Aimin Zhou
YOU?
Author Swipe
View article: A Large Language Model for Chemistry and Retrosynthesis Predictions
A Large Language Model for Chemistry and Retrosynthesis Predictions Open
Large language models (LLM) have achieved impressive progress across a broad range of general-purpose tasks, but their effectiveness in chemistry remains limited due to scarce domain-specific datasets and the demand for precise symbolic an…
View article: Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling
Mis-prompt: Benchmarking Large Language Models for Proactive Error Handling Open
Large language models (LLMs) have demonstrated significant advancements in error handling. Current error-handling works are performed in a passive manner, with explicit error-handling instructions. However, in real-world scenarios, explici…
View article: Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models
Expensive Multi-Objective Bayesian Optimization Based on Diffusion Models Open
Multi-objective Bayesian optimization (MOBO) has shown promising performance on various expensive multi-objective optimization problems (EMOPs). However, effectively modeling complex distributions of the Pareto optimal solutions is difficu…
View article: Un-evaluated Solutions May Be Valuable in Expensive Optimization
Un-evaluated Solutions May Be Valuable in Expensive Optimization Open
Expensive optimization problems (EOPs) are prevalent in real-world applications, where the evaluation of a single solution requires a significant amount of resources. In our study of surrogate-assisted evolutionary algorithms (SAEAs) in EO…
View article: DPANet: Position‐aware feature encoding and decoding for accurate large‐scale point cloud semantic segmentation
DPANet: Position‐aware feature encoding and decoding for accurate large‐scale point cloud semantic segmentation Open
Due to the scattered, unordered, and unstructured nature of point clouds, it is challenging to extract local features. Existing methods tend to design redundant and less‐discriminative spatial feature extraction methods in the encoder, whi…
View article: LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch
LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch Open
Optimization problems are prevalent across various scenarios. Formulating and then solving optimization problems described by natural language often requires highly specialized human expertise, which could block the widespread application …
View article: High-Dimensional Causal Bayesian Optimization
High-Dimensional Causal Bayesian Optimization Open
Causal global optimization (CGO) aims to complete optimization tasks through causal inference. In the high-dimensional CGO problems, traditional causal Bayesian optimization (CBO) methods struggle with the curse of dimensionality attribute…
View article: Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models
Investigating and Mitigating Object Hallucinations in Pretrained Vision-Language (CLIP) Models Open
Large Vision-Language Models (LVLMs) have achieved impressive performance, yet research has pointed out a serious issue with object hallucinations within these models. However, there is no clear conclusion as to which part of the model the…
View article: CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models
CMM-Math: A Chinese Multimodal Math Dataset To Evaluate and Enhance the Mathematics Reasoning of Large Multimodal Models Open
Large language models (LLMs) have obtained promising results in mathematical reasoning, which is a foundational skill for human intelligence. Most previous studies focus on improving and measuring the performance of LLMs based on textual m…
View article: LASCA: A Large-Scale Stable Customer Segmentation Approach to Credit Risk Assessment
LASCA: A Large-Scale Stable Customer Segmentation Approach to Credit Risk Assessment Open
Customer segmentation plays a crucial role in credit risk assessment by dividing users into specific risk levels based on their credit scores. Previous methods fail to comprehensively consider the stability in the segmentation process, res…
View article: F-CPI: Prediction of activity changes induced by fluorine substitution using multimodal deep learning
F-CPI: Prediction of activity changes induced by fluorine substitution using multimodal deep learning Open
There are a large number of fluorine (F)-containing compounds in approved drugs, and F substitution is a common method in drug discovery and development. However, F is difficult to form traditional hydrogen bonds and typical halogen bonds.…
View article: Expensive Optimization via Relation
Expensive Optimization via Relation Open
Expensive optimization problems pose significant challenges to traditional gradient-free optimization due to their costly evaluation overhead. Surrogate model-assisted evolutionary optimization, which substitutes expensive evaluation funct…
View article: Context-aware Diversity Enhancement for Neural Multi-Objective Combinatorial Optimization
Context-aware Diversity Enhancement for Neural Multi-Objective Combinatorial Optimization Open
Multi-objective combinatorial optimization (MOCO) problems are prevalent in various real-world applications. Most existing neural MOCO methods rely on problem decomposition to transform an MOCO problem into a series of singe-objective comb…
View article: Inductive Cognitive Diagnosis for Fast Student Learning in Web-Based Intelligent Education Systems
Inductive Cognitive Diagnosis for Fast Student Learning in Web-Based Intelligent Education Systems Open
Cognitive diagnosis aims to gauge students' mastery levels based on their\nresponse logs. Serving as a pivotal module in web-based online intelligent\neducation systems (WOIESs), it plays an upstream and fundamental role in\ndownstream tas…
View article: From Coarse to Fine: A Distillation Method for Fine-Grained Emotion-Causal Span Pair Extraction in Conversation
From Coarse to Fine: A Distillation Method for Fine-Grained Emotion-Causal Span Pair Extraction in Conversation Open
We study the problem of extracting emotions and the causes behind these emotions in conversations. Existing methods either tackle them separately or jointly model them at the coarse-grained level of emotions (fewer emotion categories) and …
View article: Wasserstein Differential Privacy
Wasserstein Differential Privacy Open
Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving machine learning. However, existing DP frameworks do not satisfy all the conditions for becoming metrics, which prevents them from deriving better…
View article: Are You Concerned about Limited Function Evaluations: Data-Augmented Pareto Set Learning for Expensive Multi-Objective Optimization
Are You Concerned about Limited Function Evaluations: Data-Augmented Pareto Set Learning for Expensive Multi-Objective Optimization Open
Optimizing multiple conflicting black-box objectives simultaneously is a prevalent occurrence in many real-world applications, such as neural architecture search, and machine learning. These problems are known as expensive multi-objective …
View article: Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems
Symbolic Cognitive Diagnosis via Hybrid Optimization for Intelligent Education Systems Open
Cognitive diagnosis assessment is a fundamental and crucial task for student learning. It models the student-exercise interaction, and discovers the students' proficiency levels on each knowledge attribute. In real-world intelligent educat…
View article: Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition
Emotion Neural Transducer for Fine-Grained Speech Emotion Recognition Open
The mainstream paradigm of speech emotion recognition (SER) is identifying\nthe single emotion label of the entire utterance. This line of works neglect\nthe emotion dynamics at fine temporal granularity and mostly fail to leverage\nlingui…
View article: Wasserstein Differential Privacy
Wasserstein Differential Privacy Open
Differential privacy (DP) has achieved remarkable results in the field of privacy-preserving machine learning. However, existing DP frameworks do not satisfy all the conditions for becoming metrics, which prevents them from deriving better…
View article: Skills and Techniques of Machine Repair Fitters
Skills and Techniques of Machine Repair Fitters Open
In this important understanding of machining, mechanical maintenance fitter occupies an important position. Machine repair fitters are mainly responsible for the processing and maintenance of various mechanical equipment, and use scientifi…
View article: Temporal Shift Module with Pretrained Representations for Speech Emotion Recognition
Temporal Shift Module with Pretrained Representations for Speech Emotion Recognition Open
Recent advances in self-supervised models have led to effective pretrained speech representations in downstream speech emotion recognition tasks. However, previous research has primarily focused on exploiting pretrained representations by …