arXiv subjects

Zhuo Chen

Publications and source records attributed to Zhuo Chen.

At least 271 records · Page 15Linked to original sources

arXiv2024

Domain-Agnostic Molecular Generation with Chemical Feedback

The generation of molecules with desired properties has become increasingly popular, revolutionizing the way scientists design molecular structures and providing valuable support for chemical and drug design. However, despite the potential of language models in molecule generation, they face challenges such as generating syntactically or chemically flawed molecules, having narrow domain focus, and struggling to create diverse and feasible molecules due to limited annotated data or external molecular databases. To tackle these challenges, we introduce MolGen, a pre-trained molecular language model tailored specifically for molecule generation. Through the reconstruction of over 100 million molecular SELFIES, MolGen internalizes structural and grammatical insights. This is further enhanced by domain-agnostic molecular prefix tuning, fostering robust knowledge transfer across diverse domains. Importantly, our chemical feedback paradigm steers the model away from molecular hallucinations, ensuring alignment between the model's estimated probabilities and real-world chemical preferences. Extensive experiments on well-known benchmarks underscore MolGen's optimization capabilities in properties such as penalized logP, QED, and molecular docking. Additional analyses confirm its proficiency in accurately capturing molecule distributions, discerning intricate structural patterns, and efficiently exploring the chemical space. Code is available at https://github.com/zjunlp/MolGen.

cs.LG↗

arXiv2024

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

Large Language Models (LLMs), with their remarkable task-handling capabilities and innovative outputs, have catalyzed significant advancements across a spectrum of fields. However, their proficiency within specialized domains such as biomolecular studies remains limited. To address this challenge, we introduce Mol-Instructions, a comprehensive instruction dataset designed for the biomolecular domain. Mol-Instructions encompasses three key components: molecule-oriented instructions, protein-oriented instructions, and biomolecular text instructions. Each component aims to improve the understanding and prediction capabilities of LLMs concerning biomolecular features and behaviors. Through extensive instruction tuning experiments on LLMs, we demonstrate the effectiveness of Mol-Instructions in enhancing large models' performance in the intricate realm of biomolecular studies, thus fostering progress in the biomolecular research community. Mol-Instructions is publicly available for ongoing research and will undergo regular updates to enhance its applicability.

q-bio.QM↗

arXiv2024

DRAK: Unlocking Molecular Insights with Domain-Specific Retrieval-Augmented Knowledge in LLMs

Large Language Models (LLMs) encounter challenges with the unique syntax of specific domains, such as biomolecules. Existing fine-tuning or modality alignment techniques struggle to bridge the domain knowledge gap and understand complex molecular data, limiting LLMs' progress in specialized fields. To overcome these limitations, we propose an expandable and adaptable non-parametric knowledge injection framework named Domain-specific Retrieval-Augmented Knowledge (DRAK), aimed at enhancing reasoning capabilities in specific domains. Utilizing knowledge-aware prompts and gold label-induced reasoning, DRAK has developed profound expertise in the molecular domain and the capability to handle a broad spectrum of analysis tasks. We evaluated two distinct forms of DRAK variants, proving that DRAK exceeds previous benchmarks on six molecular tasks within the Mol-Instructions dataset. Extensive experiments have underscored DRAK's formidable performance and its potential to unlock molecular insights, offering a unified paradigm for LLMs to tackle knowledge-intensive tasks in specific domains. Our code will be available soon.

q-bio.BM↗

arXiv2024

Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey

Knowledge Graphs (KGs) play a pivotal role in advancing various AI applications, with the semantic web community's exploration into multi-modal dimensions unlocking new avenues for innovation. In this survey, we carefully review over 300 articles, focusing on KG-aware research in two principal aspects: KG-driven Multi-Modal (KG4MM) learning, where KGs support multi-modal tasks, and Multi-Modal Knowledge Graph (MM4KG), which extends KG studies into the MMKG realm. We begin by defining KGs and MMKGs, then explore their construction progress. Our review includes two primary task categories: KG-aware multi-modal learning tasks, such as Image Classification and Visual Question Answering, and intrinsic MMKG tasks like Multi-modal Knowledge Graph Completion and Entity Alignment, highlighting specific research trajectories. For most of these tasks, we provide definitions, evaluation benchmarks, and additionally outline essential insights for conducting relevant research. Finally, we discuss current challenges and identify emerging trends, such as progress in Large Language Modeling and Multi-modal Pre-training strategies. This survey aims to serve as a comprehensive reference for researchers already involved in or considering delving into KG and multi-modal learning research, offering insights into the evolving landscape of MMKG research and supporting future work.

cs.AI↗

arXiv2024

Revisit and Outstrip Entity Alignment: A Perspective of Generative Models

Recent embedding-based methods have achieved great successes in exploiting entity alignment from knowledge graph (KG) embeddings of multiple modalities. In this paper, we study embedding-based entity alignment (EEA) from a perspective of generative models. We show that EEA shares similarities with typical generative models and prove the effectiveness of the recently developed generative adversarial network (GAN)-based EEA methods theoretically. We then reveal that their incomplete objective limits the capacity on both entity alignment and entity synthesis (i.e., generating new entities). We mitigate this problem by introducing a generative EEA (GEEA) framework with the proposed mutual variational autoencoder (M-VAE) as the generative model. M-VAE enables entity conversion between KGs and generation of new entities from random noise vectors. We demonstrate the power of GEEA with theoretical analysis and empirical experiments on both entity alignment and entity synthesis tasks.

cs.CL↗

arXiv2024

Unleashing the Power of Imbalanced Modality Information for Multi-modal Knowledge Graph Completion

Multi-modal knowledge graph completion (MMKGC) aims to predict the missing triples in the multi-modal knowledge graphs by incorporating structural, visual, and textual information of entities into the discriminant models. The information from different modalities will work together to measure the triple plausibility. Existing MMKGC methods overlook the imbalance problem of modality information among entities, resulting in inadequate modal fusion and inefficient utilization of the raw modality information. To address the mentioned problems, we propose Adaptive Multi-modal Fusion and Modality Adversarial Training (AdaMF-MAT) to unleash the power of imbalanced modality information for MMKGC. AdaMF-MAT achieves multi-modal fusion with adaptive modality weights and further generates adversarial samples by modality-adversarial training to enhance the imbalanced modality information. Our approach is a co-design of the MMKGC model and training strategy which can outperform 19 recent MMKGC methods and achieve new state-of-the-art results on three public MMKGC benchmarks. Our code and data have been released at https://github.com/zjukg/AdaMF-MAT.

cs.AI↗

arXiv2024

ICMC-ASR: The ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition Challenge

To promote speech processing and recognition research in driving scenarios, we build on the success of the Intelligent Cockpit Speech Recognition Challenge (ICSRC) held at ISCSLP 2022 and launch the ICASSP 2024 In-Car Multi-Channel Automatic Speech Recognition (ICMC-ASR) Challenge. This challenge collects over 100 hours of multi-channel speech data recorded inside a new energy vehicle and 40 hours of noise for data augmentation. Two tracks, including automatic speech recognition (ASR) and automatic speech diarization and recognition (ASDR) are set up, using character error rate (CER) and concatenated minimum permutation character error rate (cpCER) as evaluation metrics, respectively. Overall, the ICMC-ASR Challenge attracts 98 participating teams and receives 53 valid results in both tracks. In the end, first-place team USTCiflytek achieves a CER of 13.16% in the ASR track and a cpCER of 21.48% in the ASDR track, showing an absolute improvement of 13.08% and 51.4% compared to our challenge baseline, respectively.

cs.SD↗

arXiv2024

ChatCell: Facilitating Single-Cell Analysis with Natural Language

As Large Language Models (LLMs) rapidly evolve, their influence in science is becoming increasingly prominent. The emerging capabilities of LLMs in task generalization and free-form dialogue can significantly advance fields like chemistry and biology. However, the field of single-cell biology, which forms the foundational building blocks of living organisms, still faces several challenges. High knowledge barriers and limited scalability in current methods restrict the full exploitation of LLMs in mastering single-cell data, impeding direct accessibility and rapid iteration. To this end, we introduce ChatCell, which signifies a paradigm shift by facilitating single-cell analysis with natural language. Leveraging vocabulary adaptation and unified sequence generation, ChatCell has acquired profound expertise in single-cell biology and the capability to accommodate a diverse range of analysis tasks. Extensive experiments further demonstrate ChatCell's robust performance and potential to deepen single-cell insights, paving the way for more accessible and intuitive exploration in this pivotal field. Our project homepage is available at https://zjunlp.github.io/project/ChatCell.

cs.CL↗

arXiv2024

Bridging the gap between luminous red novae and common envelope evolution: the role of recombination energy and radiation force

Luminous red novae (LRNe) and their connection to common envelope evolution (CEE) remain elusive in astrophysics. Here, we present a radiation hydrodynamic model capable of simulating the light curves of material ejected during a CEE. For the first time, the radiation hydrodynamic model incorporates complete recombination physics for hydrogen and helium. The radiation hydrodynamic equations are solved with Guangqi. With time-independent ejecta simulations, we show that the peaks in the light curves are attributed to radiation-dominated ejecta, while the extended plateaus are produced by matter-dominated ejecta. To showcase our model's capability, we fit the light curve of AT2019zhd. The central mass object of $6M_{\odot}$ is assumed based on observations and scaling relations. Our model demonstrates that the ejecta mass of AT2019zhd falls within the range of $0.04M_{\odot}$ to $0.1M_{\odot}$. Additionally, we demonstrate that recombination energy and radiation force acceleration significantly impact the light curves, whereas dust formation has a limited effect during the peak and plateau phases.

astro-ph.SR↗

arXiv2024

Real-time, noise and drift resilient formaldehyde sensing at room temperature with aerogel filaments

Formaldehyde, a known human carcinogen, is a common indoor air pollutant. However, its real-time and selective recognition from interfering gases remains challenging, especially for low-power sensors suffering from noise and baseline drift. We report a fully 3D-printed quantum dot/graphene-based aerogel sensor for highly sensitive and real-time recognition of formaldehyde at room temperature. By optimising the morphology and doping of the printed structures, we achieve a record-high response of 15.23 percent for 1 parts-per-million formaldehyde and an ultralow detection limit of 8.02 parts-per-billion consuming only 130 uW power. Based on measured dynamic response snapshots, we also develop an intelligent computational algorithm for robust and accurate detection in real time despite simulated substantial noise and baseline drift, hitherto unachievable for room-temperature sensors. Our framework in combining materials engineering, structural design and computational algorithm to capture dynamic response offers unprecedented real-time identification capabilities of formaldehyde and other volatile organic compounds at room temperature.

physics.app-ph↗

arXiv2024

Power Transformer Fault Prediction Based on Knowledge Graphs

In this paper, we address the challenge of learning with limited fault data for power transformers. Traditional operation and maintenance tools lack effective predictive capabilities for potential faults. The scarcity of extensive fault data makes it difficult to apply machine learning techniques effectively. To solve this problem, we propose a novel approach that leverages the knowledge graph (KG) technology in combination with gradient boosting decision trees (GBDT). This method is designed to efficiently learn from a small set of high-dimensional data, integrating various factors influencing transformer faults and historical operational data. Our approach enables accurate safe state assessments and fault analyses of power transformers despite the limited fault characteristic data. Experimental results demonstrate that this method outperforms other learning approaches in prediction accuracy, such as artificial neural networks (ANN) and logistic regression (LR). Furthermore, it offers significant improvements in progressiveness, practicality, and potential for widespread application.

cs.LG↗

arXiv2024

DARCS: Memory-Efficient Deep Compressed Sensing Reconstruction for Acceleration of 3D Whole-Heart Coronary MR Angiography

Three-dimensional coronary magnetic resonance angiography (CMRA) demands reconstruction algorithms that can significantly suppress the artifacts from a heavily undersampled acquisition. While unrolling-based deep reconstruction methods have achieved state-of-the-art performance on 2D image reconstruction, their application to 3D reconstruction is hindered by the large amount of memory needed to train an unrolled network. In this study, we propose a memory-efficient deep compressed sensing method by employing a sparsifying transform based on a pre-trained artifact estimation network. The motivation is that the artifact image estimated by a well-trained network is sparse when the input image is artifact-free, and less sparse when the input image is artifact-affected. Thus, the artifact-estimation network can be used as an inherent sparsifying transform. The proposed method, named De-Aliasing Regularization based Compressed Sensing (DARCS), was compared with a traditional compressed sensing method, de-aliasing generative adversarial network (DAGAN), model-based deep learning (MoDL), and plug-and-play for accelerations of 3D CMRA. The results demonstrate that the proposed method improved the reconstruction quality relative to the compared methods by a large margin. Furthermore, the proposed method well generalized for different undersampling rates and noise levels. The memory usage of the proposed method was only 63% of that needed by MoDL. In conclusion, the proposed method achieves improved reconstruction quality for 3D CMRA with reduced memory burden.

eess.IV↗

arXiv2024

Rethinking the Soft Conflict Pseudo Boolean Constraint on MaxSAT Local Search Solvers

MaxSAT is an optimization version of the famous NP-complete Satisfiability problem (SAT). Algorithms for MaxSAT mainly include complete solvers and local search incomplete solvers. In many complete solvers, once a better solution is found, a Soft conflict Pseudo Boolean (SPB) constraint will be generated to enforce the algorithm to find better solutions. In many local search algorithms, clause weighting is a key technique for effectively guiding the search directions. In this paper, we propose to transfer the SPB constraint into the clause weighting system of the local search method, leading the algorithm to better solutions. We further propose an adaptive clause weighting strategy that breaks the tradition of using constant values to adjust clause weights. Based on the above methods, we propose a new local search algorithm called SPB-MaxSAT that provides new perspectives for clause weighting on MaxSAT local search solvers. Extensive experiments demonstrate the excellent performance of the proposed methods.

cs.AI↗

arXiv2024

ELLA-V: Stable Neural Codec Language Modeling with Alignment-guided Sequence Reordering

The language model (LM) approach based on acoustic and linguistic prompts, such as VALL-E, has achieved remarkable progress in the field of zero-shot audio generation. However, existing methods still have some limitations: 1) repetitions, transpositions, and omissions in the output synthesized speech due to limited alignment constraints between audio and phoneme tokens; 2) challenges of fine-grained control over the synthesized speech with autoregressive (AR) language model; 3) infinite silence generation due to the nature of AR-based decoding, especially under the greedy strategy. To alleviate these issues, we propose ELLA-V, a simple but efficient LM-based zero-shot text-to-speech (TTS) framework, which enables fine-grained control over synthesized audio at the phoneme level. The key to ELLA-V is interleaving sequences of acoustic and phoneme tokens, where phoneme tokens appear ahead of the corresponding acoustic tokens. The experimental findings reveal that our model outperforms VALL-E in terms of accuracy and delivers more stable results using both greedy and sampling-based decoding strategies. The code of ELLA-V will be open-sourced after cleanups. Audio samples are available at https://ereboas.github.io/ELLAV/.

cs.CL↗

arXiv2023

Inkjet-Printed High-Yield, Reconfigurable, and Recyclable Memristors on Paper

Reconfigurable memristors featuring neural and synaptic functions hold great potential for neuromorphic circuits by simplifying system architecture, cutting power consumption, and boosting computational efficiency. Their additive manufacturing on sustainable substrates offers unique advantages for future electronics, including low environmental impact. Here, exploiting structure-property relationship of MoS2 nanoflake-based resistive layer, we present paper-based, inkjet-printed, reconfigurable memristors. With >90% yield from a 16x65 device array, our memristors demonstrate robust resistive switching, with $>10^5$ ON-OFF ratio and <0.5 V operation in non-volatile state. Through modulation of compliance current, the devices transition into volatile state, with only 50 pW switching power consumption, rivalling state-of-the-art metal oxide-based counterparts. We show device recyclability and stable, reconfigurable operation following disassembly, material collection and re-fabrication. We further demonstrate synaptic plasticity and neuronal leaky integrate-and-fire functionality, with disposable applications in smart packaging and simulated medical image diagnostics. Our work shows a sustainable pathway towards printable, high-yield, reconfigurable neuromorphic devices, with minimal environmental footprint.

cs.ET↗

arXiv2023

Structure-CLIP: Towards Scene Graph Knowledge to Enhance Multi-modal Structured Representations

Large-scale vision-language pre-training has achieved significant performance in multi-modal understanding and generation tasks. However, existing methods often perform poorly on image-text matching tasks that require structured representations, i.e., representations of objects, attributes, and relations. As illustrated in Fig.~reffig:case (a), the models cannot make a distinction between ``An astronaut rides a horse" and ``A horse rides an astronaut". This is because they fail to fully leverage structured knowledge when learning representations in multi-modal scenarios. In this paper, we present an end-to-end framework Structure-CLIP, which integrates Scene Graph Knowledge (SGK) to enhance multi-modal structured representations. Firstly, we use scene graphs to guide the construction of semantic negative examples, which results in an increased emphasis on learning structured representations. Moreover, a Knowledge-Enhance Encoder (KEE) is proposed to leverage SGK as input to further enhance structured representations. To verify the effectiveness of the proposed framework, we pre-train our model with the aforementioned approaches and conduct experiments on downstream tasks. Experimental results demonstrate that Structure-CLIP achieves state-of-the-art (SOTA) performance on VG-Attribution and VG-Relation datasets, with 12.5% and 4.1% ahead of the multi-modal SOTA model respectively. Meanwhile, the results on MSCOCO indicate that Structure-CLIP significantly enhances the structured representations while maintaining the ability of general representations. Our code is available at https://github.com/zjukg/Structure-CLIP.

cs.CL↗

arXiv2023

Benchmarking highly entangled states on a 60-atom analog quantum simulator

Quantum systems have entered a competitive regime where classical computers must make approximations to represent highly entangled quantum states. However, in this beyond-classically-exact regime, fidelity comparisons between quantum and classical systems have so far been limited to digital quantum devices, and it remains unsolved how to estimate the actual entanglement content of experiments. Here we perform fidelity benchmarking and mixed-state entanglement estimation with a 60-atom analog Rydberg quantum simulator, reaching a high entanglement entropy regime where exact classical simulation becomes impractical. Our benchmarking protocol involves extrapolation from comparisons against an approximate classical algorithm, introduced here, with varying entanglement limits. We then develop and demonstrate an estimator of the experimental mixed-state entanglement, finding our experiment is competitive with state-of-the-art digital quantum devices performing random circuit evolution. Finally, we compare the experimental fidelity against that achieved by various approximate classical algorithms, and find that only the algorithm we introduce is able to keep pace with the experiment on the classical hardware we employ. Our results enable a new paradigm for evaluating the ability of both analog and digital quantum devices to generate entanglement in the beyond-classically-exact regime, and highlight the evolving divide between quantum and classical systems.

quant-ph↗

arXiv2023

Newton-Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems

Reasoning system dynamics is one of the most important analytical approaches for many scientific studies. With the initial state of a system as input, the recent graph neural networks (GNNs)-based methods are capable of predicting the future state distant in time with high accuracy. Although these methods have diverse designs in modeling the coordinates and interacting forces of the system, we show that they actually share a common paradigm that learns the integration of the velocity over the interval between the initial and terminal coordinates. However, their integrand is constant w.r.t. time. Inspired by this observation, we propose a new approach to predict the integration based on several velocity estimations with Newton-Cotes formulas and prove its effectiveness theoretically. Extensive experiments on several benchmarks empirically demonstrate consistent and significant improvement compared with the state-of-the-art methods.

cs.LG↗