Oracle Bone Script, East Asia's earliest mature writing system from over 3,500 years ago, encodes ancient cognition through visual metaphors, yet remains largely undeciphered and inaccessible, severing modern society from its cultural roots. Traditional AI methods, while accurate in classification, treat glyphs as opaque data, neglecting their pictographic essence and failing to foster public understanding—exacerbating a heritage crisis amid linguistic evolution. We pioneer a paradigm shift toward AI-driven cultural democratization, introducing OracleVis, the first human-validated multimodal dataset of glyph-image-explanation triplets, curated through expert collaborations to overcome data scarcity, bias, and incompleteness in archaeological sources. Building on this, OBS-VM, an explainability-centric multimodal large language model fine-tuned on Qwen2-VL-7B, models pictographic reasoning by balancing semantic fidelity with interpretive transparency, transforming black-box predictions into cognition-aligned narratives. Rigorous evaluations, including benchmarks and a user study with 24 non-experts, reveal our system's superiority: it outperforms GPT-4o in pictographic rationality (3.79 vs. 3.58 in human evaluation) and achieves a 35.3% relative improvement in recognition accuracy, while interactive learning boosts knowledge gains (+5.5 vs. +1.7), interest (+1.9 vs. +0.4), and confidence (+2.0 vs. +0.3) over static methods. This work illuminates AI's potential to bridge ancient wisdom and contemporary audiences, redefining heritage preservation as an inclusive, socially impactful endeavor that turns cultural alienation into enlightened engagement.

Data tables play a central role in scientific papers. However, their meaning is often co-constructed with surrounding text through narrative interplay, making comprehension cognitively demanding for readers. In this work, we explore how interfaces can better support this reading process. We conducted a formative study that revealed key characteristics of text-table narrative interplay, including linking mechanisms, multi-granularity alignments, and mention typologies, as well as a layered framework of readers’ intents. Informed by these insights, we present TableTale, an augmented reading interface that enriches text with data tables at multiple granularities, including paragraphs, sentences, and mentions. TableTale automatically constructs a document-level linking schema within the paper and progressively renders cascade visual cues on text and tables that unfold as readers move through the text. A within-subject study with 24 participants showed that TableTale reduced cognitive workload and improved reading efficiency, demonstrating its potential to enhance paper reading and inform future reading interface design.

Given the pervasive presence of feedback mechanisms and inertial loops inherent in industrial processes, increasing research efforts have focused on integrating latent feature dynamics into deep learning architectures to address the issue of strong dynamic autocorrelation in industrial processes. However, the complex temporal dependencies present in latent features and the limitations imposed by traditional alternating training methods have already constrained the performance of such models. In this paper, we propose a latent probabilistic dynamics embedding supervised deep networks for soft sensing. In detail, a probabilistic dynamic model with graph-guiding based on the past and current latent features is constructed in the latent space of the supervised deep networks to capture the complex dependencies between the latent sequences. The article introduces a new approach involving a probability-distribution-based predictive regularization term for latent features. By jointly training the model, the network parameters are optimized to ensure the overall convergence of the network. An improved variational graph recurrent neural network with the inclusion of randomness into the high-level latent space was proposed to model the latent dynamics for supervised deep networks and additional graph structure information to help analyze temporal dependencies. Finally, the proposed methods are implemented on two real industrial cases to demonstrate their effectiveness and superiority. Comparative experiments and ablation experiments are designed to illustrate the higher prediction accuracy and effectiveness of the proposed method.

This article proposes a novel selective write-assist circuit and a Sense Amplifier (SA) with adaptive offset improvement for low-voltage Static Random Access Memory (SRAM) applications. Upon detection of a write failure in a single SRAM cell, the write-assist circuit is turned on separately to save power consumption. By adaptively improving the offset of SA, the bitline discharge time during SRAM read operations is shortened, achieving a high-speed SRAM read operation. The proposed circuit was integrated into a 256kb SRAM test chip and manufactured using a 40nm CMOS process. Measurement results show that under specific conditions, the access time is 523ps, the dynamic power is$25.03\mu $W/MHz at VDD = 1.21V. The SRAM remains functional at 176MHz with a dynamic power of$11.84\mu $W/MHz when VDD is reduced to 0.81V.

A novel read circuit for embedded flash memory operating from a single 1.1-V supply is presented, featuring a negative-voltage dual-MOS transmission structure for bitline (BL) transfer and a low-voltage, high-reliability current–voltage sense amplifier (SA). This approach effectively addresses the issue of reduced read window size due to decreased BL voltage as supply voltage decreases. The proposed circuit is integrated into a 4.5-Mbit embedded flash memory test chip, fabricated using a 40-nm CMOS process. Experimental results show a read access time of 18.5 ns at a supply voltage of 0.9 V, with a read throughput of 7.78 Gbit/s and a bit density of 3.414 Mbit/mm2.

A multimodal large language model MLLMs may struggle with answering visual-based (personal) entity questions (VEQA), such as ”who is A?” or ”who is A that B is talking to?” for various reasons, e.g., the absence of the name of A in the caption or the inability of MLLMs to recognize A, particularly for less common entities. Furthermore, even if the MLLMs can identify A, it may refrain from answering due to privacy concerns. In this paper, we introduce a novel method called Matching-Augmented Reasoning (MAR) to enhance VEQA. Given a collection of visual objects with captions, MAR preprocesses each object individually, identifying faces, names, and their alignments within the object. It encodes this information and stores their vector representations in vector databases. When handling VEQA, MAR retrieves matching faces and names and organizes these entities into a matching graph. MAR then derives the answer to the query by reasoning over this matching graph. Extensive experiments show that MAR significantly improves VEQA compared with the state-of-the-art methods using MLLMs.

Multimodal named entity recognition (MNER) aims to detect named entities and identify the entity types based on texts and attached images, which also generates inputs for other comprehensive tasks, such as multimodal machine translation, visual dialog, and multimodal sentiment analysis. Existing studies have limitations in text-image matching and multimodal semantic disparity reduction. For one thing, current methods fail to resolve both overall and local text-image matching issues in a self-guided way. For another, the static graphs constructed in MNER models are challenging in bridging the semantic gap between different modalities. In this work, a dynamic graph construction framework (DGCF) is proposed to solve the above-mentioned limitations. A similarity vector-based text-image matching inferring strategy is designed to obtain the overall and local matching relation between text and image while the overall matching determines the retained proportion of visual information. Then, a multimodal dynamic graph interaction module is developed. Within each layer of the module, the local matching relations and part of speech (POS)-based multihead attention are integrated to construct a dynamic cross-modal graph and a semantic graph. Lastly, a CRF layer is used to predict entity label. Extensive experiments are performed on two benchmark datasets. The experimental results reveal that our model is a competitive alternative and achieves state-of-the-art performance.

Aspect-based sentiment analysis (ABSA) is a fine-grained sentiment analysis task that aims to identify the sentiment polarity of the given aspect. Recent studies fail to establish the relation among multiple aspects in one sentence. To address this issue, a clause-level relational graph attention network with contrastive learning (CLRCL) model is proposed. Specifically, the given sentence is segmented into clauses to obtain the relation between two aspects based on clause-level interaction. Then, to integrate multiple-aspect information, a clause-level relational graph which contains all aspects and inter-aspect relations is developed. Notably, to precisely learn the inter-aspect relations, the supervised contrastive learning strategy is used. Experimental results reveal that the proposed model is a competitive alternative compared with the state-of-the-art methods.

Multimodal Named Entity Recognition (MNER) on social media posts is a leading but challenging task. However, most existing MNER methods fail to effectively exploit the visual information from the image. Besides, the multimodal interaction and alignment remains unsettled. In this paper, we propose a novel token-wise graph-based framework to deal with the MNER task. Specifically, a token-wise image processing manner is established. A muti-modal graph is constructed based on the textual token derived from BERT and the visual token derived from SwinT. Then, the muti-modal graph is fed into a multi-layer Transformer-based module for intra- and inter-modal information fusion. In addition, multiple contrastive learning is devised to perform the global and local alignment between textual and visual nodes. Experimental results on two benchmark multimodal datasets indicate that our model achieves state-of-the-art performance in MNER tasks.

In this article, a high-performance and low-cost single-event multiple-node-upsets resilient (HLMR) latch is proposed in 55-nm CMOS technology. By using eight normal two-input Muller-C-elements (MCEs) and eight clock-gating (CG)-based two-input MCEs, a feedback loop storage module with 16 storage nodes is constructed, which makes the latch completely triple-node-upsets (TNUs) resilient. Meanwhile, through the special layout technique which guarantees the worst quadruple-node pairs as physically apart as possible, the proposed latch is completely quadruple-node-upsets (QNUs) tolerant and almost completely QNU resilient. Simulation results have validated the robustness and low cost of the proposed latch due to the use of high-speed transmission gates (TGs), CG technology, and fewer transistors. Overhead comparisons indicate that our design saves 383.53% area-power-delay product (APDP) on average and has a lower sensitivity on process, voltage and temperature (PVT) compared with other considered up-to-date multiple-node-upsets (MNUs) tolerant latches, thus providing high reliability for safety and low-cost critical applications, especially in harsh radiative environments.