arXiv subjects

Min Zeng

Publications and source records attributed to Min Zeng.

At least 37 records · Page 2Linked to original sources

arXiv2025

C$^2$MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis

Graph-based Multiple Instance Learning (MIL) is widely used in survival analysis with Hematoxylin and Eosin (H\&E)-stained whole slide images (WSIs) due to its ability to capture topological information. However, variations in staining and scanning can introduce semantic bias, while topological subgraphs that are not relevant to the causal relationships can create noise, resulting in biased slide-level representations. These issues can hinder both the interpretability and generalization of the analysis. To tackle this, we introduce a dual structural causal model as the theoretical foundation and propose a novel and interpretable dual causal graph-based MIL model, C$^2$MIL. C$^2$MIL incorporates a novel cross-scale adaptive feature disentangling module for semantic causal intervention and a new Bernoulli differentiable causal subgraph sampling method for topological causal discovery. A joint optimization strategy combining disentangling supervision and contrastive learning enables simultaneous refinement of both semantic and topological causalities. Experiments demonstrate that C$^2$MIL consistently improves generalization and interpretability over existing methods and can serve as a causal enhancement for diverse MIL baselines. The code is available at https://github.com/mimic0127/C2MIL.

cs.CV↗

arXiv2025

GTA: Supervised-Guided Reinforcement Learning for Text Classification with Large Language Models

In natural language processing tasks, pure reinforcement learning (RL) fine-tuning methods often suffer from inefficient exploration and slow convergence; while supervised fine-tuning (SFT) methods, although efficient in training, have limited performance ceiling and less solid theoretical foundation compared to RL. To address efficiency-capability trade-off, we propose the Guess-Think-Answer (GTA) framework that combines the efficiency of SFT with the capability gains of RL in a unified training paradigm. GTA works by having the model first produce a provisional guess (optimized via cross-entropy loss), then reflect on this guess before generating the final answer, with RL rewards shaping both the final output and the format of the entire GTA structure. This hybrid approach achieves both faster convergence than pure RL and higher performance ceiling than pure SFT. To mitigate gradient conflicts between the two training signals, we employ loss masking and gradient constraints. Empirical results on four text classification benchmarks demonstrate that GTA substantially accelerates convergence while outperforming both standalone SFT and RL baselines.

cs.CL↗

arXiv2025

Quantized Large Language Models in Biomedical Natural Language Processing: Evaluation and Recommendation

Large language models have demonstrated remarkable capabilities in biomedical natural language processing, yet their rapid growth in size and computational requirements present a major barrier to adoption in healthcare settings where data privacy precludes cloud deployment and resources are limited. In this study, we systematically evaluated the impact of quantization on 12 state-of-the-art large language models, including both general-purpose and biomedical-specific models, across eight benchmark datasets covering four key tasks: named entity recognition, relation extraction, multi-label classification, and question answering. We show that quantization substantially reduces GPU memory requirements-by up to 75%-while preserving model performance across diverse tasks, enabling the deployment of 70B-parameter models on 40GB consumer-grade GPUs. In addition, domain-specific knowledge and responsiveness to advanced prompting methods are largely maintained. These findings provide significant practical and guiding value, highlighting quantization as a practical and effective strategy for enabling the secure, local deployment of large yet high-capacity language models in biomedical contexts, bridging the gap between technical advances in AI and real-world clinical translation.

cs.CL↗

arXiv2025

Contrastive Regularization over LoRA for Multimodal Biomedical Image Incremental Learning

Multimodal Biomedical Image Incremental Learning (MBIIL) is essential for handling diverse tasks and modalities in the biomedical domain, as training separate models for each modality or task significantly increases inference costs. Existing incremental learning methods focus on task expansion within a single modality, whereas MBIIL seeks to train a unified model incrementally across modalities. The MBIIL faces two challenges: I) How to preserve previously learned knowledge during incremental updates? II) How to effectively leverage knowledge acquired from existing modalities to support new modalities? To address these challenges, we propose MSLoRA-CR, a method that fine-tunes Modality-Specific LoRA modules while incorporating Contrastive Regularization to enhance intra-modality knowledge sharing and promote inter-modality knowledge differentiation. Our approach builds upon a large vision-language model (LVLM), keeping the pretrained model frozen while incrementally adapting new LoRA modules for each modality or task. Experiments on the incremental learning of biomedical images demonstrate that MSLoRA-CR outperforms both the state-of-the-art (SOTA) approach of training separate models for each modality and the general incremental learning method (incrementally fine-tuning LoRA). Specifically, MSLoRA-CR achieves a 1.88% improvement in overall performance compared to unconstrained incremental learning methods while maintaining computational efficiency. Our code is publicly available at https://github.com/VentusAislant/MSLoRA_CR.

cs.LG↗

arXiv2024

Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy

In recent years, the use of large language models (LLMs) for text classification has attracted widespread attention. Despite this, the classification accuracy of LLMs has not yet universally surpassed that of smaller models. LLMs can enhance their performance in text classification through fine-tuning. However, existing data quality research based on LLMs is challenging to apply directly to solve text classification problems. To further improve the performance of LLMs in classification tasks, this paper proposes a data quality enhancement (DQE) method for text classification based on LLMs. This method starts by using a greedy algorithm to select data, dividing the dataset into sampled and unsampled subsets, and then performing fine-tuning of the LLMs using the sampled data. Subsequently, this model is used to predict the outcomes for the unsampled data, categorizing incorrectly predicted data into uncovered, difficult, and noisy data. Experimental results demonstrate that our method effectively enhances the performance of LLMs in text classification tasks and significantly improves training efficiency, saving nearly half of the training time. Our method has achieved state-of-the-art performance in several open-source classification tasks.

cs.CL↗

arXiv2024

MolMetaLM: a Physicochemical Knowledge-Guided Molecular Meta Language Model

Most current molecular language models transfer the masked language model or image-text generation model from natural language processing to molecular field. However, molecules are not solely characterized by atom/bond symbols; they encapsulate important physical/chemical properties. Moreover, normal language models bring grammar rules that are irrelevant for understanding molecules. In this study, we propose a novel physicochemical knowledge-guided molecular meta language framework MolMetaLM. We design a molecule-specialized meta language paradigm, formatted as multiple (subject, predicate, object) knowledge triples sharing the same S (i.e., molecule) to enhance learning the semantic relationships between physicochemical knowledge and molecules. By introducing different molecular knowledge and noises, the meta language paradigm generates tens of thousands of pretraining tasks. By recovering the token/sequence/order-level noises, MolMetaLM exhibits proficiency in large-scale benchmark evaluations involving property prediction, molecule generation, conformation inference, and molecular optimization. Through MolMetaLM, we offer a new insight for designing language models.

cs.ET↗

arXiv2024

MoChat: Joints-Grouped Spatio-Temporal Grounding LLM for Multi-Turn Motion Comprehension and Description

Despite continuous advancements in deep learning for understanding human motion, existing models often struggle to accurately identify action timing and specific body parts, typically supporting only single-round interaction. Such limitations in capturing fine-grained motion details reduce their effectiveness in motion understanding tasks. In this paper, we propose MoChat, a multimodal large language model capable of spatio-temporal grounding of human motion and understanding multi-turn dialogue context. To achieve these capabilities, we group the spatial information of each skeleton frame based on human anatomical structure and then apply them with Joints-Grouped Skeleton Encoder, whose outputs are combined with LLM embeddings to create spatio-aware and temporal-aware embeddings separately. Additionally, we develop a pipeline for extracting timestamps from skeleton sequences based on textual annotations, and construct multi-turn dialogues for spatially grounding. Finally, various task instructions are generated for jointly training. Experimental results demonstrate that MoChat achieves state-of-the-art performance across multiple metrics in motion understanding tasks, making it as the first model capable of fine-grained spatio-temporal grounding of human motion.

cs.CV↗

arXiv2024

NAFRSSR: a Lightweight Recursive Network for Efficient Stereo Image Super-Resolution

Stereo image super-resolution (SR) refers to the reconstruction of a high-resolution (HR) image from a pair of low-resolution (LR) images as typically captured by a dual-camera device. To enhance the quality of SR images, most previous studies focused on increasing the number and size of feature maps and introducing complex and computationally intensive structures, resulting in models with high computational complexity. Here, we propose a simple yet efficient stereo image SR model called NAFRSSR, which is modified from the previous state-of-the-art model NAFSSR by introducing recursive connections and lightweighting the constituent modules. Our NAFRSSR model is composed of nonlinear activation free and group convolution-based blocks (NAFGCBlocks) and depth-separated stereo cross attention modules (DSSCAMs). The NAFGCBlock improves feature extraction and reduces number of parameters by removing the simple channel attention mechanism from NAFBlock and using group convolution. The DSSCAM enhances feature fusion and reduces number of parameters by replacing 1x1 pointwise convolution in SCAM with weight-shared 3x3 depthwise convolution. Besides, we propose to incorporate trainable edge detection operator into NAFRSSR to further improve the model performance. Four variants of NAFRSSR with different sizes, namely, NAFRSSR-Mobile (NAFRSSR-M), NAFRSSR-Tiny (NAFRSSR-T), NAFRSSR-Super (NAFRSSR-S) and NAFRSSR-Base (NAFRSSR-B) are designed, and they all exhibit fewer parameters, higher PSNR/SSIM, and faster speed than the previous state-of-the-art models. In particular, to the best of our knowledge, NAFRSSR-M is the lightest (0.28M parameters) and fastest (50 ms inference time) model achieving an average PSNR/SSIM as high as 24.657 dB/0.7622 on the benchmark datasets. Codes and models will be released at https://github.com/JNUChenYiHong/NAFRSSR.

eess.IV↗

arXiv2024

Neural Automated Writing Evaluation with Corrective Feedback

The utilization of technology in second language learning and teaching has become ubiquitous. For the assessment of writing specifically, automated writing evaluation (AWE) and grammatical error correction (GEC) have become immensely popular and effective methods for enhancing writing proficiency and delivering instant and individualized feedback to learners. By leveraging the power of natural language processing (NLP) and machine learning algorithms, AWE and GEC systems have been developed separately to provide language learners with automated corrective feedback and more accurate and unbiased scoring that would otherwise be subject to examiners. In this paper, we propose an integrated system for automated writing evaluation with corrective feedback as a means of bridging the gap between AWE and GEC results for second language learners. This system enables language learners to simulate the essay writing tests: a student writes and submits an essay, and the system returns the assessment of the writing along with suggested grammatical error corrections. Given that automated scoring and grammatical correction are more efficient and cost-effective than human grading, this integrated system would also alleviate the burden of manually correcting innumerable essays.

cs.CL↗

arXiv2024

Evaluating Prompting Strategies for Grammatical Error Correction Based on Language Proficiency

The writing examples of English language learners may be different from those of native speakers. Given that there is a significant differences in second language (L2) learners' error types by their proficiency levels, this paper attempts to reduce overcorrection by examining the interaction between LLM's performance and L2 language proficiency. Our method focuses on zero-shot and few-shot prompting and fine-tuning models for GEC for learners of English as a foreign language based on the different proficiency. We investigate GEC results and find that overcorrection happens primarily in advanced language learners' writing (proficiency C) rather than proficiency A (a beginner level) and proficiency B (an intermediate level). Fine-tuned LLMs, and even few-shot prompting with writing examples of English learners, actually tend to exhibit decreased recall measures. To make our claim concrete, we conduct a comprehensive examination of GEC outcomes and their evaluation results based on language proficiency.

cs.CL↗

arXiv2023

Causal inference with outcome dependent sampling and mismeasured outcome

Outcome-dependent sampling designs are extensively utilized in various scientific disciplines, including epidemiology, ecology, and economics, with retrospective case-control studies being specific examples of such designs. Additionally, if the outcome used for sample selection is also mismeasured, then it is even more challenging to estimate the average treatment effect (ATE) accurately. To our knowledge, no existing method can address these two issues simultaneously. In this paper, we establish the identifiability of ATE and propose a novel method for estimating ATE in the context of generalized linear model. The estimator is shown to be consistent under some regularity conditions. To relax the model assumption, we also consider generalized additive model. We propose to estimate ATE using penalized B-splines and establish asymptotic properties for the proposed estimator. Our methods are evaluated through extensive simulation studies and the application to a dataset from the UK Biobank, with alcohol intake as the treatment and gout as the outcome.

stat.ME↗

arXiv2023

Continual Learning with Dirichlet Generative-based Rehearsal

Recent advancements in data-driven task-oriented dialogue systems (ToDs) struggle with incremental learning due to computational constraints and time-consuming issues. Continual Learning (CL) attempts to solve this by avoiding intensive pre-training, but it faces the problem of catastrophic forgetting (CF). While generative-based rehearsal CL methods have made significant strides, generating pseudo samples that accurately reflect the underlying task-specific distribution is still a challenge. In this paper, we present Dirichlet Continual Learning (DCL), a novel generative-based rehearsal strategy for CL. Unlike the traditionally used Gaussian latent variable in the Conditional Variational Autoencoder (CVAE), DCL leverages the flexibility and versatility of the Dirichlet distribution to model the latent prior variable. This enables it to efficiently capture sentence-level features of previous tasks and effectively guide the generation of pseudo samples. In addition, we introduce Jensen-Shannon Knowledge Distillation (JSKD), a robust logit-based knowledge distillation method that enhances knowledge transfer during pseudo sample generation. Our experiments confirm the efficacy of our approach in both intent detection and slot-filling tasks, outperforming state-of-the-art methods.

cs.CL↗

arXiv2023

Thermoelectric effect and temperature-gradient-driven electrokinetic flow of electrolyte solutions in charged nanocapillaries

A systematic theoretical study of thermoelectric effect and temperature-gradient-driven electrokinetic flow of electrolyte solutions in charged nanocapillaries is presented. The study is based on a semianalytical model developed by simultaneously solving the non-isothermal Poisson-Nernst-Planck-Navier-Stokes equations with the lubrication theory. Particularly, this paper clarifies the interplay and relative importance of the thermoelectric mechanisms due to (a) the convective transport of ions caused by the fluid flow, (b) the dependence of ion electrophoretic mobility on temperature, (c) the difference in the intrinsic Soret coefficients of cation and anion. Additionally, synergy conditions for the three thermoelectric mechanisms to fully cooperate are proposed for thermo-phobic/philic electrolytes. The temperature-gradient-driven electrokinetic flow is shown to be a nearly unidirectional flow whose axial velocity profiles vary with the axial location. Also, the flow can be regarded as a consequence of the counteraction or cooperation between a thermoelectric-field-driven electroosmotic flow and a thermo-osmotic flow driven by the osmotic pressure gradient and dielectric body force. Moreover, the Seebeck coefficient and the fluid average velocity are demonstrated to be affected by electrolyte-related parameters. The results are beneficial for understanding the temperature-gradient-driven electrokinetic transport in nanocapillaries and also serve as theoretical foundation for the design of low-grade waste heat recovery devices and thermoosmotic pumps.

physics.flu-dyn↗

arXiv2023

RHO ($ρ$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding

Dialogue systems can leverage large pre-trained language models and knowledge to generate fluent and informative responses. However, these models are still prone to produce hallucinated responses not supported by the input source, which greatly hinders their application. The heterogeneity between external knowledge and dialogue context challenges representation learning and source integration, and further contributes to unfaithfulness. To handle this challenge and generate more faithful responses, this paper presents RHO ($ρ$) utilizing the representations of linked entities and relation predicates from a knowledge graph (KG). We propose (1) local knowledge grounding to combine textual embeddings with the corresponding KG embeddings; and (2) global knowledge grounding to equip RHO with multi-hop reasoning abilities via the attention mechanism. In addition, we devise a response re-ranking technique based on walks over KG sub-graphs for better conversational reasoning. Experimental results on OpenDialKG show that our approach significantly outperforms state-of-the-art methods on both automatic and human evaluation by a large margin, especially in hallucination reduction (17.54% in FeQA).

cs.CL↗

arXiv2023

A Lite Fireworks Algorithm with Fractal Dimension Constraint for Feature Selection

As the use of robotics becomes more widespread, the huge amount of vision data leads to a dramatic increase in data dimensionality. Although deep learning methods can effectively process these high-dimensional vision data. Due to the limitation of computational resources, some special scenarios still rely on traditional machine learning methods. However, these high-dimensional visual data lead to great challenges for traditional machine learning methods. Therefore, we propose a Lite Fireworks Algorithm with Fractal Dimension constraint for feature selection (LFWA+FD) and use it to solve the feature selection problem driven by robot vision. The "LFWA+FD" focuses on searching the ideal feature subset by simplifying the fireworks algorithm and constraining the dimensionality of selected features by fractal dimensionality, which in turn reduces the approximate features and reduces the noise in the original data to improve the accuracy of the model. The comparative experimental results of two publicly available datasets from UCI show that the proposed method can effectively select a subset of features useful for model inference and remove a large amount of noise noise present in the original data to improve the performance.

cs.LG↗

arXiv2023

A Lite Fireworks Algorithm for Optimization

The fireworks algorithm is an optimization algorithm for simulating the explosion phenomenon of fireworks. Because of its fast convergence and high precision, it is widely used in pattern recognition, optimal scheduling, and other fields. However, most of the existing research work on the fireworks algorithm is improved based on its defects, and little consideration is given to reducing the number of parameters of the fireworks algorithm. The original fireworks algorithm has too many parameters, which increases the cost of algorithm adjustment and is not conducive to engineering applications. In addition, in the fireworks population, the unselected individuals are discarded, thus causing a waste of their location information. To reduce the number of parameters of the original Fireworks Algorithm and make full use of the location information of discarded individuals, we propose a simplified version of the Fireworks Algorithm. It reduces the number of algorithm parameters by redesigning the explosion operator of the fireworks algorithm and constructs an adaptive explosion radius by using the historical optimal information to balance the local mining and global exploration capabilities. The comparative experimental results of function optimization show that the overall performance of our proposed LFWA is better than that of comparative algorithms, such as the fireworks algorithm, particle swarm algorithm, and bat algorithm.

cs.NE↗

arXiv2022

Tripling energy storage density through order-disorder transition induced polar nanoregions in PbZrO3 thin films by ion implantation

Dielectric capacitors are widely used in pulsed power electronic devices due to their ultrahigh power densities and extremely fast charge/discharge speed. To achieve enhanced energy storage density, both maximum polarization (Pmax) and breakdown strength (Eb) need to be improved simultaneously. However, these two key parameters are inversely correlated. In this study, order-disorder transition induced polar nanoregions (PNRs) have been achieved in PbZrO3 thin films by making use of the low-energy ion implantation, enabling us overcome the trade-off between high polarizability and breakdown strength, which leads to the tripling of the energy storage density from 20.5 J/cm3 to 62.3 J/cm3 as well as the great enhancement of breakdown strength. This approach could be extended to other dielectric oxides to improve the energy storage performance, providing a new pathway for tailoring the oxide functionalities.

cond-mat.mtrl-sci↗

arXiv2022

VScript: Controllable Script Generation with Visual Presentation

In order to offer a customized script tool and inspire professional scriptwriters, we present VScript. It is a controllable pipeline that generates complete scripts, including dialogues and scene descriptions, as well as presents visually using video retrieval. With an interactive interface, our system allows users to select genres and input starting words that control the theme and development of the generated script. We adopt a hierarchical structure, which first generates the plot, then the script and its visual presentation. A novel approach is also introduced to plot-guided dialogue generation by treating it as an inverse dialogue summarization. The experiment results show that our approach outperforms the baselines on both automatic and human evaluations, especially in genre control.

cs.CL↗