arXiv subjects

Yuqi Sun

Publications and source records attributed to Yuqi Sun.

At least 19 recordsLinked to original sources

arXiv2026

A Variational Nonlocal Phase-Field Model for Dynamic Fracture in Elastic Solids

We develop a variational nonlocal phase-field model for dynamic fracture in elastic solids. The proposed formulation is distinguished by three main features. First, the model is formulated through nonlocal kinematics and kernel-dependent function spaces, allowing weaker regularity requirements while recovering the classical local theory as the nonlocal interaction domain vanishes. Second, a nonlocal crack-surface functional is introduced as an integral counterpart of the Ambrosio--Tortorelli regularization, so that the characteristic length of the diffusive crack is implicitly determined by the nonlocal interaction domain rather than by a prescribed length scale. Third, the degraded nonlocal elastic energy and the nonlocal crack-surface functional are combined into a variationally consistent dynamic fracture system, consisting of a nonlocal momentum balance and an irreversible nonlocal gradient-flow evolution law for the phase field. The coupled system is solved using two temporal discretization strategies: a structure-preserving scalar auxiliary-variable scheme and a staggered alternating scheme, both combined with finite element discretization in space. Numerical examples involving Mode-I fracture, dynamic crack branching, Kalthoff--Winkler-type shear fracture, and fragmentation show that the proposed model captures complex crack initiation, propagation, branching, and interaction without explicit crack tracking. Quantitatively, the predicted crack-tip velocities remain below $0.6c_R$ in the dynamic branching and shear-loading tests, and the shear-loading benchmark gives an inclined crack path of approximately $48^\circ$, consistent with the characteristic Kalthoff--Winkler fracture pattern.

math.NA↗

arXiv2026

Imaginarity witness

Imaginarity has shown to be an important resource in quantum information. The witness theory of quantum resource, such as entanglement witness, coherence witness, and imaginarity witness, has been established, in particular entanglement witness and coherence witness have been extensively explored. We present here another class of imaginarity witnesses beyond the one in [{Phys. Lett. A} \textbf{530}, 130135 (2025)]. Within our framework, any nonreal Hermitian operator under the reference basis is an imaginarity witness and only finite of them can detect all the imaginarity states. As the common approaches that were explored in the witness theories of entanglement and coherence, we then explore the relations between these imaginarity witnesses in different cases: (i) when they can detect common imaginary states, (ii) when they can detect the same sets of imaginary states, and (ii) when they obey the finer relation. Finally, we define an imaginarity measure in terms of witnesses, termed witnessed imaginarity, and prove that it coincides with both the trace norm of imaginarity and the robustness of imaginarity.

quant-ph↗

arXiv2026

Don't Make the LLM Read the Graph: Make the Graph Think

We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four LLM families in the cooperative card game Hanabi, we establish four findings. First, integration architecture determines whether belief graphs provide value: as prompt context, graphs are decorative for strong models and beneficial only for weak models on 2nd-order Theory of Mind (80% vs 10%, p<0.0001, OR=36.0); when graphs gate action selection through ranked shortlists, they become structurally essential even for strong models (100% vs 20% on 2nd-order ToM, p<0.001). Second, we identify "Planner Defiance," a model-family-specific failure where LLMs override correct planner recommendations at partial competence (90% override, replicated N=20); Gemini models show near-zero defiance while Llama 70B shows 90%, and models distinguish factual context (deferred to) from advisory recommendations (overridden). Third, full-game evidence confirms inter-agent conventions (+128% over baseline, p=0.003) outperform all single-agent interventions, and individual belief-graph components must be combined to produce gains. Fourth, preliminary scaling analysis (N=10/cell, exploratory) suggests graph depth has diminishing returns: shallow graphs provide the best cost-benefit ratio, while deeper ToM graphs appear harmful at larger player counts (-1.5 pts at 5-player, p=0.029).

cs.AI↗

arXiv2026

DMESR: Dual-view MLLM-based Enhancing Framework for Multimodal Sequential Recommendation

Sequential Recommender Systems (SRS) aim to predict users' next interaction based on their historical behaviors, while still facing the challenge of data sparsity. With the rapid advancement of Multimodal Large Language Models (MLLMs), leveraging their multimodal understanding capabilities to enrich item semantic representation has emerged as an effective enhancement strategy for SRS. However, existing MLLM-enhanced recommendation methods still suffer from two key limitations. First, they struggle to effectively align multimodal representations, leading to suboptimal utilization of semantic information across modalities. Second, they often overly rely on MLLM-generated content while overlooking the fine-grained semantic cues contained in the original textual data of items. To address these issues, we propose a Dual-view MLLM-based Enhancing framework for multimodal Sequential Recommendation (DMESR). For the misalignment issue, we employ a contrastive learning mechanism to align the cross-modal semantic representations generated by MLLMs. For the loss of fine-grained semantics, we introduce a cross-attention fusion module that integrates the coarse-grained semantic knowledge obtained from MLLMs with the fine-grained original textual semantics. Finally, these two fused representations can be seamlessly integrated into the downstream sequential recommendation models. Extensive experiments conducted on three real-world datasets and three popular sequential recommendation architectures demonstrate the superior effectiveness and generalizability of our proposed approach.

cs.IR↗

arXiv2026

Data-Centric Interpretability for LLM-based Multi-Agent Reinforcement Learning

Large language models (LLMs) are increasingly trained in complex Reinforcement Learning, multi-agent environments, making it difficult to understand how behavior changes over training. Sparse Autoencoders (SAEs) have recently shown to be useful for data-centric interpretability. In this work, we analyze large-scale reinforcement learning training runs from the sophisticated environment of Full-Press Diplomacy by applying pretrained SAEs, alongside LLM-summarizer methods. We introduce Meta-Autointerp, a method for grouping SAE features into interpretable hypotheses about training dynamics. We discover fine-grained behaviors including role-playing patterns, degenerate outputs, language switching, alongside high-level strategic behaviors and environment-specific bugs. Through automated evaluation, we validate that 90% of discovered SAE Meta-Features are significant, and find a surprising reward hacking behavior. However, through two user studies, we find that even subjectively interesting and seemingly helpful SAE features may be worse than useless to humans, along with most LLM generated hypotheses. However, a subset of SAE-derived hypotheses are predictively useful for downstream tasks. We further provide validation by augmenting an untrained agent's system prompt, improving the score by +14.2%. Overall, we show that SAEs and LLM-summarizer provide complementary views into agent behavior, and together our framework forms a practical starting point for future data-centric interpretability work on ensuring trustworthy LLM behavior throughout training.

cs.LG↗

arXiv2025

Evaluating Control Protocols for Untrusted AI Agents

As AI systems become more capable and widely deployed as agents, ensuring their safe operation becomes critical. AI control offers one approach to mitigating the risk from untrusted AI agents by monitoring their actions and intervening or auditing when necessary. Evaluating the safety of these protocols requires understanding both their effectiveness against current attacks and their robustness to adaptive adversaries. In this work, we systematically evaluate a range of control protocols in SHADE-Arena, a dataset of diverse agentic environments. First, we evaluate blue team protocols, including deferral to trusted models, resampling, and deferring on critical actions, against a default attack policy. We find that resampling for incrimination and deferring on critical actions perform best, increasing safety from 50% to 96%. We then iterate on red team strategies against these protocols and find that attack policies with additional affordances, such as knowledge of when resampling occurs or the ability to simulate monitors, can substantially improve attack success rates against our resampling strategy, decreasing safety to 17%. However, deferring on critical actions is highly robust to even our strongest red team strategies, demonstrating the importance of denying attack policies access to protocol internals.

cs.AI↗

arXiv2025

MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design

Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We present MACO, an open-source, multi-agent LLM framework that automates CGRA HW/SW co-design. MACO decomposes the design loop into four collaborative stages, HW/SW Co-design, Error Correction, Best-Design Selection, and Evaluation & Feedback, to iteratively optimize power, performance, and area (PPA). To accelerate convergence and efficiently traverse the design space, MACO introduces an exponentially decaying exploration strategy, EDA-guided LLM self-learning, and robust rule-based error correction. Evaluated against state-of-the-art baselines, MACO reduces power consumption by 25.9%, improves performance by 20.0%, and accelerates the search process by 5x. Finally, we validate MACO's physical design through a complete 7nm ASIC design flow.

cs.AR↗

arXiv2025

SHADE-Arena: Evaluating Sabotage and Monitoring in LLM Agents

As Large Language Models (LLMs) are increasingly deployed as autonomous agents in complex and long horizon settings, it is critical to evaluate their ability to sabotage users by pursuing hidden objectives. We study the ability of frontier LLMs to evade monitoring and achieve harmful hidden goals while completing a wide array of realistic tasks. We evaluate a broad range of frontier LLMs using SHADE (Subtle Harmful Agent Detection & Evaluation)-Arena, the first highly diverse agent evaluation dataset for sabotage and monitoring capabilities of LLM agents. SHADE-Arena consists of complex pairs of benign main tasks and harmful side objectives in complicated environments. Agents are evaluated on their ability to complete the side task without appearing suspicious to an LLM monitor. When measuring agent ability to (a) complete the main task, (b) complete the side task, and (c) avoid detection, we find that the best performing frontier models score 27% (Claude 3.7 Sonnet) and 15% (Gemini 2.5 Pro) as sabotage agents when overseen by Claude 3.6 Sonnet. For current frontier models, success on the side task relies heavily on having access to a hidden scratchpad that is not visible to the monitor. We also use SHADE-Arena to measure models' monitoring abilities, with the top monitor (Gemini 2.5 Pro) achieving an AUC of 0.87 at distinguishing benign and malign transcripts. We find that for now, models still struggle at sabotage due to failures in long-context main task execution. However, our measurements already demonstrate the difficulty of monitoring for subtle sabotage attempts, which we expect to only increase in the face of more complex and longer-horizon tasks.

cs.AI↗

arXiv2025

MM-Skin: Enhancing Dermatology Vision-Language Model with an Image-Text Dataset Derived from Textbooks

Medical vision-language models (VLMs) have shown promise as clinical assistants across various medical fields. However, specialized dermatology VLM capable of delivering professional and detailed diagnostic analysis remains underdeveloped, primarily due to less specialized text descriptions in current dermatology multimodal datasets. To address this issue, we propose MM-Skin, the first large-scale multimodal dermatology dataset that encompasses 3 imaging modalities, including clinical, dermoscopic, and pathological and nearly 10k high-quality image-text pairs collected from professional textbooks. In addition, we generate over 27k diverse, instruction-following vision question answering (VQA) samples (9 times the size of current largest dermatology VQA dataset). Leveraging public datasets and MM-Skin, we developed SkinVL, a dermatology-specific VLM designed for precise and nuanced skin disease interpretation. Comprehensive benchmark evaluations of SkinVL on VQA, supervised fine-tuning (SFT) and zero-shot classification tasks across 8 datasets, reveal its exceptional performance for skin diseases in comparison to both general and medical VLM models. The introduction of MM-Skin and SkinVL offers a meaningful contribution to advancing the development of clinical dermatology VLM assistants. MM-Skin is available at https://github.com/ZwQ803/MM-Skin

cs.CV↗

arXiv2025

LLMSeR: Enhancing Sequential Recommendation via LLM-based Data Augmentation

Sequential Recommender Systems (SRS) have become a cornerstone of online platforms, leveraging users' historical interaction data to forecast their next potential engagement. Despite their widespread adoption, SRS often grapple with the long-tail user dilemma, resulting in less effective recommendations for individuals with limited interaction records. The advent of Large Language Models (LLMs), with their profound capability to discern semantic relationships among items, has opened new avenues for enhancing SRS through data augmentation. Nonetheless, current methodologies encounter obstacles, including the absence of collaborative signals and the prevalence of hallucination phenomena. In this work, we present LLMSeR, an innovative framework that utilizes Large Language Models (LLMs) to generate pseudo-prior items, thereby improving the efficacy of Sequential Recommender Systems (SRS). To alleviate the challenge of insufficient collaborative signals, we introduce the Semantic Interaction Augmentor (SIA), a method that integrates both semantic and collaborative information to comprehensively augment user interaction data. Moreover, to weaken the adverse effects of hallucination in SRS, we develop the Adaptive Reliability Validation (ARV), a validation technique designed to assess the reliability of the generated pseudo items. Complementing these advancements, we also devise a Dual-Channel Training strategy, ensuring seamless integration of data augmentation into the SRS training process.Extensive experiments conducted with three widely-used SRS models demonstrate the generalizability and efficacy of LLMSeR.

cs.IR↗

arXiv2024

Graph Structure Refinement with Energy-based Contrastive Learning

Graph Neural Networks (GNNs) have recently gained widespread attention as a successful tool for analyzing graph-structured data. However, imperfect graph structure with noisy links lacks enough robustness and may damage graph representations, therefore limiting the GNNs' performance in practical tasks. Moreover, existing generative architectures fail to fit discriminative graph-related tasks. To tackle these issues, we introduce an unsupervised method based on a joint of generative training and discriminative training to learn graph structure and representation, aiming to improve the discriminative performance of generative models. We propose an Energy-based Contrastive Learning (ECL) guided Graph Structure Refinement (GSR) framework, denoted as ECL-GSR. To our knowledge, this is the first work to combine energy-based models with contrastive learning for GSR. Specifically, we leverage ECL to approximate the joint distribution of sample pairs, which increases the similarity between representations of positive pairs while reducing the similarity between negative ones. Refined structure is produced by augmenting and removing edges according to the similarity metrics among node representations. Extensive experiments demonstrate that ECL-GSR outperforms the state-of-the-art on eight benchmark datasets in node classification. ECL-GSR achieves faster training with fewer samples and memories against the leading baseline, highlighting its simplicity and efficiency in downstream tasks.

cs.LG↗

arXiv2024

Large Language Model Enhanced Recommender Systems: A Survey

Large Language Model (LLM) has transformative potential in various domains, including recommender systems (RS). There have been a handful of research that focuses on empowering the RS by LLM. However, previous efforts mainly focus on LLM as RS, which may face the challenge of intolerant inference costs by LLM. Recently, the integration of LLM into RS, known as LLM-Enhanced Recommender Systems (LLMERS), has garnered significant interest due to its potential to address latency and memory constraints in real-world applications. This paper presents a comprehensive survey of the latest research efforts aimed at leveraging LLM to enhance RS capabilities. We identify a critical shift in the field with the move towards incorporating LLM into the online system, notably by avoiding their use during inference. Our survey categorizes the existing LLMERS approaches into three primary types based on the component of the RS model being augmented: Knowledge Enhancement, Interaction Enhancement, and Model Enhancement. We provide an in-depth analysis of each category, discussing the methodologies, challenges, and contributions of recent studies. Furthermore, we highlight several promising research directions that could further advance the field of LLMERS.

cs.IR↗

arXiv2024

A Self-Supervised Paradigm for Data-Efficient Medical Foundation Model Pre-training: V-information Optimization Framework

Self-supervised pre-training medical foundation models on large-scale datasets demonstrate exceptional performance. Recent research challenges this common paradigm by introducing data-effective learning approaches, demonstrating that merely increasing pre-training data volume does not necessarily improve model performance. However, current methods still have unclear standards and the underlying theoretical foundation remains unknown. In this paper, as the first attempt to address this limitation, we introduce V-information into self-supervised pre-training of foundation models to provide a theoretical foundation for sample selection. Our derivation confirms that by optimizing V-information, sample selection can be framed as an optimization problem where choosing diverse and challenging samples enhances model performance even under limited training data. Under this guidance, we develop an optimized data-effective learning method (OptiDEL) to optimize V-information in real-world medical domains by generating more diverse and harder samples. We compare the OptiDEL method with state-of-the-art approaches finding that OptiDEL consistently outperforms existing approaches across eight different datasets, with foundation models trained on only 5% of the pre-training data achieving up to 6.2% higher mIoU than those trained on the full dataset. Remarkably, OptiDEL demonstrates an average improvement of 4.7% mIoU over competing methods while using 20x less training data.

cs.LG↗

arXiv2024

A Medical Data-Effective Learning Benchmark for Highly Efficient Pre-training of Foundation Models

Foundation models, pre-trained on massive datasets, have achieved unprecedented generalizability. However, is it truly necessary to involve such vast amounts of data in pre-training, consuming extensive computational resources? This paper introduces data-effective learning, aiming to use data in the most impactful way to pre-train foundation models. This involves strategies that focus on data quality rather than quantity, ensuring the data used for training has high informational value. Data-effective learning plays a profound role in accelerating foundation model training, reducing computational costs, and saving data storage, which is very important as the volume of medical data in recent years has grown beyond many people's expectations. However, due to the lack of standards and comprehensive benchmarks, research on medical data-effective learning is poorly studied. To address this gap, our paper introduces a comprehensive benchmark specifically for evaluating data-effective learning in the medical field. This benchmark includes a dataset with millions of data samples from 31 medical centers (DataDEL), a baseline method for comparison (MedDEL), and a new evaluation metric (NormDEL) to objectively measure data-effective learning performance. Our extensive experimental results show the baseline MedDEL can achieve performance comparable to the original large dataset with only 5% of the data. Establishing such an open data-effective learning benchmark is crucial for the medical foundation model research community because it facilitates efficient data use, promotes collaborative breakthroughs, and fosters the development of cost-effective, scalable, and impactful healthcare solutions.

cs.LG↗

arXiv2023

Low-latency Space-time Supersampling for Real-time Rendering

With the rise of real-time rendering and the evolution of display devices, there is a growing demand for post-processing methods that offer high-resolution content in a high frame rate. Existing techniques often suffer from quality and latency issues due to the disjointed treatment of frame supersampling and extrapolation. In this paper, we recognize the shared context and mechanisms between frame supersampling and extrapolation, and present a novel framework, Space-time Supersampling (STSS). By integrating them into a unified framework, STSS can improve the overall quality with lower latency. To implement an efficient architecture, we treat the aliasing and warping holes unified as reshading regions and put forth two key components to compensate the regions, namely Random Reshading Masking (RRM) and Efficient Reshading Module (ERM). Extensive experiments demonstrate that our approach achieves superior visual fidelity compared to state-of-the-art (SOTA) methods. Notably, the performance is achieved within only 4ms, saving up to 75\% of time against the conventional two-stage pipeline that necessitates 17ms.

cs.CV↗

arXiv2023

Instruct-NeuralTalker: Editing Audio-Driven Talking Radiance Fields with Instructions

Recent neural talking radiance field methods have shown great success in photorealistic audio-driven talking face synthesis. In this paper, we propose a novel interactive framework that utilizes human instructions to edit such implicit neural representations to achieve real-time personalized talking face generation. Given a short speech video, we first build an efficient talking radiance field, and then apply the latest conditional diffusion model for image editing based on the given instructions and guiding implicit representation optimization towards the editing target. To ensure audio-lip synchronization during the editing process, we propose an iterative dataset updating strategy and utilize a lip-edge loss to constrain changes in the lip region. We also introduce a lightweight refinement network for complementing image details and achieving controllable detail generation in the final rendered image. Our method also enables real-time rendering at up to 30FPS on consumer hardware. Multiple metrics and user verification show that our approach provides a significant improvement in rendering quality compared to state-of-the-art methods.

cs.CV↗

arXiv2023

Direct Linearly-Polarised Electroluminescence from Perovskite Nanoplatelet Superlattices

Polarised light is critical for a wide range of applications, but is usually generated by filtering unpolarised light, which leads to significant energy losses and requires additional optics. Herein, the direct emission of linearly-polarised light is achieved from light-emitting diodes (LEDs) made of CsPbI3 perovskite nanoplatelet superlattices. Through use of solvents with different vapour pressures, the self-assembly of perovskite nanoplatelets is achieved to enable fine control over the orientation (either face-up or edge-up) and therefore the transition dipole moment. As a result of the highly-uniform alignment of the nanoplatelets, as well as their strong quantum and dielectric confinement, large exciton fine-structure splitting is achieved at the film level, leading to pure-red LEDs exhibiting a high degree of linear polarisation of 74.4% without any photonic structures. This work unveils the possibilities of perovskite nanoplatelets as a highly promising source of linearly-polarised electroluminescence, opening up the development of next-generation 3D displays and optical communications from this highly versatile, solution-processable system.

physics.optics↗

arXiv2022

Sliding induced multiple polarization states in two-dimensional ferroelectrics

When the atomic layers in a non-centrosymmetric van der Waals structure slide against each other, the interfacial charge transfer results in a reversal of the structures spontaneous polarization. This phenomenon is known as sliding ferroelectricity and it is markedly different from conventional ferroelectric switching mechanisms relying on ion displacement. Here, we present layer dependence as a new dimension to control sliding ferroelectricity. By fabricating 3R MoS2 of various thicknesses into dual-gate field-effect transistors, we obtain anomalous intermediate polarization states in multilayer 3R MoS2. Using results from ab initio density functional theory calculations, we propose a generalized model to describe the ferroelectric switching process in multilayer 3R MoS2 and to explain the formation of these intermediate polarization states. This work reveals the critical roles that layer number and interlayer dipole coupling play in sliding ferroelectricity and presents a new strategy for the design of novel sliding ferroelectric devices.

cond-mat.mtrl-sci↗