Search Results for author:
Found 82 papers, 25 papers with code
Integrating Generative Adversarial Networks and Convolutional Neural Networks for Enhanced Traffic Accidents Detection and Analysis
Accident detection using Closed Circuit Television (CCTV) footage is one of the most imperative features for enhancing transport safety and efficient traffic control.
Combining Self-attention and Dilation Convolutional for Semantic Segmentation of Coal Maceral Groups
The segmentation of coal maceral groups can be described as a semantic segmentation process of coal maceral group images, which is of great significance for studying the chemical properties of coal.
Topological Machine Learning for Protein-Nucleic Acid Binding Affinity Changes Upon Mutation
Understanding how protein mutations affect protein-nucleic acid binding is critical for unraveling disease mechanisms and advancing therapies.
Can Compressed LLMs Truly Act? An Empirical Evaluation of Agentic Capabilities in LLM Compression
Post-training compression reduces the computational and memory costs of large language models (LLMs), enabling resource-efficient deployment.
Efficient Reasoning via Chain of Unconscious Thought
Inspired by UTT, we propose a new reasoning paradigm, termed Chain of Unconscious Thought (CoUT), to improve the token efficiency of LRMs by guiding them to mimic human unconscious thought and internalize reasoning processes.
Multimodal Online Federated Learning with Modality Missing in Internet of Things
Furthermore, the real-time nature of data collection and limited local storage on edge devices in IoT call for an online learning paradigm.
FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management
FlowKV's core innovation is a multi-turn isolation mechanism that preserves the accumulated compressed KV cache from past turns.
CAFES: A Collaborative Multi-Agent Framework for Multi-Granular Multimodal Essay Scoring
Automated Essay Scoring (AES) is crucial for modern education, particularly with the increasing prevalence of multimodal assessments.
Teach2Eval: An Indirect Evaluation Method for LLM by Judging How It Teaches
Recent progress in large language models (LLMs) has outpaced the development of effective evaluation methods.
Quotient Complex Transformer (QCformer) for Perovskite Data Analysis
To address these limitations, we propose a novel representation based on quotient complexes (QCs) and introduce the Quotient Complex Transformer (QCformer) for material property prediction.
TSP-OCS: A Time-Series Prediction for Optimal Camera Selection in Multi-Viewpoint Surgical Video Analysis
This study addresses these limitations by employing a multi-viewpoint camera recording system, capturing the surgical procedure from six different angles to mitigate occlusions.
Learning Shape-Independent Transformation via Spherical Representations for Category-Level Object Pose Estimation
Category-level object pose estimation aims to determine the pose and size of novel objects in specific categories.
State Space Model Meets Transformer: A New Paradigm for 3D Object Detection
To the best of our knowledge, this is the first method to model queries as system states and scene points as system inputs, which can simultaneously update scene point features and query features with linear complexity.
Ranked #1 on
3D Object Detection
on ScanNetV2
A Multimodal Benchmark Dataset and Model for Crop Disease Diagnosis
We demonstrate the utility of the dataset by finetuning state-of-the-art multimodal models, showcasing significant improvements in crop disease diagnosis.
Optimizing for the Shortest Path in Denoising Diffusion Model
In this research, we propose a novel denoising diffusion model based on shortest-path modeling that optimizes residual propagation to enhance both denoising efficiency and quality. Drawing on Denoising Diffusion Implicit Models (DDIM) and insights from graph theory, our model, termed the Shortest Path Diffusion Model (ShortDF), treats the denoising process as a shortest-path problem aimed at minimizing reconstruction error.
Manifold Topological Deep Learning for Biomedical Data
Recently, topological deep learning (TDL), which integrates algebraic topology with deep neural networks, has achieved tremendous success in processing point-cloud data, emerging as a promising paradigm in data science.
The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
In this blog, we present a brief review of recent advancements in LLMs related to retrieval-augmented generation, multi-step reasoning, external tools, and computational expressivity, all of which substantially enhance LLM performance.
Road Traffic Sign Recognition method using Siamese network Combining Efficient-CNN based Encoder
Traffic signs recognition (TSR) plays an essential role in assistant driving and intelligent transportation system.
Perovskite-LLM: Knowledge-Enhanced Large Language Models for Perovskite Solar Cell Research
The rapid advancement of perovskite solar cells (PSCs) has led to an exponential growth in research publications, creating an urgent need for efficient knowledge management and reasoning systems in this domain.
EssayJudge: A Multi-Granular Benchmark for Assessing Automated Essay Scoring Capabilities of Multimodal Large Language Models
Automated Essay Scoring (AES) plays a crucial role in educational assessment by providing scalable and consistent evaluations of writing tasks.
Automatic Pruning via Structured Lasso with Class-wise Information
For instance, using the VGG16 model on the CIFAR-10 dataset, we achieve a parameter reduction of 85%, a decrease in FLOPs by 61%, and maintain an accuracy of 94. 10% (0. 14% higher than the original model); we reduce the parameters by 55% with the accuracy at 76. 12% using the ResNet architecture on ImageNet (only drops 0. 03%).
One-shot Federated Learning Methods: A Practical Guide
One-shot Federated Learning (OFL) is a distributed machine learning paradigm that constrains client-server communication to a single round, addressing privacy and communication overhead issues associated with multiple rounds of data exchange in traditional Federated Learning (FL).
HODDI: A Dataset of High-Order Drug-Drug Interactions for Computational Pharmacovigilance
However, the scarcity of higher-order datasets that capture the combinatorial effects of multiple drugs severely limits progress in this field.
Mediator: Memory-efficient LLM Merging with Less Parameter Conflicts and Uncertainty Based Routing
To further reduce storage costs, inspired by task arithmetic sparsity, we decouple multiple fine-tuned experts into a dense expert and several sparse experts.
Can LLMs Maintain Fundamental Abilities under KV Cache Compression?
This paper investigates an underexplored challenge in large language models (LLMs): the impact of KV cache compression methods on LLMs' fundamental capabilities.
ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference.
Rethinking Noisy Video-Text Retrieval via Relation-aware Alignment
Video-Text Retrieval (VTR) is a core task in multi-modal understanding, drawing growing attention from both academia and industry in recent years.
Dual-Agent Optimization framework for Cross-Domain Few-Shot Segmentation
In the consistent mutual aggregation module, we employ a set of agents to learn domain-invariant features across domains, and then use these features to enhance the original representations for feature adaptation.
Learning Radiance Fields from a Single Snapshot Compressive Image
SCI is a cost-effective method that enables the recording of high-dimensional data, such as hyperspectral or temporal information, into a single image using low-cost 2D imaging sensors.
SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image Generation
To adapt SILMM to LMMs with continuous features, we propose a diversity mechanism to obtain diverse representations and a kernel-based continuous DPO for alignment.
S3TU-Net: Structured Convolution and Superpixel Transformer for Lung Nodule Segmentation
In addition to comparison and ablation studies, we validated the generalization ability of our model on the EPDB private dataset, achieving a DSC of 86. 40%.
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Our findings indicate that current editing methods are only suitable for small-scale knowledge updates within language models, which motivates further research on more practical and reliable editing methods.
Efficient Partitioning Vision Transformer on Edge Devices for Distributed Inference
To further reduce computational overhead and inference latency, we introduce a class-wise pruning technique that decreases the size of each sub-model.
LPZero: Language Model Zero-cost Proxy Search from Zero
Specifically, we model the ZC proxy as a symbolic equation and incorporate a unified proxy search space that encompasses existing ZC proxies, which are composed of a predefined set of mathematical symbols.
LongGenBench: Long-context Generation Benchmark
Current long-context benchmarks primarily focus on retrieval-based tests, requiring Large Language Models (LLMs) to locate specific information within extensive input contexts, such as the needle-in-a-haystack (NIAH) benchmark.
DIIT: A Domain-Invariant Information Transfer Method for Industrial Cross-Domain Recommendation
Finally, for improving the efficiency, we design a migrator to transfer the extracted information to the latest target domain model, which only need the target domain model for inference.
Piculet: Specialized Models-Guided Hallucination Decrease for MultiModal Large Language Models
Multimodal Large Language Models (MLLMs) have made significant progress in bridging the gap between visual and language modalities.
3D Question Answering for City Scene Understanding
3D multimodal question answering (MQA) plays a crucial role in scene understanding by enabling intelligent agents to comprehend their surroundings in 3D environments.
Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for Large Language Models
In particular, we devise an elaborate search space encompassing the existing pruning metrics to discover the potential symbolic pruning metric.
Gaussian Primitives for Deformable Image Registration
Furthermore, the movement of individual voxel is derived via blending the local rigid transformation of the neighboring Gaussian primitives.
FedCAda: Adaptive Client-Side Optimization for Accelerated and Stable Federated Learning
This comparative analysis revealed that due to the limited information contained within client models from other clients during the initial stages of federated learning, more substantial constraints need to be imposed on the parameters of the adaptive algorithm.
Computation and Communication Efficient Lightweighting Vertical Federated Learning for Smart Building IoT
With the increasing number and enhanced capabilities of IoT devices in smart buildings, these devices are evolving beyond basic data collection and control to actively participate in deep learning tasks.
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Attempting to complement this deficiency, we investigate the layerwise properties of LoRA on fine-tuning tasks and observe an unexpected but consistent skewness of weight norms across different layers.
Are LLMs Rational Investors? A Study on Detecting and Reducing the Financial Bias in LLMs
Results show varying degrees of financial irrationality among models, influenced by their design and training.
ParZC: Parametric Zero-Cost Proxies for Efficient NAS
Recent advancements in Zero-shot Neural Architecture Search (NAS) highlight the efficacy of zero-cost proxies in various NAS benchmarks.
An Efficient Implicit Neural Representation Image Codec Based on Mixed Autoregressive Model for Low-Complexity Decoding
To the best of our knowledge, our method is the first INR-based codec comparable with Hyperprior in both decoding speed and quality while maintaining low complexity.
MAPO: Advancing Multilingual Reasoning through Multilingual Alignment-as-Preference Optimization
To enhance reasoning abilities in non-dominant languages, we propose a Multilingual-Alignment-as-Preference Optimization framework (MAPO), aiming to align the reasoning processes in other languages with the dominant language.
Plum: Prompt Learning using Metaheuristic
Since the emergence of large language models, prompt learning has become a popular method for optimizing and customizing these models.
Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models
For end users, our benchmark and findings help better understand different optimization techniques, training and inference frameworks, together with hardware platforms in choosing configurations for deploying LLMs.
$R^3$-NL2GQL: A Model Coordination and Knowledge Graph Alignment Approach for NL2GQL
While current tasks of converting natural language to SQL (NL2SQL) using Foundation Models have shown impressive achievements, adapting these approaches for converting natural language to Graph Query Language (NL2GQL) encounters hurdles due to the distinct nature of GQL compared to SQL, alongside the diverse forms of GQL.
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Efficiently aggregating trained neural networks from local clients into a global model on a server is a widely researched topic in federated learning.
Torsion Graph Neural Networks
This demonstrates that analytic torsion is a highly efficient topological invariant in the characterization of graph structures and can significantly boost the performance of GNNs.
Depression Detection Using Digital Traces on Social Media: A Knowledge-aware Deep Learning Approach
Depression is a common disease worldwide.
Active Prompting with Chain-of-Thought for Large Language Models
For this purpose, we propose a solution to the key problem of determining which questions are the most important and helpful ones to annotate from a pool of task-specific queries.
AI of Brain and Cognitive Sciences: From the Perspective of First Principles
Nowadays, we have witnessed the great success of AI in various applications, including image classification, game playing, protein structure analysis, language translation, and content generation.
Research on College Students' Innovation and Entrepreneurship Education from The Perspective of Artificial Intelligence Knowledge-Based Crowdsourcing
Based on the practical process of innovation and entrepreneurship education for college students in the author's university, this study analyzes and deconstructs the key concepts of AI knowledge-based crowdsourcing on the basis of literature research, and analyzes the objective fitting needs of combining AI knowledge-based crowdsourcing with college students' innovation and entrepreneurship education practice through a survey and research of a random sample of college students, and verifies that college students' knowledge and application of AI knowledge-based crowdsourcing in the learning and practice of innovation and entrepreneurship The study also verifies the awareness and application of AI knowledge-based crowdsourcing knowledge by university students in the learning and practice of innovation and entrepreneurship.
Cross-Modality Transformer for Visible-Infrared Person Re-Identification
To alleviate the above issues, we propose a novel Cross-Modality Transformer (CMT) to jointly explore a modality-level alignment module and an instance-level module for VI-ReID.
Care for the Mind Amid Chronic Diseases: An Interpretable AI Approach Using IoT
We draw on the medical literature to support depression detection using motion sensor data.
Spacecraft depth completion based on the gray image and the sparse depth map
In this way, the background interference to foreground spacecraft depth completion is effectively avoided.
Transmit Design for Joint MIMO Radar and Multiuser Communications with Transmit Covariance Constraint
With this constraint, we formulate and solve the signal-to-interference-plus-noise ratio (SINR) balancing problem for multiuser transmit beamforming via convex optimization.
Diverse Part Discovery: Occluded Person Re-identification with Part-Aware Transformer
To address these issues, we propose a novel end-to-end Part-Aware Transformer (PAT) for occluded person Re-ID through diverse part discovery via a transformer encoderdecoder architecture, including a pixel context based transformer encoder and a part prototype based transformer decoder.
Ranked #18 on
Person Re-Identification
on Occluded-DukeMTMC
Newly observed $X(4630)$: a new charmoniumlike molecule
Very recently, the LHCb Collaboration at the Large Hadron Collider at CERN observed new resonance $X(4630)$.
High Energy Physics - Phenomenology
Hidden-charm pentaquarks with triple strangeness due to the $Ω_{c}^{(*)}\bar{D}_s^{(*)}$ interactions
Our results suggest that the $\Omega_{c}\bar D_s^*$ state with $J^P={3}/{2}^{-}$ and the $\Omega_{c}^{*}\bar D_s^*$ state with $J^P={5}/{2}^{-}$ can be recommended as the candidates of the hidden-charm molecular pentaquark with triple strangeness.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Universal behavior of mass gaps existing in the single heavy baryon family
The mass gaps existing in the discovered single heavy flavor baryons are analyzed, which show some universal behaviors.
High Energy Physics - Phenomenology
Time-Series Regeneration with Convolutional Recurrent Generative Adversarial Network for Remaining Useful Life Estimation
Out of this consideration, an enhanced RUL framework focusing on data self-generation is put forward for both non-cyclic and cyclic degradation patterns for the first time.
Unambiguous Delay-Doppler Recovery from Random Phase Coded Pulses
Our method encodes each pulse with a random phase, varying from pulse to pulse, and then processes the received samples jointly to resolve the range ambiguity.
Multi-Features Guidance Network for partial-to-partial point cloud registration
In the correspondences credibility computation module, based on the conflicted relationship between the features matching matrix and the coordinates matching matrix, we score the reliability for each correspondence, which can reduce the impact of mismatched or non-matched points.
Establishing the first hidden-charm pentaquark with strangeness
We study the $P_{cs}(4459)^0$ recently observed by LHCb using the method of QCD sum rules.
High Energy Physics - Phenomenology High Energy Physics - Experiment
Neural Network-based Automatic Factor Construction
This paper proposes Neural Network-based Automatic Factor Construction (NNAFC), a tailored neural network framework that can automatically construct diversified financial factors based on financial domain knowledge and a variety of neural network structures.
Deep Learning Based Defect Detection for Solder Joints on Industrial X-Ray Circuit Board Images
With some advanced algorithms, the new technologies are expected to control the production quality based on the digital images.
FSD-10: A Dataset for Competitive Sports Content Analysis
To promote the research on action recognition from competitive sports video clips, we introduce a Figure Skating Dataset (FSD-10) for finegrained sports content analysis.
PENet: Object Detection using Points Estimation in Aerial Images
Aerial imagery has been increasingly adopted in mission-critical tasks, such as traffic surveillance, smart cities, and disaster assistance.
Alpha Discovery Neural Network based on Prior Knowledge
This paper proposes Alpha Discovery Neural Network (ADNN), a tailored neural network structure which can automatically construct diversified financial technical indicators based on prior knowledge.
Multiple Learning for Regression in big data
Results showed our approaches can achieve closed-form solutions of multiple models at the cost of half training time of the traditional methods for a single model.
Color Recognition for Rubik's Cube Robot
We finally design a Rubik's cube robot and construct a dataset to illustrate the efficiency and effectiveness of our online methods and to indicate the ineffectiveness of offline method by color drifting in our dataset.
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Perceptual Visual Interactive Learning
Supervised learning methods are widely used in machine learning.
A Sparse Graph-Structured Lasso Mixed Model for Genetic Association with Confounding Correction
We proposed the sparse graph-structured linear mixed model (sGLMM) that can incorporate the relatedness information from traits in a dataset with confounding correction.
A New Medical Diagnosis Method Based on Z-Numbers
In this paper, a new decision making methodology based on Z-numbers is presented.
