Search Results for author:
Found 294 papers, 85 papers with code
Sociolectal Analysis of Pretrained Language Models
Using data from English cloze tests, in which subjects also self-reported their gender, age, education, and race, we examine performance differences of pretrained language models across demographic groups, defined by these (protected) attributes.
Data Efficacy for Language Model Training
This work introduces a general paradigm, DELT, for considering data efficacy in LM training, which highlights the significance of training data organization.
A Novel Large Vision Foundation Model (LVFM)-based Approach for Generating High-Resolution Canopy Height Maps in Plantations for Precision Forestry Management
Accurate, cost-effective monitoring of plantation aboveground biomass (AGB) is crucial for supporting local livelihoods and carbon sequestration initiatives like the China Certified Emission Reduction (CCER) program.
Gradients of unitary optical neural networks using parameter-shift rule
This paper explores the application of the parameter-shift rule (PSR) for computing gradients in unitary optical neural networks (UONNs).
LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation
Automation of analog topology design is crucial due to customized requirements of modern applications with heavily manual engineering efforts.
OmniDRCA: Parallel Speech-Text Foundation Model via Dual-Resolution Speech Representations and Contrastive Alignment
This paper presents OmniDRCA, a parallel speech-text foundation model based on joint autoregressive modeling, featuring dual-resolution speech representations and contrastive cross-modal alignment.
Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
In this work, we introduce the Qwen3 Embedding series, a significant advancement over its predecessor, the GTE-Qwen series, in text embedding and reranking capabilities, built upon the Qwen3 foundation models.
MiMo-VL Technical Report
We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning.
TRIDENT: Enhancing Large Language Model Safety with Tri-Dimensional Diversified Red-Teaming Data Synthesis
Large Language Models (LLMs) excel in various natural language processing tasks but remain vulnerable to generating harmful content or being exploited for malicious purposes.
EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions
Large language models (LLMs) frequently refuse to respond to pseudo-malicious instructions: semantically harmless input queries triggering unnecessary LLM refusals due to conservative safety alignment, significantly impairing user experience.
DISTA-Net: Dynamic Closely-Spaced Infrared Small Target Unmixing
Resolving closely-spaced small targets in dense clusters presents a significant challenge in infrared imaging, as the overlapping signals hinder precise determination of their quantity, sub-pixel positions, and radiation intensities.
Understanding and Mitigating Overrefusal in LLMs from an Unveiling Perspective of Safety Decision Boundary
This approach not only provides a more precise and interpretable view of model safety decisions but also seamlessly extends to multilingual scenarios. We have explored the safety decision boundaries of various LLMs and construct the MORBench evaluation set to facilitate robust assessment of model safety and helpfulness across multiple languages.
$\text{R}^2\text{ec}$: Towards Large Recommender Models with Reasoning
To address these issues, we propose \name, a unified large recommender model with intrinsic reasoning capabilities.
Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities
Surprisingly, we find that satellite imagery, publicly available across the globe, contains rich urban semantic signals to support high-quality OD flow generation, with over 98\% expressiveness of traditional multisource hard-to-collect urban sociodemographic, economics, land use, and point of interest data.
EAVIT: Efficient and Accurate Human Value Identification from Text data via LLMs
The rapid evolution of large language models (LLMs) has revolutionized various fields, including the identification and discovery of human values within text data.
Towards Budget-Friendly Model-Agnostic Explanation Generation for Large Language Models
With Large language models (LLMs) becoming increasingly prevalent in various applications, the need for interpreting their predictions has become a critical challenge.
Beyond Modality Collapse: Representations Blending for Multimodal Dataset Distillation
Multimodal Dataset Distillation (MDD) seeks to condense large-scale image-text datasets into compact surrogates while retaining their effectiveness for cross-modal learning.
UrbanMind: Urban Dynamics Prediction with Multifaceted Spatial-Temporal Large Language Models
Understanding and predicting urban dynamics is crucial for managing transportation systems, optimizing urban planning, and enhancing public services.
Large Language Model Psychometrics: A Systematic Review of Evaluation, Validation, and Enhancement
The rapid advancement of large language models (LLMs) has outpaced traditional evaluation methodologies.
MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining
We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages.
A Survey on 3D Reconstruction Techniques in Plant Phenotyping: From Classical Methods to Neural Radiance Fields (NeRF), 3D Gaussian Splatting (3DGS), and Beyond
Through this review, we aim to provide insights into how these diverse 3D reconstruction techniques can be effectively leveraged for automated and high-throughput plant phenotyping, contributing to the next generation of agricultural technology.
An Accelerated Camera 3DMA Framework for Efficient Urban GNSS Multipath Estimation
Robust GNSS positioning in urban environments is still plagued by multipath effects, particularly due to the complex signal propagation induced by ubiquitous surfaces with varied radio frequency reflectivities.
Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models
We propose a double-channel design that leverages pseudorandom error-correcting codes to encode the random seed required for watermark pseudorandomization, achieving performance-lossless watermarking under a fixed watermark key and overcoming key management challenges.
CoT-RAG: Integrating Chain of Thought and Retrieval-Augmented Generation to Enhance Reasoning in Large Language Models
Chain-of-thought (CoT) reasoning boosts large language models' (LLMs) performance on complex tasks but faces two key limitations: a lack of reliability when solely relying on LLM-generated reasoning chains and interference from natural language reasoning steps with the models' inference process, also known as the inference logic of LLMs.
MAIN: Mutual Alignment Is Necessary for instruction tuning
Instruction tuning has enabled large language models (LLMs) to achieve remarkable performance, but its success heavily depends on the availability of large-scale, high-quality instruction-response pairs.
REWARD CONSISTENCY: Improving Multi-Objective Alignment from a Data-Centric Perspective
Multi-objective preference alignment in language models often encounters a challenging trade-off: optimizing for one human preference (e. g., helpfulness) frequently compromises others (e. g., harmlessness) due to the inherent conflicts between competing objectives.
MIEB: Massive Image Embedding Benchmark
We introduce the Massive Image Embedding Benchmark (MIEB) to evaluate the performance of image and image-text embedding models across the broadest spectrum to date.
The Tenth NTIRE 2025 Efficient Super-Resolution Challenge Report
This paper presents a comprehensive review of the NTIRE 2025 Challenge on Single-Image Efficient Super-Resolution (ESR).
Outage Probability Analysis for OTFS with Finite Blocklength
Orthogonal time frequency space (OTFS) modulation is widely acknowledged as a prospective waveform for future wireless communication networks. To provide insights for the practical system design, this paper analyzes the outage probability of OTFS modulation with finite blocklength. To begin with, we present the system model and formulate the analysis of outage probability for OTFS with finite blocklength as an equivalent problem of calculating the outage probability with finite blocklength over parallel additive white Gaussian noise (AWGN) channels. Subsequently, we apply the equivalent noise approach to derive a lower bound on the outage probability of OTFS with finite blocklength under both average power allocation and water-filling power allocation strategies, respectively. Finally, the lower bounds of the outage probability are determined using the Monte-Carlo method for the two power allocation strategies. The impact of the number of resolvable paths and coding rates on the outage probability is analyzed, and the simulation results are compared with the theoretical lower bounds.
Apt-Serve: Adaptive Request Scheduling on Hybrid Cache for Scalable LLM Inference Serving
In this paper, we introduce Apt-Serve, a scalable framework designed to enhance effective throughput in LLM inference serving.
Emergency Communication: OTFS-Based Semantic Transmission with Diffusion Noise Suppression
However, the complex channel conditions in high-speed mobile scenarios significantly impact the reliability and efficiency of traditional communication systems.
Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation
However, existing DGSS methods often rely exclusively on either VFMs or VLMs, overlooking their complementary strengths.
CamoSAM2: Motion-Appearance Induced Auto-Refining Prompts for Video Camouflaged Object Detection
The Segment Anything Model 2 (SAM2), a prompt-guided video foundation model, has remarkably performed in video object segmentation, drawing significant attention in the community.
Ranked #2 on
Camouflaged Object Segmentation
on MoCA-Mask
MuseFace: Text-driven Face Editing via Diffusion-based Mask Generation Approach
The Text-to-Mask diffusion model provides \textit{diversity} and \textit{flexibility} to the framework, while the semantic-aware face editing model ensures \textit{controllability} of the framework.
Object Isolated Attention for Consistent Story Visualization
Open-ended story visualization is a challenging task that involves generating coherent image sequences from a given storyline.
CTSAC: Curriculum-Based Transformer Soft Actor-Critic for Goal-Oriented Robot Exploration
With the increasing demand for efficient and flexible robotic exploration solutions, Reinforcement Learning (RL) is becoming a promising approach in the field of autonomous robotic exploration.
Enhanced Multi-Tuple Extraction for Alloys: Integrating Pointer Networks and Augmented Attention
Extracting high-quality structured information from scientific literature is crucial for advancing material design through data-driven methods.
FEA-Bench: A Benchmark for Evaluating Repository-Level Code Generation for Feature Implementation
Implementing new features in repository-level codebases is a crucial application of code generation models.
M$^3$amba: CLIP-driven Mamba Model for Multi-modal Remote Sensing Classification
Multi-modal fusion holds great promise for integrating information from different modalities.
Computational Efficiency
Hyperspectral Image Classification
+2
SynGraph: A Dynamic Graph-LLM Synthesis Framework for Sparse Streaming User Sentiment Modeling
In this paper, we introduce SynGraph, a novel framework designed to address data sparsity in sentiment analysis on streaming reviews.
Process-based Self-Rewarding Language Models
Human-annotated preference data is used for training to further improve LLMs' performance, which is constrained by the upper limit of human performance.
IterPref: Focal Preference Learning for Code Generation via Iterative Debugging
Preference learning enhances Code LLMs beyond supervised fine-tuning by leveraging relative quality comparisons.
C-LoRA: Continual Low-Rank Adaptation for Pre-trained Models
Low-Rank Adaptation (LoRA) is an efficient fine-tuning method that has been extensively applied in areas such as natural language processing and computer vision.
TabulaTime: A Novel Multimodal Deep Learning Framework for Advancing Acute Coronary Syndrome Prediction through Environmental and Clinical Data Integration
We introduce TabulaTime, a multimodal deep learning framework that enhances ACS risk prediction by combining clinical risk factors with air pollution data.
External Large Foundation Model: How to Efficiently Serve Trillions of Parameters for Online Ads Recommendation
Second, large-volume data arrive in a streaming mode with data distributions dynamically shifting, as new users/ads join and existing users/ads leave the system.
Towards Text-Image Interleaved Retrieval
In this work, we introduce the text-image interleaved retrieval (TIIR) task, where the query and document are interleaved text-image sequences, and the model is required to understand the semantics from the interleaved context for effective retrieval.
CCJA: Context-Coherent Jailbreak Attack for Aligned Large Language Models
We define jailbreak attacks as an optimization problem within the embedding space of masked language models.
Accelerating Anchors via Specialization and Feature Transformation
Anchors is a popular local model-agnostic explanation technique whose applicability is limited by its computational inefficiency.
Enhancing Reasoning to Adapt Large Language Models for Domain-Specific Applications
This paper presents SOLOMON, a novel Neuro-inspired Large Language Model (LLM) Reasoning Network architecture that enhances the adaptability of foundation models for domain-specific applications.
Generative Psycho-Lexical Approach for Constructing Value Systems in Large Language Models
Despite growing efforts in evaluating, understanding, and aligning LLM values, a psychologically grounded LLM value system remains underexplored.
Personalized Interpolation: An Efficient Method to Tame Flexible Optimization Window Estimation
In the realm of online advertising, optimizing conversions is crucial for delivering relevant products to users and enhancing business outcomes.
Study on a Fast Solver for Combined Field Integral Equations of 3D Conducting Bodies Based on Graph Neural Networks
In this paper, we present a graph neural networks (GNNs)-based fast solver (GraphSolver) for solving combined field integral equations (CFIEs) of 3D conducting bodies.
RSAR: Restricted State Angle Resolver and Rotated SAR Benchmark
Our approach can effectively improve the performance of existing state-of-the-art weakly supervised methods and even surpasses fully supervised models on existing optical benchmarks (i. e., DOTA-v1. 0 dataset).
EpiCoder: Encompassing Diversity and Complexity in Code Generation
Effective instruction tuning is indispensable for optimizing code LLMs, aligning model behavior with user expectations and enhancing model performance in real-world applications.
SEEN-DA: SEmantic ENtropy guided Domain-aware Attention for Domain Adaptive Object Detection
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain.
Bridging Modalities: Improving Universal Multimodal Retrieval by Multimodal Large Language Models
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
JTD-UAV: MLLM-Enhanced Joint Tracking and Description Framework for Anti-UAV Systems
To benchmark this task, we introduce the TDUAV dataset, the largest dataset for joint UAV tracking and intent understanding, featuring 1, 328 challenging video sequences, over 163K annotated thermal frames, and 3K VQA pairs.
GME: Improving Universal Multimodal Retrieval by Multimodal LLMs
Last, we provide in-depth analyses of model scaling and training strategies, and perform ablation studies on both the model and synthetic data.
MMLU-CF: A Contamination-free Multi-task Language Understanding Benchmark
This benchmark reassesses LLMs' understanding of world knowledge by averting both unintentional and malicious data leakage.
PointTalk: Audio-Driven Dynamic Lip Point Cloud for 3D Gaussian-based Talking Head Synthesis
Furthermore, we integrate the audio-point enhancement module, which not only ensures the synchronization of the audio signal with the corresponding lip point cloud within the feature space, but also facilitates a deeper understanding of the interrelations among cross-modal conditional features.
Moderating the Generalization of Score-based Generative Model
To fill this gap, we first examine the current 'gold standard' in Machine Unlearning (MU), i. e., re-training the model after removing the undesirable training data, and find it does not work in SGMs.
InfinityDrive: Breaking Time Limits in Driving World Models
Comprehensive experiments in multiple datasets validate InfinityDrive's ability to generate complex and varied scenarios, highlighting its potential as a next-generation driving world model built for the evolving demands of autonomous driving.
Neural-Network-Enhanced Metalens Camera for High-Definition, Dynamic Imaging in the Long-Wave Infrared Spectrum
To provide a lightweight and cost-effective solution for the long-wave infrared imaging using a singlet, we develop a camera by integrating a High-Frequency-Enhancing Cycle-GAN neural network into a metalens imaging system.
Multitask Learning for SAR Ship Detection with Gaussian-Mask Joint Segmentation
Detecting ships in synthetic aperture radar (SAR) images is challenging due to strong speckle noise, complex surroundings, and varying scales.
Velocitune: A Velocity-based Dynamic Domain Reweighting Method for Continual Pre-training
To evaluate the effectiveness of Velocitune, we conduct experiments in a reasoning-focused dataset with CodeLlama, as well as in a corpus specialised for system command generation with Llama3 and Mistral.
LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits
Existing automation efforts using methods like Bayesian Optimization (BO) and Reinforcement Learning (RL) are sub-optimal and costly to generalize across different topologies and technology nodes.
BPO: Towards Balanced Preference Optimization between Knowledge Breadth and Depth in Alignment
Building on this, we further propose Balanced Preference Optimization (BPO), designed to dynamically augment the knowledge depth of each sample.
Legal Evalutions and Challenges of Large Language Models
In this paper, we review legal testing methods based on Large Language Models (LLMs), using the OPENAI o1 model as a case study to evaluate the performance of large models in applying legal provisions.
The Backpropagation of the Wave Network
This paper provides an in-depth analysis of Wave Network, a novel token representation method derived from the Wave Network, designed to capture both global and local semantics of input text through wave-inspired complex vectors.
Neuro-Symbolic AI: Explainability, Challenges, and Future Trends
Explainability is an essential reason limiting the application of neural networks in many vital fields.
Bridging the Gap: Representation Spaces in Neuro-Symbolic AI
Neuro-symbolic AI is an effective method for improving the overall performance of AI models by combining the advantages of neural networks and symbolic learning.
Wave Network: An Ultra-Small Language Model
We propose an innovative token representation and update method in a new ultra-small language model: the Wave network.
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
To address these communication cost issues and increase the performance of pre-trained model adaptation in FL, we propose an innovative model interpolation-based local training technique called ``Local Superior Soups.''
Robust Graph Neural Networks for Stability Analysis in Dynamic Networks
In the current context of accelerated globalization and digitalization, the complexity and uncertainty of financial markets are increasing, and the identification and prevention of economic risks have become a key link in maintaining the stability of the financial system.
Self-Supervised Graph Neural Networks for Enhanced Feature Extraction in Heterogeneous Information Networks
This paper explores the applications and challenges of graph neural networks (GNNs) in processing complex graph data brought about by the rapid development of the Internet.
ConLUX: Concept-Based Local Unified Explanations
With the rapid advancements of various machine learning models, there is a significant demand for model-agnostic explanation techniques, which can explain these models across different architectures.
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
Domain adaptive object detection (DAOD) aims to generalize detectors trained on an annotated source domain to an unlabelled target domain.
SurgicalGS: Dynamic 3D Gaussian Splatting for Accurate Robotic-Assisted Surgical Scene Reconstruction
Accurate 3D reconstruction of dynamic surgical scenes from endoscopic video is essential for robotic-assisted surgery.
IntrinsicVoice: Empowering LLMs with Intrinsic Real-time Voice Interaction Abilities
Current methods of building LLMs with voice interaction capabilities rely heavily on explicit text autoregressive generation before or during speech response generation to maintain content quality, which unfortunately brings computational overhead and increases latency in multi-turn interactions.
SAFE: Semantic Adaptive Feature Extraction with Rate Control for 6G Wireless Communications
Most current Deep Learning-based Semantic Communication (DeepSC) systems are designed and trained exclusively for particular single-channel conditions, which restricts their adaptability and overall bandwidth utilization.
Evaluation of OpenAI o1: Opportunities and Challenges of AGI
-Impressive performance in chip design tasks, outperforming specialized models in areas such as EDA script generation and bug analysis.
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
Specifically, we introduce a novel method that employs dynamic and directed weight adjustment techniques to modulate the synthesis process, thereby maximizing the representativeness and diversity of each synthetic instance.
Cascade Prompt Learning for Vision-Language Model Adaptation
Prompt learning has surfaced as an effective approach to enhance the performance of Vision-Language Models (VLMs) like CLIP when applied to downstream tasks.
FMDLlama: Financial Misinformation Detection based on Large Language Models
The emergence of social media has made the spread of misinformation easier.
Measuring Human and AI Values Based on Generative Psychometrics with Large Language Models
Human values and their measurement are long-standing interdisciplinary inquiry.
Multimodality Adaptive Transformer and Mutual Learning for Unsupervised Domain Adaptation Vehicle Re-Identification
Unsupervised Domain Adaptation Vehicle Re-Identification (UDA vehicle re-ID) aims to enable the model trained in the source domain dataset to adapt to the target domain data and obtain accurate re-identification results, which has received widespread attention due to its practicality in the field of intelligent transportation systems.
Adaptive Transformer Modelling of Density Function for Nonparametric Survival Analysis
Survival analysis holds a crucial role across diverse disciplines, such as economics, engineering and healthcare.
SPDiffusion: Semantic Protection Diffusion for Multi-concept Text-to-image Generation
We found that attribute confusion occurs when a certain region of the latent features attend to multiple or incorrect prompt tokens.
RGDA-DDI: Residual graph attention network and dual-attention based framework for drug-drug interaction prediction
In addition, a dual-attention based feature fusion block is constructed to learn local joint interaction representations.
A novel k-generation propagation model for cyber risk and its application to cyber insurance
The frequent occurrence of cyber risks and their serious economic consequences have created a growth market for cyber insurance.
ICFRNet: Image Complexity Prior Guided Feature Refinement for Real-time Semantic Segmentation
In this paper, we leverage image complexity as a prior for refining segmentation features to achieve accurate real-time semantic segmentation.
Breaking Class Barriers: Efficient Dataset Distillation via Inter-Class Feature Compensator
This leads to inefficient utilization of the distillation budget and oversight of inter-class feature distributions, which ultimately limits the effectiveness and efficiency, as demonstrated in our analysis.
FSSC: Federated Learning of Transformer Neural Networks for Semantic Image Communication
In this paper, we address the problem of image semantic communication in a multi-user deployment scenario and propose a federated learning (FL) strategy for a Swin Transformer-based semantic communication system (FSSC).
mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrieval
We first introduce a text encoder (base size) enhanced with RoPE and unpadding, pre-trained in a native 8192-token context (longer than 512 of previous multilingual encoders).
Revising the Problem of Partial Labels from the Perspective of CNNs' Robustness
These remarkable achievements are greatly attributed to the support of extensive datasets with precise labels.
LaMAGIC: Language-Model-based Topology Generation for Analog Integrated Circuits
To this end, we introduce LaMAGIC, a pioneering language model-based topology generation model that leverages supervised finetuning for automated analog circuit design.
GDDS: A Single Domain Generalized Defect Detection Frame of Open World Scenario using Gather and Distribute Domain-shift Suppression Network
Therefore, we propose the Gather and Distribute Domain shift Suppression Network (GDDS).
Positive and Unlabeled Data: Model, Estimation, Inference, and Classification
This study introduces a new approach to addressing positive and unlabeled (PU) data through the double exponential tilting model (DETM).
Detection-Triggered Recursive Impact Mitigation against Secondary False Data Injection Attacks in Microgrids
The proposed mitigation method can work even in the worst case where all communication links are under SFDIAs and only require extra current sensors.
Potential of Multimodal Large Language Models for Data Mining of Medical Images and Free-text Reports
Our experimental results demonstrated that Gemini-series models excelled in report generation and lesion detection but faces challenges in disease classification and anatomical localization.
Gradient-Mask Tuning Elevates the Upper Limits of LLM Performance
Large language models (LLMs) have revolutionized lots of fields of research.
Urban-Focused Multi-Task Offline Reinforcement Learning with Contrastive Data Sharing
MODA addresses the challenges of data scarcity and heterogeneity in a multi-task urban setting through Contrastive Data Sharing among tasks.
CityBench: Evaluating the Capabilities of Large Language Models for Urban Tasks
The challenge in constructing a systematic evaluation benchmark for urban research lies in the diversity of urban data, the complexity of application scenarios and the highly dynamic nature of the urban environment.
GraphKAN: Enhancing Feature Extraction with Graph Kolmogorov Arnold Networks
Massive number of applications involve data with underlying relationships embedded in non-Euclidean space.
Video Frame Interpolation for Polarization via Swin-Transformer
Video Frame Interpolation (VFI) has been extensively explored and demonstrated, yet its application to polarization remains largely unexplored.
AutoSurvey: Large Language Models Can Automatically Write Surveys
This paper introduces AutoSurvey, a speedy and well-organized methodology for automating the creation of comprehensive literature surveys in rapidly evolving fields like artificial intelligence.
Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification
In the medical field, managing high-dimensional massive medical imaging data and performing reliable medical analysis from it is a critical challenge, especially in resource-limited environments such as remote medical facilities and mobile devices.
ValueBench: Towards Comprehensively Evaluating Value Orientations and Understanding of Large Language Models
This work introduces ValueBench, the first comprehensive psychometric benchmark for evaluating value orientations and value understanding in LLMs.
CIRCUITSYNTH: Leveraging Large Language Models for Circuit Topology Synthesis
Circuit topology generation plays a crucial role in the design of electronic circuits, influencing the fundamental functionality of the circuit.
Magnetic Resonance Image Processing Transformer for General Accelerated Image Reconstruction
Recent advancements in deep learning have enabled the development of generalizable models that achieve state-of-the-art performance across various imaging tasks.
Overcoming Data and Model Heterogeneities in Decentralized Federated Learning via Synthetic Anchors
Conventional Federated Learning (FL) involves collaborative training of a global model while maintaining user data privacy.
E2GNN: Efficient Graph Neural Network Ensembles for Semi-Supervised Classification
Next, instead of directly combing their outputs for label inference, we train a simple multi-layer perceptron--MLP model to mimic their predictions on both labeled and unlabeled nodes.
A Novel Spike Transformer Network for Depth Estimation from Event Cameras via Cross-modality Knowledge Distillation
This necessitates the development of innovative, spike-aware algorithms tailored for event cameras, a task compounded by the irregularity, continuity, noise, and spatial and temporal characteristics inherent in spiking data. Harnessing the strong generalization capabilities of transformer neural networks for spatiotemporal data, we propose a purely spike-driven spike transformer network for depth estimation from spiking camera data.
SpeechAlign: Aligning Speech Generation to Human Preferences
However, the integration of human feedback to align speech outputs to human preferences is often neglected.
DSGNN: A Dual-View Supergrid-Aware Graph Neural Network for Regional Air Quality Estimation
To this end, we propose a Dual-view Supergrid-aware Graph Neural Network (DSGNN) for regional air quality estimation, which can model the spatial dependencies of distant grid regions from dual views (i. e., satellite-derived aerosol optical depth (AOD) and meteorology).
CSST Strong Lensing Preparation: a Framework for Detecting Strong Lenses in the Multi-color Imaging Survey by the China Survey Space Telescope (CSST)
To overcome these challenges, we have developed a framework based on a hierarchical visual Transformer with a sliding window technique to search for strong lensing systems within entire images.
General LLMs as Instructors for Domain-Specific LLMs: A Sequential Fusion Method to Integrate Extraction and Editing
To tackle this challenge, we introduce a Sequential Fusion method to integrate knowledge from complex contexts into LLMs.
GCN-DevLSTM: Path Development for Skeleton-Based Action Recognition
Skeleton-based action recognition (SAR) in videos is an important but challenging task in computer vision.
PE-GPT: A Physics-Informed Interactive Large Language Model for Power Converter Modulation Design
This paper proposes PE-GPT, a custom-tailored large language model uniquely adapted for power converter modulation design.
Accurate and Data-Efficient Micro-XRD Phase Identification Using Multi-Task Learning: Application to Hydrothermal Fluids
Traditional analysis of highly distorted micro-X-ray diffraction ({\mu}-XRD) patterns from hydrothermal fluid environments is a time-consuming process, often requiring substantial data preprocessing and labeled experimental data.
Two-sided Acoustic Metascreen for Broadband and Individual Reflection and Transmission Control
Acoustic wave modulation plays a pivotal role in various applications, including sound-field reconstruction, wireless communication, and particle manipulation, among others.
ArgMed-Agents: Explainable Clinical Decision Reasoning with LLM Disscusion via Argumentation Schemes
We construct a formal model of ArgMed-Agents and present conjectures for theoretical guarantees.
Fine-grainedly Synthesize Streaming Data Based On Large Language Models With Graph Structure Understanding For Data Sparsity
Due to the sparsity of user data, sentiment analysis on user reviews in e-commerce platforms often suffers from poor performance, especially when faced with extremely sparse user data or long-tail labels.
PromptKD: Unsupervised Prompt Distillation for Vision-Language Models
To our best knowledge, we are the first to (1) perform unsupervised domain-specific prompt-driven knowledge distillation for CLIP, and (2) establish a practical pre-storing mechanism of text features as shared class vectors between teacher and student.
Ranked #1 on
Prompt Engineering
on Oxford-IIIT Pet Dataset
Explicit Motion Handling and Interactive Prompting for Video Camouflaged Object Detection
The prompt fed to the motion stream is learned by supervising optical flow in a self-supervised manner.
A Literature Review of Literature Reviews in Pattern Analysis and Machine Intelligence
This paper presents a thorough analysis of these literature reviews within the PAMI field, and tries to address three core research questions: (1) What are the prevalent structural and statistical characteristics of PAMI literature reviews?
AnyGPT: Unified Multimodal LLM with Discrete Sequence Modeling
We introduce AnyGPT, an any-to-any multimodal language model that utilizes discrete representations for the unified processing of various modalities, including speech, text, images, and music.
Knowledge Graph Assisted Automatic Sports News Writing
In this paper, we present a novel method for automatically generating sports news, which employs a unique algorithm that extracts pivotal moments from live text broadcasts and uses them to create an initial draft of the news.
Dynamic Patch-aware Enrichment Transformer for Occluded Person Re-Identification
To facilitate the seamless integration of global classification features with the finely detailed local features selected by DPSM, we introduce a novel feature blending module (FBM).
Ranked #10 on
Person Re-Identification
on Occluded-DukeMTMC
ICDPO: Effectively Borrowing Alignment Capability of Others via In-context Direct Preference Optimization
Large Language Models (LLMs) rely on Human Preference Alignment (HPA) to ensure the generation of safe content.
Partially Recentralization Softmax Loss for Vision-Language Models Robustness
However, it has been shown that multimodal NLP are vulnerable to adversarial attacks, where the outputs of a model can be dramatically changed by a perturbation to the input.
ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
This work focuses on the target shift problem in a regression setting (Zhang et al., 2013; Nguyen et al., 2016).
SpeechGPT-Gen: Scaling Chain-of-Information Speech Generation
It comprises an autoregressive model based on LLM for semantic information modeling and a non-autoregressive model employing flow matching for perceptual information modeling.
CLIP Model for Images to Textual Prompts Based on Top-k Neighbors
Text-to-image synthesis, a subfield of multimodal generation, has gained significant attention in recent years.
UV-SAM: Adapting Segment Anything Model for Urban Village Identification
Urban villages, defined as informal residential areas in or around urban centers, are characterized by inadequate infrastructures and poor living conditions, closely related to the Sustainable Development Goals (SDGs) on poverty, adequate housing, and sustainable cities.
Weiss-Weinstein bound of frequency estimation error for very weak GNSS signals
Tightness remains the center quest in all modern estimation bounds.
SpeechAgents: Human-Communication Simulation with Multi-Modal Multi-Agent Systems
In this paper, we propose SpeechAgents, a multi-modal LLM based multi-agent system designed for simulating human communication.
TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing
Representation learning frameworks in unlabeled time series have been proposed for medical signal processing.
Understanding LLMs: A Comprehensive Overview from Training to Inference
Low-cost training and deployment of LLMs represent the future development trend.
Efficient Sparse Least Absolute Deviation Regression with Differential Privacy
To fast solve the non-smooth loss under a given privacy budget, we develop a Fast Robust And Privacy-Preserving Estimation (FRAPPE) algorithm for least absolute deviation regression.
HEAP: Unsupervised Object Discovery and Localization with Contrastive Grouping
Further, to ensure the distinguishability among various regions, we introduce a region-level contrastive clustering loss to pull closer similar regions across images.
WaveCoder: Widespread And Versatile Enhancement For Code Large Language Models By Instruction Tuning
Recent work demonstrates that, after instruction tuning, Code Large Language Models (Code LLMs) can obtain impressive capabilities to address a wide range of code-related tasks.
TMID: A Comprehensive Real-world Dataset for Trademark Infringement Detection in E-Commerce
Annually, e-commerce platforms incur substantial financial losses due to trademark infringements, making it crucial to identify and mitigate potential legal risks tied to merchant information registered to the platforms.
Physics Inspired Criterion for Pruning-Quantization Joint Learning
Pruning-quantization joint learning always facilitates the deployment of deep neural networks (DNNs) on resource-constrained edge devices.
Automated interpretation of congenital heart disease from multi-view echocardiograms
Our video-based model can diagnose with an accuracy of 93. 9\% (binary classification), and 92. 1\% (3-class classification) in a collected 2D video testing set, which does not need key-frame selection and view annotation in testing.
CLIPC8: Face liveness detection algorithm based on image-text pairs and contrastive learning
To tackle this issue, we propose a face liveness detection method based on image-text pairs and contrastive learning, dividing liveness attack problems in the financial field into eight categories and using text information to describe the images of these eight types of attacks.
SiGeo: Sub-One-Shot NAS via Information Theory and Geometry of Loss Landscape
Neural Architecture Search (NAS) has become a widely used tool for automating neural network design.
Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning
Dataset pruning aims to construct a coreset capable of achieving performance comparable to the original, full dataset.
LDConv: Linear deformable convolution for improving convolutional neural networks
In response to the above questions, the Linear Deformable Convolution (LDConv) is explored in this work, which gives the convolution kernel an arbitrary number of parameters and arbitrary sampled shapes to provide richer options for the trade-off between network overhead and performance.
Learning to Reconstruct Accelerated MRI Through K-space Cold Diffusion without Noise
In this paper, we propose a k-space cold diffusion model that performs image degradation and restoration in k-space without the need for Gaussian noise.
Rankitect: Ranking Architecture Search Battling World-class Engineers at Meta Scale
In industry system, such as ranking system in Meta, it is unclear whether NAS algorithms from the literature can outperform production baselines because of: (1) scale - Meta ranking systems serve billions of users, (2) strong baselines - the baselines are production models optimized by hundreds to thousands of world-class engineers for years since the rise of deep learning, (3) dynamic baselines - engineers may have established new and stronger baselines during NAS search, and (4) efficiency - the search pipeline must yield results quickly in alignment with the productionization life cycle.
Holistic Evaluation of GPT-4V for Biomedical Imaging
GPT-4V represents a breakthrough in artificial general intelligence (AGI) for computer vision, with applications in the biomedical domain.
Reconfigurable Intelligent Surface & Edge -- An Introduction of an EM manipulation structure on obstacles' edge
In this paper, Reconfigurable Intelligent Surface & Edge (RISE) is proposed to extend RIS' abilities of reflection and refraction over surfaces to diffraction around obstacles' edge for better adaptation to specific coverage scenarios.
Image Recognition of Oil Leakage Area Based on Logical Semantic Discrimination
The process begins with histogram equalization to enhance the original image, followed by the use of Mask RCNN to identify the preliminary positions and outlines of oil tanks, the ground, and areas of potential oil contamination.
Map-assisted TDOA Localization Enhancement Based On CNN
For signal processing related to localization technologies, non line of sight (NLOS) multipaths have a significant impact on the localization error level.
TBDLNet: a network for classifying multidrug-resistant and drug-sensitive tuberculosis
Five indexes are selected in this paper, which are accuracy, sensitivity, precision, F1-score, and specificity.
Self-supervised Fetal MRI 3D Reconstruction Based on Radiation Diffusion Generation Model
Finally, the experimental results on real-world fetal brain MRI stacks demonstrate the state-of-the-art performance of our method.
Language Models are Universal Embedders
As such cases span from English to other natural or programming languages, from retrieval to classification and beyond, it is desirable to build a unified embedding model rather than dedicated ones for each scenario.
ChatRadio-Valuer: A Chat Large Language Model for Generalizable Radiology Report Generation Based on Multi-institution and Multi-system Data
Radiology report generation, as a key step in medical image analysis, is critical to the quantitative analysis of clinically informed decision-making levels.
SpeechTokenizer: Unified Speech Tokenizer for Speech Large Language Models
Therefore, we propose SpeechTokenizer, a unified speech tokenizer for speech large language models.
Regularization by Neural Style Transfer for MRI Field-Transfer Reconstruction with Limited Data
Recent advances in MRI reconstruction have demonstrated remarkable success through deep learning-based models.
Real-time Strawberry Detection Based on Improved YOLOv5s Architecture for Robotic Harvesting in open-field environment
This study proposed a YOLOv5-based custom object detection model to detect strawberries in an outdoor environment.
Towards General Text Embeddings with Multi-stage Contrastive Learning
We present GTE, a general-purpose text embedding model trained with multi-stage contrastive learning.
Particle swarm optimization with state-based adaptive velocity limit strategy
Several adaptive VL strategies have been introduced with which the performance of PSO can be improved.
Artificial-Intelligence-Based Hybrid Extended Phase Shift Modulation for the Dual Active Bridge Converter with Full ZVS Range and Optimal Efficiency
ZVS range and efficiency are two significant performance indicators for DAB converter.
Artificial-Intelligence-Based Triple Phase Shift Modulation for Dual Active Bridge Converter with Minimized Current Stress
However, to minimize the current stress when the DAB converter is under TPS modulation, two difficulties exist in analysis process and realization process, respectively.
Towards Imbalanced Large Scale Multi-label Classification with Partially Annotated Labels
In this work, we address the issue of label imbalance and investigate how to train classifiers using partial labels in large labeling spaces.
Data-Driven Modeling with Experimental Augmentation for the Modulation Strategy of the Dual-Active-Bridge Converter
The D2EA approach is instantiated for the efficiency optimization of a hybrid modulation for neutral-point-clamped dual-active-bridge (NPC-DAB) converter.
Holistic Exploration on Universal Decompositional Semantic Parsing: Architecture, Data Augmentation, and LLM Paradigm
In this paper, we conduct a holistic exploration of the Universal Decompositional Semantic (UDS) Parsing.
Evaluating Large Language Models for Radiology Natural Language Processing
The rise of large language models (LLMs) has marked a pivotal shift in the field of natural language processing (NLP).
Collaborative Graph Neural Networks for Attributed Network Embedding
Graph neural networks (GNNs) have shown prominent performance on attributed network embedding.
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts
Firstly, the layout of existing datasets is relatively fixed and limited in the number of semantic entity categories, creating a significant gap between these datasets and the complex real-world scenarios.
Joint Service Caching, Communication and Computing Resource Allocation in Collaborative MEC Systems: A DRL-based Two-timescale Approach
Meeting the strict Quality of Service (QoS) requirements of terminals has imposed a signiffcant challenge on Multiaccess Edge Computing (MEC) systems, due to the limited multidimensional resources.
Early Autism Diagnosis based on Path Signature and Siamese Unsupervised Feature Compressor
Specifically, we propose a Siamese verification framework to extend the scarce data, and an unsupervised compressor to alleviate data imbalance by extracting key features.
A generic self-supervised learning (SSL) framework for representation learning from spectra-spatial feature of unlabeled remote sensing imagery
The success of SSL is heavily dependent on a pre-designed pretext task, which introduces an inductive bias into the model from a large amount of unlabelled data.
SHISRCNet: Super-resolution And Classification Network For Low-resolution Breast Cancer Histopathology Image
CF module extracts and fuses the multi-scale features of SR images for classification.
Histopathological Image Classification
image-classification
+2
Attention Hybrid Variational Net for Accelerated MRI Reconstruction
However, the drawback of these structures is that they are not fully utilizing the information from both domains (k-space and image).
Deep learning radiomics for assessment of gastroesophageal varices in people with compensated advanced chronic liver disease
Validation analysis revealed that the AUCs of DLRP were 0. 91 for GEV (95% CI 0. 90 to 0. 93, p < 0. 05) and 0. 88 for HRV (95% CI 0. 86 to 0. 89, p < 0. 01), which were significantly and robustly better than canonical risk indicators, including the value of LSM and SSM.
Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model
To guarantee the visual coherence of the generated or edited image, we introduce an inpainting and harmonizing module to guide the pre-trained diffusion model to seamlessly blend the inserted subject into the scene naturally.
ELSA: Efficient Label Shift Adaptation through the Lens of Semiparametric Models
We study the domain adaptation problem with label shift in this work.
GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks
These techniques neither preserve the semantic consistency of the original sentences when rule-based augmentations are adopted, nor preserve the syntax structure of sentences when expressing relations using seq2seq models, resulting in less diverse augmentations.
SpeechGPT: Empowering Large Language Models with Intrinsic Cross-Modal Conversational Abilities
Multi-modal large language models are regarded as a crucial step towards Artificial General Intelligence (AGI) and have garnered significant interest with the emergence of ChatGPT.
RFAConv: Innovating Spatial Attention and Standard Convolutional Operation
In this paper, we propose a new perspective on the effectiveness of spatial attention, which is that the spatial attention mechanism essentially solves the problem of convolutional kernel parameter sharing.
D-Score: A White-Box Diagnosis Score for CNNs Based on Mutation Operators
However, concerns have been raised with respect to the trustworthiness of these models: The standard testing method evaluates the performance of a model on a test set, while low-quality and insufficient test sets can lead to unreliable evaluation results, which can have unforeseeable consequences.
LMDA-Net:A lightweight multi-dimensional attention network for general EEG-based brain-computer interface paradigms and interpretability
By incorporating two novel attention modules designed specifically for EEG signals, the channel attention module and the depth attention module, LMDA-Net can effectively integrate features from multiple dimensions, resulting in improved classification performance across various BCI tasks.
A Heterogeneous Parallel Non-von Neumann Architecture System for Accurate and Efficient Machine Learning Molecular Dynamics
This paper proposes a special-purpose system to achieve high-accuracy and high-efficiency machine learning (ML) molecular dynamics (MD) calculations.
Distribution-restrained Softmax Loss for the Model Robustness
Recently, the robustness of deep learning models has received widespread attention, and various methods for improving model robustness have been proposed, including adversarial training, model architecture modification, design of loss functions, certified defenses, and so on.
Machine Learning Automated Approach for Enormous Synchrotron X-Ray Diffraction Data Interpretation
This study highlighted the importance of labeled experimental patterns on the training of DNN models to solve u-XRD mapping data from in-situ experiments involving liquid phase.
Co-Occurrence Matters: Learning Action Relation for Temporal Action Localization
Existing works in this field mainly suffer from two weaknesses: (1) They often neglect the multi-label case and only focus on temporal modeling.
PRECISION: Decentralized Constrained Min-Max Learning with Low Communication and Sample Complexities
Decentralized min-max optimization problems with domain constraints underpins many important ML applications, including multi-agent ML fairness assurance, and policy evaluations in multi-agent reinforcement learning.
Knowledge-infused Contrastive Learning for Urban Imagery-based Socioeconomic Prediction
To address such issues, in this paper, we propose a Knowledge-infused Contrastive Learning (KnowCL) model for urban imagery-based socioeconomic prediction.
ChatIE: Zero-Shot Information Extraction via Chatting with ChatGPT
Zero-shot information extraction (IE) aims to build IE systems from the unannotated text.
sMRI-PatchNet: A novel explainable patch-based deep learning network for Alzheimer's disease diagnosis and discriminative atrophy localisation with Structural MRI
Specifically, it consists of two primary components: 1) A fast and efficient explainable patch selection mechanism for determining the most discriminative patches based on computing the SHapley Additive exPlanations (SHAP) contribution to a transfer learning model for AD diagnosis on massive medical data; and 2) A novel patch-based network for extracting deep features and AD classfication from the selected patches with position embeddings to retain position information, capable of capturing the global and local information of inter- and intra-patches.
How Close is ChatGPT to Human Experts? Comparison Corpus, Evaluation, and Detection
We call the collected dataset the Human ChatGPT Comparison Corpus (HC3).
Ordinal Label Distribution Learning
Therefore, we propose a new paradigm, termed ordinal label distribution learning (OLDL).
Bring Your Own View: Graph Neural Networks for Link Prediction with Personalized Subgraph Selection
To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP.
Weakly Supervised Video Anomaly Detection Based on Cross-Batch Clustering Guidance
To enhance the discriminative power of features, we propose a batch clustering based loss to encourage a clustering branch to generate distinct normal and abnormal clusters based on a batch of data.
Stutter-TTS: Controlled Synthesis and Improved Recognition of Stuttered Speech
By fine-tuning an ASR model on synthetic stuttered speech we are able to reduce word error by 5. 7% relative on stuttered utterances, with only minor (<0. 2% relative) degradation for fluent utterances.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Depth Monocular Estimation with Attention-based Encoder-Decoder Network from Single Image
Depth information is the foundation of perception, essential for autonomous driving, robotics, and other source-constrained applications.
An Effective Approach for Multi-label Classification with Missing Labels
Through comprehensive experiments on three large-scale multi-label image datasets, i. e. MS-COCO, NUS-WIDE, and Pascal VOC12, we show that our method can handle the imbalance between positive labels and negative labels, while still outperforming existing missing-label learning approaches in most cases, and in some cases even approaches with fully labeled datasets.
