Search Results for author:
Found 48 papers, 25 papers with code
APIRecX: Cross-Library API Recommendation via Pre-Trained Language Model
APIRecX can migrate the knowledge of existing libraries to a new library, and can recommend APIs that are previously regarded as OOV.
Modeling Syntactic-Semantic Dependency Correlations in Semantic Role Labeling Using Mixture Models
In this paper, we propose a mixture model-based end-to-end method to model the syntactic-semantic dependency correlation in Semantic Role Labeling (SRL).
Enhancing LLM-Based Agents via Global Planning and Hierarchical Execution
We evaluate GoalAct on LegalAgentBench, a benchmark with multiple types of legal tasks that require the use of multiple types of tools.
NTIRE 2025 Challenge on Real-World Face Restoration: Methods and Results
This paper provides a review of the NTIRE 2025 challenge on real-world face restoration, highlighting the proposed solutions and the resulting outcomes.
Overlap-Aware Feature Learning for Robust Unsupervised Domain Adaptation for 3D Semantic Segmentation
3D point cloud semantic segmentation (PCSS) is a cornerstone for environmental perception in robotic systems and autonomous driving, enabling precise scene understanding through point-wise classification.
ProtoGuard-guided PROPEL: Class-Aware Prototype Enhancement and Progressive Labeling for Incremental 3D Point Cloud Segmentation
Thus, offline-trained segmentation models may lead to catastrophic forgetting of previously seen classes.
Robust Unsupervised Domain Adaptation for 3D Point Cloud Segmentation Under Source Adversarial Attacks
Unsupervised domain adaptation (UDA) frameworks have shown good generalization capabilities for 3D point cloud semantic segmentation models on clean data.
Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation
Hence, these works neglect to mine fine-grained and structure-aware (FGSA) features from both support and query images, which are crucial for pixel-level keypoint localization.
The Design of Monopoly Information Broker
An information broker incentivizes consumers to share their information, while designing an information structure to shape the market segmentation.
Seeing Sarcasm Through Different Eyes: Analyzing Multimodal Sarcasm Perception in Large Vision-Language Models
With the advent of large vision-language models (LVLMs) demonstrating increasingly human-like abilities, a pivotal question emerges: do different LVLMs interpret multimodal sarcasm differently, and can a single model grasp sarcasm from multiple perspectives like humans?
From Reusing to Forecasting: Accelerating Diffusion Models with TaylorSeers
To solve this problem, feature caching has been proposed to accelerate diffusion models by caching the features in the previous timesteps and then reusing them in the following timesteps.
Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Flexible and Effective Paradigm
Most of existing blind omnidirectional image quality assessment (BOIQA) models rely on viewport generation by modeling user viewing behavior or transforming omnidirectional images (OIs) into varying formats; however, these methods are either computationally expensive or less scalable.
LexRAG: Benchmarking Retrieval-Augmented Generation in Multi-Turn Legal Consultation Conversation
To fill this gap, we propose LexRAG, the first benchmark to evaluate RAG systems for multi-turn legal consultations.
CaseGen: A Benchmark for Multi-Stage Legal Case Documents Generation
To the best of our knowledge, CaseGen is the first benchmark designed to evaluate LLMs in the context of legal case document generation.
Omnidirectional Image Quality Captioning: A Large-scale Database and A New Model
The fast growing application of omnidirectional images calls for effective approaches for omnidirectional image quality assessment (OIQA).
Multitask Auxiliary Network for Perceptual Quality Assessment of Non-Uniformly Distorted Omnidirectional Images
The proposed network mainly consists of three parts: a backbone for extracting multiscale features from the viewport sequence, a multitask feature selection module for dynamically allocating specific features to different tasks, and auxiliary sub-networks for guiding the proposed model to capture local distortion and global quality change.
LegalAgentBench: Evaluating LLM Agents in Legal Domain
Therefore, we propose LegalAgentBench, a comprehensive benchmark specifically designed to evaluate LLM Agents in the Chinese legal domain.
ProsodyFM: Unsupervised Phrasing and Intonation Control for Intelligible Speech Synthesis
We propose ProsodyFM, a prosody-aware text-to-speech synthesis (TTS) model with a flow-matching (FM) backbone that aims to enhance the phrasing and intonation aspects of prosody.
LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods
Finally, we provide a detailed analysis of the limitations of LLM judges and discuss potential future directions.
CalibraEval: Calibrating Prediction Distribution to Mitigate Selection Bias in LLMs-as-Judges
The use of large language models (LLMs) as automated evaluation tools to assess the quality of generated natural language, known as LLMs-as-Judges, has demonstrated promising capabilities and is rapidly gaining widespread attention.
An Automatic and Cost-Efficient Peer-Review Framework for Language Generation Evaluation
Moreover, our study highlights the impact of prompt strategies and evaluation formats on evaluation performance, offering guidance for method optimization in the future.
Machine Unlearning in Forgettability Sequence
Machine unlearning (MU) is becoming a promising paradigm to achieve the "right to be forgotten", where the training trace of any chosen data points could be eliminated, while maintaining the model utility on general testing samples after unlearning.
Improving Unsupervised Constituency Parsing via Maximizing Semantic Information
In this paper, we introduce a novel objective for training unsupervised parsers: maximizing the information between constituent structures and sentence semantics (SemInfo).
Continual Learning for Adaptable Car-Following in Dynamic Traffic Environments
The continual evolution of autonomous driving technology requires car-following models that can adapt to diverse and dynamic traffic environments.
GenFollower: Enhancing Car-Following Prediction with Large Language Models
In this study, we propose GenFollower, a novel zero-shot prompting approach that leverages large language models (LLMs) to address these challenges.
InterCLIP-MEP: Interactive CLIP and Memory-Enhanced Predictor for Multi-modal Sarcasm Detection
Sarcasm in social media, often expressed through text-image combinations, poses challenges for sentiment analysis and intention mining.
Unsupervised Parsing by Searching for Frequent Word Sequences among Sentences with Equivalent Predicate-Argument Structures
Linguists identify the constituent by evaluating a set of Predicate-Argument Structure (PAS) equivalent sentences where we find the constituent appears more frequently than non-constituents (i. e., the constituent corresponds to a frequent word sequence within the sentence set).
Meta-Point Learning and Refining for Category-Agnostic Pose Estimation
Existing methods only rely on the features extracted at support keypoints to predict or refine the keypoints on query image, but a few support feature vectors are local and inadequate for CAPE.
A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models
Specifically, we target the widely-used application scenario of image classification, and utilized three different datasets and five commonly-used performance metrics to assess in total 13 methods from diverse categories.
Triple-View Knowledge Distillation for Semi-Supervised Semantic Segmentation
To alleviate the expensive human labeling, semi-supervised semantic segmentation employs a few labeled images and an abundant of unlabeled images to predict the pixel-level label map with the same size.
Task Selection and Assignment for Multi-modal Multi-task Dialogue Act Classification with Non-stationary Multi-armed Bandits
Our proposed method is significantly superior in terms of UAR and F1 to the single-task and multi-task baselines with p-values < 0. 05.
How to Evaluate Semantic Communications for Images with ViTScore Metric?
To evaluate the performance of ViTScore, we compare ViTScore with 3 typical metrics (PSNR, MS-SSIM, and LPIPS) through 4 classes of experiments: (i) correlation with BERTScore through evaluation of image caption downstream CV task, (ii) evaluation in classical image communications, (iii) evaluation in image semantic communication systems, and (iv) evaluation in image semantic communication systems with semantic attack.
Bias Testing and Mitigation in LLM-based Code Generation
This issue concerns the integrity, fairness, and ethical foundation of software applications that depend on the code generated by these models but are underexplored in the literature.
Try with Simpler -- An Evaluation of Improved Principal Component Analysis in Log-based Anomaly Detection
This addresses the issue of unseen log events in training data, enhancing log representation.
Scene-aware Human Pose Generation using Transformer
Affordance learning considers the interaction opportunities for an actor in the scene and thus has wide application in scene understanding and intelligent robotics.
Residual Spatial Fusion Network for RGB-Thermal Semantic Segmentation
Specifically, we employ an asymmetric encoder to learn the compensating features of the RGB and the thermal images.
Ranked #23 on
Thermal Image Segmentation
on MFN Dataset
Generic and Robust Root Cause Localization for Multi-Dimensional Data in Online Service Systems
Such attribute combinations are substantial clues to the underlying root causes and thus are called root causes of multidimensional data.
iEnhancer-ELM: improve enhancer identification by extracting position-related multiscale contextual information based on enhancer language models
Although many feature extraction methods have been proposed to improve the performance of enhancer identification, they cannot learn position-related multiscale contextual information from raw DNA sequences.
Weak-shot Semantic Segmentation via Dual Similarity Transfer
Proposal segmentation allows proposal-pixel similarity transfer from base classes to novel classes, which enables the mask learning of novel classes.
Bridging the View Disparity Between Radar and Camera Features for Multi-modal Fusion 3D Object Detection
A novel method that realizes the feature-level fusion under the bird's-eye view (BEV) for a better feature representation is proposed.
Mixed Supervised Object Detection by Transferring Mask Prior and Semantic Similarity
Specifically, the ability of using mask prior to help detect objects is learned from base categories and transferred to novel categories.
Pyramid Correlation based Deep Hough Voting for Visual Object Tracking
Through experiments we find that, without regression, the performance could be equally promising as long as we delicately design the network to suit the training objective.
An Improved StarGAN for Emotional Voice Conversion: Enhancing Voice Quality and Data Augmentation
Emotional Voice Conversion (EVC) aims to convert the emotional style of a source speech signal to a target style while preserving its content and speaker identity information.
On the Evaluation of Neural Code Summarization
To achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code summarization models on 6 widely used BLEU variants, 4 pre-processing operations and their combinations, and 3 widely used datasets.
Weak-shot Fine-grained Classification via Similarity Transfer
In this setting, we propose a method called SimTrans to transfer pairwise semantic similarity from base categories to novel categories.
A System for Worldwide COVID-19 Information Aggregation
The global pandemic of COVID-19 has made the public pay close attention to related news, covering various domains, such as sanitation, treatment, and effects on education.
Detection of Information Hiding at Anti-Copying 2D Barcodes
Our experimental results show that the PVBD scheme can correctly detect the existence of the hidden information at both the 2LQR code and the LCAC 2D barcode.
Learning from Web Data with Self-Organizing Memory Module
However, crawled web images usually have two types of noises, label noise and background noise, which induce extra difficulties in utilizing them effectively.
Ranked #14 on
Image Classification
on WebVision-1000
