arXiv subjects

Jiang Li

Publications and source records attributed to Jiang Li.

At least 37 records · Page 2Linked to original sources

arXiv2026

From Signal Degradation to Computation Collapse: Uncovering the Two Failure Modes of LLM Quantization

Post-Training Quantization (PTQ) is critical for the efficient deployment of Large Language Models (LLMs). While 4-bit quantization is widely regarded as an optimal trade-off, reducing the precision to 2-bit usually triggers a catastrophic ``performance cliff.'' It remains unclear whether the underlying mechanisms differ fundamentally. Consequently, we conduct a systematic mechanistic analysis, revealing two qualitatively distinct failure modes: Signal Degradation, where the computational patterns remain intact but information precision is impaired by cumulative error; and Computation Collapse, where key components fail to function, preventing correct information processing and destroying the signal in the early layers. Guided by this diagnosis, we conduct mechanism-aware interventions, demonstrating that targeted, training-free repair can mitigate Signal Degradation, but remains ineffective for Computation Collapse. Our findings provide a systematic diagnostic framework for PTQ failures and suggest that addressing Computation Collapse requires structural reconstruction rather than mere compensation.

cs.CL↗

arXiv2026

Exploring the Capability Boundaries of LLMs in Mastering of Chinese Chouxiang Language

While large language models (LLMs) have achieved remarkable success in general language tasks, their performance on Chouxiang Language, a representative subcultural language in the Chinese internet context, remains largely unexplored. In this paper, we introduce Mouse, a specialized benchmark designed to evaluate the capabilities of LLMs on NLP tasks involving Chouxiang Language across six tasks. Experimental results show that, current state-of-the-art (SOTA) LLMs exhibit clear limitations on multiple tasks, while performing well on tasks that involve contextual semantic understanding. In addition, we further discuss the reasons behind the generally low performance of SOTA LLMs on Chouxiang Language, examine whether the LLM-as-a-judge approach adopted for translation tasks aligns with human judgments and values, and analyze the key factors that influence Chouxiang translation. Our study aims to promote further research in the NLP community on multicultural integration and the dynamics of evolving internet languages. Our code and data are publicly available.

cs.CL↗

arXiv2026

Who Wrote This Line? Evaluating the Detection of LLM-Generated Classical Chinese Poetry

The rapid development of large language models (LLMs) has extended text generation tasks into the literary domain. However, AI-generated literary creations has raised increasingly prominent issues of creative authenticity and ethics in literary world, making the detection of LLM-generated literary texts essential and urgent. While previous works have made significant progress in detecting AI-generated text, it has yet to address classical Chinese poetry. Due to the unique linguistic features of classical Chinese poetry, such as strict metrical regularity, a shared system of poetic imagery, and flexible syntax, distinguishing whether a poem is authored by AI presents a substantial challenge. To address these issues, we introduce ChangAn, a benchmark for detecting LLM-generated classical Chinese poetry that containing total 30,664 poems, 10,276 are human-written poems and 20,388 poems are generated by four popular LLMs. Based on ChangAn, we conducted a systematic evaluation of 12 AI detectors, investigating their performance variations across different text granularities and generation strategies. Our findings highlight the limitations of current Chinese text detectors, which fail to serve as reliable tools for detecting LLM-generated classical Chinese poetry. These results validate the effectiveness and necessity of our proposed ChangAn benchmark. Our dataset and code are available at https://github.com/VelikayaScarlet/ChangAn.

cs.CL↗

arXiv2025

Geometric inequalities related to fractional perimeter: fractional Poincaré, isoperimetric, and boxing inequalities in metric measure spaces

In the setting of a complete, doubling metric measure space $(X,d,μ)$ supporting a $(1,1)$-Poincaré inequality, we show that for all $0<θ<1$, the following fractional Poincaré inequality holds for all balls $B$ and locally integrable functions $u$, $$ \int_{B}|u-u_B|dμ\le C(1-θ)\,\text{rad}(B)^θ\int_{τB}\int_{τB}\frac{|u(x)-u(y)|}{d(x,y)^θμ(B(x,d(x,y)))}dμ(y)dμ(x), $$ where $C\ge 1$ and $τ\ge 1$ are constants depending only on the doubling and $(1,1)$-Poincaré inequality constants. Notably, this inequality features the scaling constant $(1-θ)$ present in the Bourgain-Brezis-Mironescu theory characterizing Sobolev functions via nonlocal functionals. From this inequality, we obtain a fractional relative isoperimetric inequality as well as global and local versions of a fractional boxing inequality, each featuring the same scaling constant $(1-θ)$ and defined in terms of the fractional $θ$-perimeter, and prove equivalences with the above fractional Poincaré inequality. We also show that $(X,d,μ)$ supports a $(1,1)$-Poincaré inequality if and only if the above fractional Poincaré inequality holds for all $θ$ sufficiently close to $1$. Under the additional assumption of lower Ahlfors $Q$-regularity of the measure $μ$, we additionally use the aforementioned results to establish global inequalities, in the form of fractional isoperimetric and fractional Sobolev inequalities, which also feature the scaling constant $(1-θ)$. Moreover, we prove that such inequalities are equivalent with the lower Ahlfors $Q$-regularity condition on the measure.

math.FA↗

arXiv2025

The Role of AI in Facilitating Interdisciplinary Collaboration: Evidence from AlphaFold

The acceleration of artificial intelligence (AI) in science is recognized and many scholars have begun to explore its role in interdisciplinary collaboration. However, the mechanisms and extent of this impact are still unclear. This study, using AlphaFold's impact on structural biologists, examines how AI technologies influence interdisciplinary collaborative patterns. By analyzing 1,247 AlphaFold-related papers and 7,700 authors from Scopus, we employ bibliometric analysis and causal inference to compare interdisciplinary collaboration between AlphaFold adopters and non-adopters. Contrary to the widespread belief that AI facilitates interdisciplinary collaboration, our findings show that AlphaFold increased structural biology-computer science collaborations by just 0.48%, with no measurable effect on other disciplines. Specifically, AI creates interdisciplinary collaboration demands with specific disciplines due to its technical characteristics, but this demand is weakened by technological democratization and other factors. These findings demonstrate that artificial intelligence (AI) alone has limited efficacy in bridging disciplinary divides or fostering meaningful interdisciplinary collaboration.

cs.DL↗

arXiv2025

Automated Multi-label Classification of Eleven Retinal Diseases: A Benchmark of Modern Architectures and a Meta-Ensemble on a Large Synthetic Dataset

The development of multi-label deep learning models for retinal disease classification is often hindered by the scarcity of large, expertly annotated clinical datasets due to patient privacy concerns and high costs. The recent release of SynFundus-1M, a high-fidelity synthetic dataset with over one million fundus images, presents a novel opportunity to overcome these barriers. To establish a foundational performance benchmark for this new resource, we developed an end-to-end deep learning pipeline, training six modern architectures (ConvNeXtV2, SwinV2, ViT, ResNet, EfficientNetV2, and the RETFound foundation model) to classify eleven retinal diseases using a 5-fold multi-label stratified cross-validation strategy. We further developed a meta-ensemble model by stacking the out-of-fold predictions with an XGBoost classifier. Our final ensemble model achieved the highest performance on the internal validation set, with a macro-average Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9973. Critically, the models demonstrated strong generalization to three diverse, real-world clinical datasets, achieving an AUC of 0.7972 on a combined DR dataset, an AUC of 0.9126 on the AIROGS glaucoma dataset and a macro-AUC of 0.8800 on the multi-label RFMiD dataset. This work provides a robust baseline for future research on large-scale synthetic datasets and establishes that models trained exclusively on synthetic data can accurately classify multiple pathologies and generalize effectively to real clinical images, offering a viable pathway to accelerate the development of comprehensive AI systems in ophthalmology.

cs.CV↗

arXiv2025

McBE: A Multi-task Chinese Bias Evaluation Benchmark for Large Language Models

As large language models (LLMs) are increasingly applied to various NLP tasks, their inherent biases are gradually disclosed. Therefore, measuring biases in LLMs is crucial to mitigate its ethical risks. However, most existing bias evaluation datasets focus on English and North American culture, and their bias categories are not fully applicable to other cultures. The datasets grounded in the Chinese language and culture are scarce. More importantly, these datasets usually only support single evaluation tasks and cannot evaluate the bias from multiple aspects in LLMs. To address these issues, we present a Multi-task Chinese Bias Evaluation Benchmark (McBE) that includes 4,077 bias evaluation instances, covering 12 single bias categories, 82 subcategories and introducing 5 evaluation tasks, providing extensive category coverage, content diversity, and measuring comprehensiveness. Additionally, we evaluate several popular LLMs from different series and with parameter sizes. In general, all these LLMs demonstrated varying degrees of bias. We conduct an in-depth analysis of results, offering novel insights into bias in LLMs.

cs.CL↗

arXiv2025

Tracing Intricate Cues in Dialogue: Joint Graph Structure and Sentiment Dynamics for Multimodal Emotion Recognition

Multimodal emotion recognition in conversation (MERC) has garnered substantial research attention recently. Existing MERC methods face several challenges: (1) they fail to fully harness direct inter-modal cues, possibly leading to less-than-thorough cross-modal modeling; (2) they concurrently extract information from the same and different modalities at each network layer, potentially triggering conflicts from the fusion of multi-source data; (3) they lack the agility required to detect dynamic sentimental changes, perhaps resulting in inaccurate classification of utterances with abrupt sentiment shifts. To address these issues, a novel approach named GraphSmile is proposed for tracking intricate emotional cues in multimodal dialogues. GraphSmile comprises two key components, i.e., GSF and SDP modules. GSF ingeniously leverages graph structures to alternately assimilate inter-modal and intra-modal emotional dependencies layer by layer, adequately capturing cross-modal cues while effectively circumventing fusion conflicts. SDP is an auxiliary task to explicitly delineate the sentiment dynamics between utterances, promoting the model's ability to distinguish sentimental discrepancies. GraphSmile is effortlessly applied to multimodal sentiment analysis in conversation (MSAC), thus enabling simultaneous execution of MERC and MSAC tasks. Empirical results on multiple benchmarks demonstrate that GraphSmile can handle complex emotional and sentimental patterns, significantly outperforming baseline models.

cs.CL↗

arXiv2025

Degradation-Aware Image Enhancement via Vision-Language Classification

Image degradation is a prevalent issue in various real-world applications, affecting visual quality and downstream processing tasks. In this study, we propose a novel framework that employs a Vision-Language Model (VLM) to automatically classify degraded images into predefined categories. The VLM categorizes an input image into one of four degradation types: (A) super-resolution degradation (including noise, blur, and JPEG compression), (B) reflection artifacts, (C) motion blur, or (D) no visible degradation (high-quality image). Once classified, images assigned to categories A, B, or C undergo targeted restoration using dedicated models tailored for each specific degradation type. The final output is a restored image with improved visual quality. Experimental results demonstrate the effectiveness of our approach in accurately classifying image degradations and enhancing image quality through specialized restoration models. Our method presents a scalable and automated solution for real-world image enhancement tasks, leveraging the capabilities of VLMs in conjunction with state-of-the-art restoration techniques.

cs.CV↗

arXiv2025

Joint Masked Reconstruction and Contrastive Learning for Mining Interactions Between Proteins

Protein-protein interaction (PPI) prediction is an instrumental means in elucidating the mechanisms underlying cellular operations, holding significant practical implications for the realms of pharmaceutical development and clinical treatment. Presently, the majority of research methods primarily concentrate on the analysis of amino acid sequences, while investigations predicated on protein structures remain in the nascent stages of exploration. Despite the emergence of several structure-based algorithms in recent years, these are still confronted with inherent challenges: (1) the extraction of intrinsic structural information of proteins typically necessitates the expenditure of substantial computational resources; (2) these models are overly reliant on seen protein data, struggling to effectively unearth interaction cues between unknown proteins. To further propel advancements in this domain, this paper introduces a novel PPI prediction method jointing masked reconstruction and contrastive learning, termed JmcPPI. This methodology dissects the PPI prediction task into two distinct phases: during the residue structure encoding phase, JmcPPI devises two feature reconstruction tasks and employs graph attention mechanism to capture structural information between residues; during the protein interaction inference phase, JmcPPI perturbs the original PPI graph and employs a multi-graph contrastive learning strategy to thoroughly mine extrinsic interaction information of novel proteins. Extensive experiments conducted on three widely utilized PPI datasets demonstrate that JmcPPI surpasses existing optimal baseline models across various data partition schemes. The associated code can be accessed via https://github.com/lijfrank-open/JmcPPI.

cs.LG↗

arXiv2025

Mitigating Heterogeneity among Factor Tensors via Lie Group Manifolds for Tensor Decomposition Based Temporal Knowledge Graph Embedding

Recent studies have highlighted the effectiveness of tensor decomposition methods in the Temporal Knowledge Graphs Embedding (TKGE) task. However, we found that inherent heterogeneity among factor tensors in tensor decomposition significantly hinders the tensor fusion process and further limits the performance of link prediction. To overcome this limitation, we introduce a novel method that maps factor tensors onto a unified smooth Lie group manifold to make the distribution of factor tensors approximating homogeneous in tensor decomposition. We provide the theoretical proof of our motivation that homogeneous tensors are more effective than heterogeneous tensors in tensor fusion and approximating the target for tensor decomposition based TKGE methods. The proposed method can be directly integrated into existing tensor decomposition based TKGE methods without introducing extra parameters. Extensive experiments demonstrate the effectiveness of our method in mitigating the heterogeneity and in enhancing the tensor decomposition based TKGE models.

cs.LG↗

arXiv2025

Spiral resonator referenced on-chip low noise microwave generation

In recent years, miniaturization and integration of photonic microwave oscillators by optical frequency division approach have witnessed rapid progress. In this work, we report on-chip low phase noise photonic microwave generation based on a planar chip design. Dual lasers are co-locked to a silicon nitride spiral resonator and their relative phase noise is measured below the cavity thermal noise limit, resulting in record low on-chip relative optical phase noise. A broadband integrated electro-optic comb up to 3.43 THz (27 nm) bandwidth is utilized to divide down the relative phase noise of the spiral resonator referenced lasers to the microwave domain. All-around record-low phase noise is achieved for planar chip-based photonic microwave oscillators from 10 Hz to 10 kHz offsets. The planar chip design, high technology-readiness level, foundry-ready processing, combined with the exceptional phase noise performance for our work represent a major advance of integrated photonic microwave oscillators.

physics.optics↗

arXiv2025

Extracting Inter-Protein Interactions Via Multitasking Graph Structure Learning

Identifying protein-protein interactions (PPI) is crucial for gaining in-depth insights into numerous biological processes within cells and holds significant guiding value in areas such as drug development and disease treatment. Currently, most PPI prediction methods focus primarily on the study of protein sequences, neglecting the critical role of the internal structure of proteins. This paper proposes a novel PPI prediction method named MgslaPPI, which utilizes graph attention to mine protein structural information and enhances the expressive power of the protein encoder through multitask learning strategy. Specifically, we decompose the end-to-end PPI prediction process into two stages: amino acid residue reconstruction (A2RR) and protein interaction prediction (PIP). In the A2RR stage, we employ a graph attention-based residue reconstruction method to explore the internal relationships and features of proteins. In the PIP stage, in addition to the basic interaction prediction task, we introduce two auxiliary tasks, i.e., protein feature reconstruction (PFR) and masked interaction prediction (MIP). The PFR task aims to reconstruct the representation of proteins in the PIP stage, while the MIP task uses partially masked protein features for PPI prediction, with both working in concert to prompt MgslaPPI to capture more useful information. Experimental results demonstrate that MgslaPPI significantly outperforms existing state-of-the-art methods under various data partitioning schemes.

q-bio.QM↗

arXiv2024

Unleashing the Power of Large Language Models in Zero-shot Relation Extraction via Self-Prompting

Recent research in zero-shot Relation Extraction (RE) has focused on using Large Language Models (LLMs) due to their impressive zero-shot capabilities. However, current methods often perform suboptimally, mainly due to a lack of detailed, context-specific prompts needed for understanding various sentences and relations. To address this, we introduce the Self-Prompting framework, a novel method designed to fully harness the embedded RE knowledge within LLMs. Specifically, our framework employs a three-stage diversity approach to prompt LLMs, generating multiple synthetic samples that encapsulate specific relations from scratch. These generated samples act as in-context learning samples, offering explicit and context-specific guidance to efficiently prompt LLMs for RE. Experimental evaluations on benchmark datasets show our approach outperforms existing LLM-based zero-shot RE methods. Additionally, our experiments confirm the effectiveness of our generation pipeline in producing high-quality synthetic data that enhances performance.

cs.IR↗

arXiv2024

Coded Distributed (Batch) Matrix Multiplication over Galois Ring via RMFE

Coded Distributed Matrix Multiplication (CDMM) is a distributed matrix multiplication (DMM) for large-scale matrices through a coding scheme such that any $R$ worker node among all $N$ worker nodes can recover the final product, where $N$ corresponds to the length of the code and $R\leq N$ is called the recovery threshold. The state-of-art CDMM schemes, such as EP codes for Single DMM and GCAS codes for batch DMM, are defined over a Galois field $\mathsf{GF}(q)$ of size $q\geq N$. These are inefficient for small Galois fields such as $\mathsf{GF}(2)$ and the integer residue ring $\mathbb{Z}_{p^{e}}$ due to the lack of invertible elements for interpolation. DMM over $\mathbb{Z}_{p^{e}}$ (such as $\mathbb{Z}_{2^{64}}$ ) is well-motivated in practice due to their direct compatibility with hardware. In this work, we construct efficient CDMM over the Galois ring $\mathsf{GR}(p^e,d)$ which is an extension ring over $\mathbb{Z}_{p^{e}}$ of degree $d$, particularly, $\mathsf{GR}(p,d)=\mathsf{GF}(p^d)$ is the Galois field and $\mathsf{GR}(p^e,1)=\mathbb{Z}_{p^e}$. We first give a general CDMM framework for the batch of $n$ matrix multiplications via the famous RMFE (Cascudo et al. Crypto'18). Compared with GCSA, our construction has a smaller recovery threshold by a factor of $1/n$. Next, we optimize EP codes via batch preprocessing of the input matrices. We give two types of Single CDMM, which can achieve almost the same performance as EP codes over a Galois field with size $q\geq N$. Finally, we present the experimental analysis of our CDMM on Galois rings.

cs.DC↗

arXiv2024

Data-Driven Gradient Optimization for Field Emission Management in a Superconducting Radio-Frequency Linac

Field emission can cause significant problems in superconducting radio-frequency linear accelerators (linacs). When cavity gradients are pushed higher, radiation levels within the linacs may rise exponentially, causing degradation of many nearby systems. This research aims to utilize machine learning with uncertainty quantification to predict radiation levels at multiple locations throughout the linacs and ultimately optimize cavity gradients to reduce field emission induced radiation while maintaining the total linac energy gain necessary for the experimental physics program. The optimized solutions show over 40% reductions for both neutron and gamma radiation from the standard operational settings.

physics.acc-ph↗

arXiv2024

Large, Complex, and Realistic Safety Clothing and Helmet Detection: Dataset and Method

Detecting safety clothing and helmets is paramount for ensuring the safety of construction workers. However, the development of deep learning models in this domain has been impeded by the scarcity of high-quality datasets. In this study, we construct a large, complex, and realistic safety clothing and helmet detection (SFCHD) dataset. SFCHD is derived from two authentic chemical plants, comprising 12,373 images, 7 categories, and 50,552 annotations. We partition the SFCHD dataset into training and testing sets with a ratio of 4:1 and validate its utility by applying several classic object detection algorithms. Furthermore, drawing inspiration from spatial and channel attention mechanisms, we design a spatial and channel attention-based low-light enhancement (SCALE) module. SCALE is a plug-and-play component with a high degree of flexibility. Extensive evaluations of the SCALE module on both the ExDark and SFCHD datasets have empirically demonstrated its efficacy in enhancing the performance of detectors under low-light conditions. The dataset and code are publicly available at https://github.com/lijfrank-open/SFCHD-SCALE.

cs.CV↗

arXiv2024

Algebraic Geometry Codes for Distributed Matrix Multiplication Using Local Expansions

Code-based Distributed Matrix Multiplication (DMM) has been extensively studied in distributed computing for efficiently performing large-scale matrix multiplication using coding theoretic techniques. The communication cost and recovery threshold (i.e., the least number of successful worker nodes required to recover the product of two matrices) are two major challenges in coded DMM research. Several constructions based on Reed-Solomon (RS) codes are known, including Polynomial codes, MatDot codes, and PolyDot codes. However, these RS-based schemes are not efficient for small finite fields because the distributed order (i.e., the total number of worker nodes) is limited by the size of the underlying finite field. Algebraic geometry (AG) codes can have a code length exceeding the size of the finite field, which helps solve this problem. Some work has been done to generalize Polynomial and MatDot codes to AG codes, but the generalization of PolyDot codes to AGcodes still remains an open problem as far as we know. This is because functions of an algebraic curve do not behave as nicely as polynomials. In this work, by using local expansions of functions, we are able to generalize the three DMM schemes based on RS codes to AG codes. Specifically, we provide a construction of AG-based PolyDot codes for the first time. In addition, our AG-based Polynomial and MatDot codes achieve better recovery thresholds compared to previous AG-based DMM schemes while maintaining similar communication costs. Our constructions are based on a novel basis of the Riemann-Roch space using local expansions, which naturally generalizes the standard monomial basis of the univariate polynomial space in RS codes. In contrast, previous work used the non-gap numbers to construct a basis of the Riemann-Roch space, which can cause cancellation problems that prevent the conditions of PolyDot codes from being satisfied.

cs.IT↗