Dongping Liu

Dongping Liu, Aoyu Zhang, Luyao Zhang

The 2024--2025 Nobel and Turing awards recognised artificial intelligence and quantum science in the same breath -- machine learning as a physical science, artificial intelligence solving 50-year scientific problems, superconducting quantum circuits as the hardware foundation of quantum computing, and quantum information principles as computing's highest achievement. Yet no deployed artificial intelligence system has brought these two streams together for the general public: identity systems still rely on pseudo-random tokens, and quantum circuits remain invisible to the billions of people who use bot-enabled social messaging platforms daily. This paper presents QSignAI, a production-deployed open-source platform demonstrating a bidirectional relationship between artificial intelligence and quantum science in a real-time event participation system. We address three research questions: first, can quantum-randomness generation via real quantum circuits be embedded in an artificial-intelligence-driven social platform with acceptable latency and cost; second, can an artificial intelligence bot make quantum phenomena perceptually legible to general audiences with no prior technical knowledge; and third, does a system combining both directions work in practice. A conversational artificial intelligence bot routes each participant's first message through a two-circuit quantum pipeline on a cloud quantum simulator, producing a unique quantum-randomness-seeded identity signature per participant. The first two questions are answered through system design and qualitative deployment evidence; measurable comparisons are identified as priority future work.

Dongping Liu, Aoyu Zhang, Luyao Zhang

Advances in quantum computing introduce long-term security challenges for widely deployed public-key cryptographic systems used across blockchain platforms and decentralized applications. Although post-quantum cryptography (PQC) standards are emerging, understanding quantum risk remains fragmented across research, engineering, governance, and investment communities. This demo presents Quantum Futures Interactive, a live interdisciplinary demonstration platform combining educational visualization, participatory interaction, and cryptographic artifact generation to illustrate the transition from classical to quantum-resilient blockchain systems. Participants engage in a structured interaction flow including quantum threat education, sentiment capture, technology prioritization, infrastructure tradeoff exploration, and generation of post-quantum cryptographic outputs. The system integrates distributed trust concepts, sustainability-aware infrastructure considerations, and responsible innovation within an interactive decision framework. The demonstration supports interdisciplinary dialogue on blockchain resilience while aligning with United Nations Sustainable Development Goals (SDGs).

Daning Cheng, Zeyu Liu, Jun Sun et al.

The scaling behavior, in which test performance often improves as model size and data increase, is a central empirical phenomenon in modern deep learning, yet its theoretical basis remains incomplete. In this paper, we study depth expansion in normalized residual networks: starting from a trained model in an old hypothesis class, we insert a new residual block at an intermediate layer and ask when such an expansion can yield a provable improvement in test risk. We develop a unified framework that decomposes this question into representational gain, optimization gain, and generalization transfer. First, under a first-order descent condition near zero initialization, we prove that the expanded hypothesis class contains an auxiliary jumpboard model with strictly smaller population risk than the original model. Second, under norm control tailored to post-normalized residual architectures, we establish a norm-based Rademacher complexity bound for the expanded model class. These ingredients lead to two complementary test-risk guarantees: one route passes through population risk and is tighter when a positive population margin is available, while the other works directly at the train/test level, avoids Hoeffding transfer, and is more robust in degenerate regimes. Together, these results provide a theorem-driven mechanism under which residual depth expansion can improve test performance in normalized residual networks. More broadly, they suggest that scaling is inherently joint: depth creates new improving directions, width enhances the finite-sample observability of weak signals, and data determines whether the statistical cost of expansion can be controlled.

Rihui Jin, Yuchen Lu, Ting Zhang et al.

Table Retrieval (TR) has traditionally been formulated as an ad-hoc retrieval problem, where relevance is primarily determined by topical semantic similarity. With the growing adoption of LLM-based agentic systems, access to structured data is increasingly instruction-driven, where relevance is conditional on explicit content and schema constraints rather than topical similarity alone. We therefore formalize Instruction-Following Table Retrieval (IFTR), a new task that requires models to jointly satisfy topical relevance and fine-grained instruction constraints. We identify two core challenges in IFTR: (i) sensitivity to content scope, such as inclusion and exclusion constraints, and (ii) awareness of schema-grounded requirements, including column semantics and representation granularity--capabilities largely absent in existing retrievers. To support systematic evaluation, we introduce FollowTable, the first large-scale benchmark for IFTR, constructed via a taxonomy-driven annotation pipeline. We further propose a new metric, termed the Instruction Responsiveness Score, to evaluate whether retrieval rankings consistently adapt to user instructions relative to a topic-only baseline. Our results indicate that existing retrieval models struggle to follow fine-grained instructions over tabular data. In particular, they exhibit systematic biases toward surface-level semantic cues and remain limited in handling schema-grounded constraints, highlighting substantial room for future improvements.

Leo Chen, Benjamin Boardley, Ping Hu et al.

This article describes the 2023 IEEE Low-Power Computer Vision Challenge (LPCVC). Since 2015, LPCVC has been an international competition devoted to tackling the challenge of computer vision (CV) on edge devices. Most CV researchers focus on improving accuracy, at the expense of ever-growing sizes of machine models. LPCVC balances accuracy with resource requirements. Winners must achieve high accuracy with short execution time when their CV solutions run on an embedded device, such as Raspberry PI or Nvidia Jetson Nano. The vision problem for 2023 LPCVC is segmentation of images acquired by Unmanned Aerial Vehicles (UAVs, also called drones) after disasters. The 2023 LPCVC attracted 60 international teams that submitted 676 solutions during the submission window of one month. This article explains the setup of the competition and highlights the winners' methods that improve accuracy and shorten execution time.