arXiv subjects

Jingyuan Chen

Publications and source records attributed to Jingyuan Chen.

At least 73 records · Page 4Linked to original sources

arXiv2025

Large Language Models for Bioinformatics

With the rapid advancements in large language model (LLM) technology and the emergence of bioinformatics-specific language models (BioLMs), there is a growing need for a comprehensive analysis of the current landscape, computational characteristics, and diverse applications. This survey aims to address this need by providing a thorough review of BioLMs, focusing on their evolution, classification, and distinguishing features, alongside a detailed examination of training methodologies, datasets, and evaluation frameworks. We explore the wide-ranging applications of BioLMs in critical areas such as disease diagnosis, drug discovery, and vaccine development, highlighting their impact and transformative potential in bioinformatics. We identify key challenges and limitations inherent in BioLMs, including data privacy and security concerns, interpretability issues, biases in training data and model outputs, and domain adaptation complexities. Finally, we highlight emerging trends and future directions, offering valuable insights to guide researchers and clinicians toward advancing BioLMs for increasingly sophisticated biological and clinical applications.

q-bio.QM↗

arXiv2024

Fine-Grained Guidance for Retrievers: Leveraging LLMs' Feedback in Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) has proven to be an effective method for mitigating hallucination issues inherent in large language models (LLMs). Previous approaches typically train retrievers based on semantic similarity, lacking optimization for RAG. More recent works have proposed aligning retrievers with the preference signals of LLMs. However, these preference signals are often difficult for dense retrievers, which typically have weaker language capabilities, to understand and learn effectively. Drawing inspiration from pedagogical theories like Guided Discovery Learning, we propose a novel framework, FiGRet (Fine-grained Guidance for Retrievers), which leverages the language capabilities of LLMs to construct examples from a more granular, information-centric perspective to guide the learning of retrievers. Specifically, our method utilizes LLMs to construct easy-to-understand examples from samples where the retriever performs poorly, focusing on three learning objectives highly relevant to the RAG scenario: relevance, comprehensiveness, and purity. These examples serve as scaffolding to ultimately align the retriever with the LLM's preferences. Furthermore, we employ a dual curriculum learning strategy and leverage the reciprocal feedback between LLM and retriever to further enhance the performance of the RAG system. A series of experiments demonstrate that our proposed framework enhances the performance of RAG systems equipped with different retrievers and is applicable to various LLMs.

cs.IR↗

arXiv2024

Classifier-guided Gradient Modulation for Enhanced Multimodal Learning

Multimodal learning has developed very fast in recent years. However, during the multimodal training process, the model tends to rely on only one modality based on which it could learn faster, thus leading to inadequate use of other modalities. Existing methods to balance the training process always have some limitations on the loss functions, optimizers and the number of modalities and only consider modulating the magnitude of the gradients while ignoring the directions of the gradients. To solve these problems, in this paper, we present a novel method to balance multimodal learning with Classifier-Guided Gradient Modulation (CGGM), considering both the magnitude and directions of the gradients. We conduct extensive experiments on four multimodal datasets: UPMC-Food 101, CMU-MOSI, IEMOCAP and BraTS 2021, covering classification, regression and segmentation tasks. The results show that CGGM outperforms all the baselines and other state-of-the-art methods consistently, demonstrating its effectiveness and versatility. Our code is available at https://github.com/zrguo/CGGM.

cs.LG↗

arXiv2024

Enabling Clinical Use of Linear Energy Transfer in Proton Therapy for Head and Neck Cancer -- A Review of Implications for Treatment Planning and Adverse Events Study

Proton therapy offers significant advantages due to its unique physical and biological properties, particularly the Bragg peak, enabling precise dose delivery to tumors while sparing healthy tissues. However, the clinical implementation is challenged by the oversimplification of the relative biological effectiveness (RBE) as a fixed value of 1.1, which does not account for the complex interplay between dose, linear energy transfer (LET), and biological endpoints. Lack of heterogeneity control or the understanding of the complex interplay may result in unexpected adverse events and suboptimal patient outcomes. On the other hand, expanding our knowledge of variable tumor RBE and LET optimization may provide a better management strategy for radioresistant tumors. This review examines recent advancements in LET calculation methods, including analytical models and Monte Carlo simulations. The integration of LET into plan evaluation is assessed to enhance plan quality control. LET-guided robust optimization demonstrates promise in minimizing high-LET exposure to organs at risk, thereby reducing the risk of adverse events. Dosimetric seed spot analysis is discussed to show its importance in revealing the true LET-related effect upon the adverse event initialization by finding the lesion origins and eliminating the confounding factors from the biological processes. Dose-LET volume histograms (DLVH) are discussed as effective tools for correlating physical dose and LET with clinical outcomes, enabling the derivation of clinically relevant dose-LET volume constraints without reliance on uncertain RBE models. Based on DLVH, the dose-LET volume constraints (DLVC)-guided robust optimization is introduced to upgrade conventional dose-volume constraints-based robust optimization, which optimizes the joint distribution of dose and LET simultaneously.

physics.med-ph↗

arXiv2024

MPCODER: Multi-user Personalized Code Generator with Explicit and Implicit Style Representation Learning

Large Language Models (LLMs) have demonstrated great potential for assisting developers in their daily development. However, most research focuses on generating correct code, how to use LLMs to generate personalized code has seldom been investigated. To bridge this gap, we proposed MPCoder (Multi-user Personalized Code Generator) to generate personalized code for multiple users. To better learn coding style features, we utilize explicit coding style residual learning to capture the syntax code style standards and implicit style learning to capture the semantic code style conventions. We train a multi-user style adapter to better differentiate the implicit feature representations of different users through contrastive learning, ultimately enabling personalized code generation for multiple users. We further propose a novel evaluation metric for estimating similarities between codes of different coding styles. The experimental results show the effectiveness of our approach for this novel task.

cs.CL↗

arXiv2024

AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding

With the rapid advancement of large language models, there has been a growing interest in their capabilities in mathematical reasoning. However, existing research has primarily focused on text-based algebra problems, neglecting the study of geometry due to the lack of high-quality geometric datasets. To address this gap, this paper introduces AutoGeo, a novel approach for automatically generating mathematical geometric images to fulfill the demand for large-scale and diverse geometric datasets. AutoGeo facilitates the creation of AutoGeo-100k, an extensive repository comprising 100k high-quality geometry image-text pairs. By leveraging precisely defined geometric clauses, AutoGeo-100k contains a wide variety of geometric shapes, including lines, polygons, circles, and complex spatial relationships, etc. Furthermore, this paper demonstrates the efficacy of AutoGeo-100k in enhancing the performance of multimodal large language models through fine-tuning. Experimental results indicate significant improvements in the model's ability in handling geometric images, as evidenced by enhanced accuracy in tasks such as geometric captioning and mathematical reasoning. This research not only fills a critical gap in the availability of geometric datasets but also paves the way for the advancement of sophisticated AI-driven tools in education and research. Project page: https://autogeo-official.github.io/.

cs.LG↗

arXiv2024

Semantic Alignment for Multimodal Large Language Models

Research on Multi-modal Large Language Models (MLLMs) towards the multi-image cross-modal instruction has received increasing attention and made significant progress, particularly in scenarios involving closely resembling images (e.g., change captioning). Existing MLLMs typically follow a two-step process in their pipelines: first, extracting visual tokens independently for each input image, and then aligning these visual tokens from different images with the Large Language Model (LLM) in its textual feature space. However, the independent extraction of visual tokens for each image may result in different semantics being prioritized for different images in the first step, leading to a lack of preservation of linking information among images for subsequent LLM analysis. This issue becomes more serious in scenarios where significant variations exist among the images (e.g., visual storytelling). To address this challenge, we introduce Semantic Alignment for Multi-modal large language models (SAM). By involving the bidirectional semantic guidance between different images in the visual-token extraction process, SAM aims to enhance the preservation of linking information for coherent analysis and align the semantics of different images before feeding them into LLM. As the test bed, we propose a large-scale dataset named MmLINK consisting of 69K samples. Different from most existing datasets for MLLMs fine-tuning, our MmLINK dataset comprises multi-modal instructions with significantly diverse images. Extensive experiments on the group captioning task and the storytelling task prove the effectiveness of our SAM model, surpassing the state-of-the-art methods by a large margin (+37% for group captioning and +22% for storytelling on CIDEr score). Project page: https://mccartney01.github.io/SAM.

cs.CV↗

arXiv2024

Semantic Codebook Learning for Dynamic Recommendation Models

Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve the personalization of sequential recommendation under various user preferences. However, it faces the challenges of large parameter search space and sparse and noisy user-item interactions, which reduces the applicability of the generated model parameters. The Semantic Codebook Learning for Dynamic Recommendation Models (SOLID) framework presents a significant advancement in DSR by effectively tackling these challenges. By transforming item sequences into semantic sequences and employing a dual parameter model, SOLID compresses the parameter generation search space and leverages homogeneity within the recommendation system. The introduction of the semantic metacode and semantic codebook, which stores disentangled item representations, ensures robust and accurate parameter generation. Extensive experiments demonstrates that SOLID consistently outperforms existing DSR, delivering more accurate, stable, and robust recommendations.

cs.IR↗

arXiv2024

Photohermal Microswimmer Penetrate Cell Membrane with Cavitation Bubble

Self-propelled micromotors can efficiently convert ambient energy into mechanical motion, which is of great interest for its potential biomedical applications in delivering therapeutics noninvasively. However, navigating these micromotors through biological barriers remains a significant challenge as most micromotors do not provide sufficient disruption forces in in-vivo conditions. In this study, we employed focused scanning laser from conventional confocal microscope to manipulate carbon microbottle based microswimmers. With the increasing of the laser power, the microswimmers' motions translates from autonomous to directional, and finally the high power laser induced the microswimmer explosions, which effectively deliveres microbottle fragments through the cell membrane. It is revealed that photothermally-induced cavitation bubbles enable the propulsion of microbottles in liquids, where the motion direction can be precisely regulated by the scanning orientation of the laser. Furthermore, the membrane penetration ability of the microbottles promised potential applications in drug delivery and cellular injections. As microbottles navigate toward cells, we strategically increase the laser power to trigger their explosion. By loading microswimmers with transfection genes, cytoplasmic transfection can be realized, which is demonstrated by successful gene transfection of GPF in cells. Our findings open new possibilities for cell injection and gene transfection using micromotors.

cond-mat.soft↗

arXiv2024

DIET: Customized Slimming for Incompatible Networks in Sequential Recommendation

Due to the continuously improving capabilities of mobile edges, recommender systems start to deploy models on edges to alleviate network congestion caused by frequent mobile requests. Several studies have leveraged the proximity of edge-side to real-time data, fine-tuning them to create edge-specific models. Despite their significant progress, these methods require substantial on-edge computational resources and frequent network transfers to keep the model up to date. The former may disrupt other processes on the edge to acquire computational resources, while the latter consumes network bandwidth, leading to a decrease in user satisfaction. In response to these challenges, we propose a customizeD slImming framework for incompatiblE neTworks(DIET). DIET deploys the same generic backbone (potentially incompatible for a specific edge) to all devices. To minimize frequent bandwidth usage and storage consumption in personalization, DIET tailors specific subnets for each edge based on its past interactions, learning to generate slimming subnets(diets) within incompatible networks for efficient transfer. It also takes the inter-layer relationships into account, empirically reducing inference time while obtaining more suitable diets. We further explore the repeated modules within networks and propose a more storage-efficient framework, DIETING, which utilizes a single layer of parameters to represent the entire network, achieving comparably excellent performance. The experiments across four state-of-the-art datasets and two widely used models demonstrate the superior accuracy in recommendation and efficiency in transmission and storage of our framework.

cs.DC↗

arXiv2024

Non-confusing Generation of Customized Concepts in Diffusion Models

We tackle the common challenge of inter-concept visual confusion in compositional concept generation using text-guided diffusion models (TGDMs). It becomes even more pronounced in the generation of customized concepts, due to the scarcity of user-provided concept visual examples. By revisiting the two major stages leading to the success of TGDMs -- 1) contrastive image-language pre-training (CLIP) for text encoder that encodes visual semantics, and 2) training TGDM that decodes the textual embeddings into pixels -- we point that existing customized generation methods only focus on fine-tuning the second stage while overlooking the first one. To this end, we propose a simple yet effective solution called CLIF: contrastive image-language fine-tuning. Specifically, given a few samples of customized concepts, we obtain non-confusing textual embeddings of a concept by fine-tuning CLIP via contrasting a concept and the over-segmented visual regions of other concepts. Experimental results demonstrate the effectiveness of CLIF in preventing the confusion of multi-customized concept generation.

cs.CV↗

arXiv2024

Robust Optimization for Spot Scanning Proton Therapy based on Dose-Linear Energy Transfer (LET) Volume Constraints

Purpose: Historically, spot scanning proton therapy (SSPT) treatment planning utilizes dose volume constraints and linear-energy-transfer (LET) volume constraints separately to balance tumor control and organs-at-risk (OARs) protection. We propose a novel dose-LET volume constraint (DLVC)-based robust optimization (DLVCRO) method for SSPT in treating prostate cancer to obtain a desirable joint dose and LET distribution to minimize adverse events (AEs). Methods: DLVCRO treats DLVC as soft constraints controlling the joint distribution of dose and LET. Ten prostate cancer patients were included with rectum and bladder as OARs. DLVCRO was compared with the conventional robust optimization (RO) method using the worst-case analysis method. Besides the dose-volume histogram (DVH) indices, the analogous LETVH and extra-biological-dose (xBD)-volume histogram indices were also used. The Wilcoxon signed rank test was used to measure statistical significance. Results: In nominal scenario, DLVCRO significantly improved dose, LET and xBD distributions to protect OARs (rectum: V70Gy: 3.07\% vs. 2.90\%, p = .0063, RO vs. DLVCRO; $\text{LET}_{\max}$ (keV/um): 11.53 vs. 9.44, p = .0101; $\text{xBD}_{\max}$ (Gy$\cdot$keV/um): 420.55 vs. 398.79, p = .0086; bladder: V65Gy: 4.82\% vs. 4.61\%, p = .0032; $\text{LET}_{\max}$ 8.97 vs. 7.51, p = .0047; $\text{xBD}_{\max}$ 490.11 vs. 476.71, p = .0641). The physical dose distributions in targets are comparable (D2%: 98.57\% vs. 98.39\%; p = .0805; CTV D2% - D98%: 7.10\% vs. 7.75\%, p = .4624). In the worst-case scenario, DLVCRO robustly enhanced OAR while maintaining the similar plan robustness in target dose coverage and homogeneity. Conclusion: DLVCRO upgrades 2D DVH-based to 3D DLVH-based treatment planning to adjust dose/LET distributions simultaneously and robustly. DLVCRO is potentially a powerful tool to improve patient outcomes in SSPT.

physics.med-ph↗

arXiv2024

An "Okay" Method for Observing Solar Eclipses

Solar eclipses, as rare astronomical events, often evoke a profound sense of wonder and awe within the human spirit. However, for ordinary people, the extremely short preparation time, a few hours of notice from friends or social media, and the lack of observation equipment often hinder safe and effective eclipse viewing. Some individuals directly observe the sun with their naked eyes, risking vision damage. To enable ordinary people to safely observe eclipses in very little preparation and reduce the risk of vision damage, we present a simple and safe method that almost anyone can use under very basic conditions, known as the "Okay" observation method.

physics.ed-ph↗

arXiv2023

Holistic Evaluation of GPT-4V for Biomedical Imaging

In this paper, we present a large-scale evaluation probing GPT-4V's capabilities and limitations for biomedical image analysis. GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain. We assess GPT-4V's performance across 16 medical imaging categories, including radiology, oncology, ophthalmology, pathology, and more. Tasks include modality recognition, anatomy localization, disease diagnosis, report generation, and lesion detection. The extensive experiments provide insights into GPT-4V's strengths and weaknesses. Results show GPT-4V's proficiency in modality and anatomy recognition but difficulty with disease diagnosis and localization. GPT-4V excels at diagnostic report generation, indicating strong image captioning skills. While promising for biomedical imaging AI, GPT-4V requires further enhancement and validation before clinical deployment. We emphasize responsible development and testing for trustworthy integration of biomedical AGI. This rigorous evaluation of GPT-4V on diverse medical images advances understanding of multimodal large language models (LLMs) and guides future work toward impactful healthcare applications.

eess.IV↗

arXiv2022

Geometry and physics in the deformations of crystalline caps

Elucidating the interplay of stress and geometry is a fundamental scientific question arising in multiple fields. In this work, we investigate the geometric frustration of crystalline caps confined on the sphere in both elastic and plastic regimes. Based on the revealed quasi-conformal ordering, we discover the partial, but uniform screening of the substrate curvature by the induced curvature underlying the inhomogeneous lattice. This scenario is fundamentally different from the conventional screening mechanism based on topological defects. In the plastic regime, the yield of highly stressed caps leads to fractures with featured morphologies not found in planar systems. We also demonstrate the strategy of engineering stress and fractures by vacancies. These results advance our general understanding on the organization and adaptivity of geometrically-frustrated crystalline order.

cond-mat.soft↗

arXiv2021

Dual-Modality Vehicle Anomaly Detection via Bilateral Trajectory Tracing

Traffic anomaly detection has played a crucial role in Intelligent Transportation System (ITS). The main challenges of this task lie in the highly diversified anomaly scenes and variational lighting conditions. Although much work has managed to identify the anomaly in homogenous weather and scene, few resolved to cope with complex ones. In this paper, we proposed a dual-modality modularized methodology for the robust detection of abnormal vehicles. We introduced an integrated anomaly detection framework comprising the following modules: background modeling, vehicle tracking with detection, mask construction, Region of Interest (ROI) backtracking, and dual-modality tracing. Concretely, we employed background modeling to filter the motion information and left the static information for later vehicle detection. For the vehicle detection and tracking module, we adopted YOLOv5 and multi-scale tracking to localize the anomalies. Besides, we utilized the frame difference and tracking results to identify the road and obtain the mask. In addition, we introduced multiple similarity estimation metrics to refine the anomaly period via backtracking. Finally, we proposed a dual-modality bilateral tracing module to refine the time further. The experiments conducted on the Track 4 testset of the NVIDIA 2021 AI City Challenge yielded a result of 0.9302 F1-Score and 3.4039 root mean square error (RMSE), indicating the effectiveness of our framework.

cs.CV↗

arXiv2021

The Blessings of Unlabeled Background in Untrimmed Videos

Weakly-supervised Temporal Action Localization (WTAL) aims to detect the action segments with only video-level action labels in training. The key challenge is how to distinguish the action of interest segments from the background, which is unlabelled even on the video-level. While previous works treat the background as "curses", we consider it as "blessings". Specifically, we first use causal analysis to point out that the common localization errors are due to the unobserved confounder that resides ubiquitously in visual recognition. Then, we propose a Temporal Smoothing PCA-based (TS-PCA) deconfounder, which exploits the unlabelled background to model an observed substitute for the unobserved confounder, to remove the confounding effect. Note that the proposed deconfounder is model-agnostic and non-intrusive, and hence can be applied in any WTAL method without model re-designs. Through extensive experiments on four state-of-the-art WTAL methods, we show that the deconfounder can improve all of them on the public datasets: THUMOS-14 and ActivityNet-1.3.

cs.CV↗

arXiv2020

Learning to Segment the Tail

Real-world visual recognition requires handling the extreme sample imbalance in large-scale long-tailed data. We propose a "divide&conquer" strategy for the challenging LVIS task: divide the whole data into balanced parts and then apply incremental learning to conquer each one. This derives a novel learning paradigm: class-incremental few-shot learning, which is especially effective for the challenge evolving over time: 1) the class imbalance among the old-class knowledge review and 2) the few-shot data in new-class learning. We call our approach Learning to Segment the Tail (LST). In particular, we design an instance-level balanced replay scheme, which is a memory-efficient approximation to balance the instance-level samples from the old-class images. We also propose to use a meta-module for new-class learning, where the module parameters are shared across incremental phases, gaining the learning-to-learn knowledge incrementally, from the data-rich head to the data-poor tail. We empirically show that: at the expense of a little sacrifice of head-class forgetting, we can gain a significant 8.3% AP improvement for the tail classes with less than 10 instances, achieving an overall 2.0% AP boost for the whole 1,230 classes.

cs.CV↗