface temperature and chlorophyll concentration. The approach is designed to enhance the accuracy of PFZ identification and provide region-specific insights for sustainable fishing practices. Preliminary results indicate that the framework can support fishermen by reducing search time, lowering fuel consumption, and promoting efficient resource utilization.

AI components are increasingly becoming a key element of all types of software systems to enhance their functionality. These AI components are often implemented as AI Agents, offering more autonomy than a plain integration of Large Language Models (LLMs), moving from a Model-as-a-Service paradigm to an Agent-as-a-Service one, bringing new challenges to the development of smart software systems. Indeed, while support for the design, implementation, and deployment of those agents exist, the specification of Quality of Service (QoS) and definition of Service Level Agreements (SLAs) aspects for those agents, important to ensure the quality of the resulting systems, remains an open challenge. Part of this is due to the difficulty to clearly define quality in the context of AI components, resulting in a lack of consensus on how to best approach Quality Assurance (QA) for these types of systems. To address this challenge, this paper proposes both a quality model for AI agents based on the ISO/IEC 25010 standard, and a domain specific language to support the definition of SLAs for the services provided by these AI agents.

While prior work on group recommender systems (GRSs) has primarily focused on improving recommendation accuracy, most approaches assume static or predefined groups, making them unsuitable for dynamic, real-world scenarios. We reframe group formation as a core challenge in GRSs and propose DeepForm (Stochastic Deep Graph Clustering for Practical Group Formation), a framework designed to meet three key operational requirements: (1) the incorporation of high-order user information, (2) real-time group formation, and (3) dynamic adjustment of the number of groups. DeepForm employs a lightweight GCN architecture that effectively captures high-order structural signals. Stochastic cluster learning enables adaptive group reconfiguration without retraining, while contrastive learning refines groups under dynamic conditions. Experiments on multiple datasets demonstrate that DeepForm achieves superior group formation quality, efficiency, and recommendation accuracy compared with various baselines.

As generative AI diffuses through academia, policy-practice divergence becomes consequential, creating demand for auditable indicators of alignment. This study prototypes a ten-item, indirect-elicitation instrument embedded in a structured interpretive framework to surface voids between institutional rules and practitioner AI use. The framework extracts empirical and epistemic signals from academics, yielding three filtered indicators of such voids: (1) AI-integrated assessment capacity (proxy) - within a three-signal screen (AI skill, perceived teaching benefit, detection confidence), the share who would fully allow AI in exams; (2) sector-level necessity (proxy) - among high output control users who still credit AI with high contribution, the proportion who judge AI capable of challenging established disciplines; and (3) ontological stance - among respondents who judge AI different in kind from prior tools, report practice change, and pass a metacognition gate, the split between material and immaterial views as an ontological map aligning procurement claims with evidence classes.

Abstract--Blockchain systems face persistent challenges of scalability, latency, and energy inefficiency. Existing consensus protocols such as Proof-of-Work (PoW) and Proof-of-Stake (PoS) either consume excessive resources or risk centralization. This paper proposes Proof-of-Spiking-Neurons (PoSN), a neuromor-phic consensus protocol inspired by spiking neural networks. A hybrid system architecture is implemented on neuromorphic platforms, supported by simulation frameworks such as Nengo and PyNN. Experimental results show significant gains in energy efficiency, throughput, and convergence compared to PoB and PoR. PoSN establishes a foundation for sustainable, adaptive blockchains suitable for IoT, edge, and large-scale distributed systems. Index T erms--Blockchain consensus, Neuromorphic computing, Distributed ledger technology.

Abstract--Bit-flip attacks threaten the reliability and security of Language Models (LMs) by altering internal parameters and compromising output integrity. Recent studies show that flipping only a few bits in model parameters can bypass safety mechanisms and jailbreak the model. Existing detection approaches for DNNs and CNNs are not suitable for LMs, as the massive number of parameters significantly increases timing and memory overhead for software-based methods and chip area overhead for hardware-based methods. In this work, we present LM-Fix, a lightweight LM-driven detection and recovery framework that leverages the model's own capabilities to identify and recover faults. Our method detects bit-flips by generating a single output token from a predefined test vector and auditing the output tensor of a target layer against stored reference data. The same mechanism enables rapid recovery without reloading the entire model. Experiments across various models show that LM-Fix detects more than 94% of single-bit flips and nearly 100% of multi-bit flips, with very low computational overhead ( 1%- 7.7% at TVL = 200 across models). Recovery achieves more than 100 speedup compared to full-model reload, which is critical in edge devices. LM-Fix can handle bit-flips affecting any part of the model's computation, including memory, cache, and arithmetic operations. Evaluation against recent LM-specific bit-flip attacks confirms its robustness and practical value for real-world deployment.