Search Results for author:
Found 36 papers, 24 papers with code
Revisit Overconfidence for OOD Detection: Reassigned Contrastive Learning with Adaptive Class-dependent Threshold
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system.
Disentangled Knowledge Transfer for OOD Intent Discovery with Unified Contrastive Learning
Discovering Out-of-Domain(OOD) intents is essential for developing new skills in a task-oriented dialogue system.
Learning Discriminative Representations for Open Relation Extraction with Instance Ranking and Label Calibration
In this paper, we propose a novel method based on Instance Ranking and Label Calibration strategies (IRLC) to learn discriminative representations for open relation extraction.
RCL: Relation Contrastive Learning for Zero-Shot Relation Extraction
Zero-shot relation extraction aims to identify novel relations which cannot be observed at the training stage.
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
First, a single-controller architecture combined with an abstraction of the parallel worker simplifies the development of the training pipeline.
DREAM: Disentangling Risks to Enhance Safety Alignment in Multimodal Large Language Models
Multimodal Large Language Models (MLLMs) pose unique safety challenges due to their integration of visual and textual data, thereby introducing new dimensions of potential attacks and complex risk combinations.
ProgCo: Program Helps Self-Correction of Large Language Models
Then, program-driven refinement (ProgRe) receives feedback from ProgVe, conducts dual reflection and refinement on both responses and verification programs to mitigate misleading of incorrect feedback in complex reasoning tasks.
V$^2$-SfMLearner: Learning Monocular Depth and Ego-motion for Multimodal Wireless Capsule Endoscopy
Therefore, we propose V$^2$-SfMLearner, a multimodal approach integrating vibration signals into vision-based depth and capsule motion estimation for monocular capsule endoscopy.
M2rc-Eval: Massively Multilingual Repository-level Code Completion Evaluation
Besides, the existing benchmarks usually report overall average scores of different languages, where the fine-grained abilities in different completion scenarios are ignored.
Transferring Knowledge from High-Quality to Low-Quality MRI for Adult Glioma Diagnosis
Our top-performing model achieves Dice scores of 0. 882, 0. 840, and 0. 926, and Hausdorff Distance (95%) scores of 15. 324, 37. 518, and 13. 971 for enhancing tumor, tumor core, and whole tumor, respectively, in the validation phase.
Task Consistent Prototype Learning for Incremental Few-shot Semantic Segmentation
Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples.
MTU-Bench: A Multi-granularity Tool-Use Benchmark for Large Language Models
Besides, all evaluation metrics of our MTU-Bench are based on the prediction results and the ground truth without using any GPT or human evaluation metrics.
DDK: Distilling Domain Knowledge for Efficient Large Language Models
Despite the advanced intelligence abilities of large language models (LLMs) in various applications, they still face significant computational and storage demands.
Distribution Alignment for Fully Test-Time Adaptation with Dynamic Online Data Streams
Given a model trained on source data, Test-Time Adaptation (TTA) enables adaptation and inference in test data streams with domain shifts from the source.
R2C2-Coder: Enhancing and Benchmarking Real-world Repository-level Code Completion Abilities of Code Large Language Models
Code completion models have made significant progress in recent years.
ConceptMath: A Bilingual Concept-wise Benchmark for Measuring Mathematical Reasoning of Large Language Models
This paper introduces ConceptMath, a bilingual (English and Chinese), fine-grained benchmark that evaluates concept-wise mathematical reasoning of Large Language Models (LLMs).
SAR-RARP50: Segmentation of surgical instrumentation and Action Recognition on Robot-Assisted Radical Prostatectomy Challenge
Surgical tool segmentation and action recognition are fundamental building blocks in many computer-assisted intervention applications, ranging from surgical skills assessment to decision support systems.
Test-Time Domain Adaptation by Learning Domain-Aware Batch Normalization
In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer.
APP: Adaptive Prototypical Pseudo-Labeling for Few-shot OOD Detection
Detecting out-of-domain (OOD) intents from user queries is essential for a task-oriented dialogue system.
Rethinking Exemplars for Continual Semantic Segmentation in Endoscopy Scenes: Entropy-based Mini-Batch Pseudo-Replay
More seriously, data privacy and storage issues may lead to the unavailability of old data when updating the model.
MetaGCD: Learning to Continually Learn in Generalized Category Discovery
The goal is to continually discover novel classes while maintaining the performance in known classes.
Landmark Detection using Transformer Toward Robot-assisted Nasal Airway Intubation
This paper proposes a transformer-based landmark detection solution with deformable DeTR and the semantic-aligned-matching module for detecting landmarks in robot-assisted intubation.
Semi-supervised Learning for Segmentation of Bleeding Regions in Video Capsule Endoscopy
Notably, we develop the segmentation annotations for this dataset ourselves.
LLCaps: Learning to Illuminate Low-Light Capsule Endoscopy with Curved Wavelet Attention and Reverse Diffusion
Given the exuberant development of the denoising diffusion probabilistic model (DDPM) in computer vision, we introduce a WCE LLIE framework based on the multi-scale convolutional neural network (CNN) and reverse diffusion process.
Semantic-Aware Graph Matching Mechanism for Multi-Label Image Recognition
In this paper, we treat each image as a bag of instances, and formulate the task of multi-label image recognition as an instance-label matching selection problem.
Two-stage Contextual Transformer-based Convolutional Neural Network for Airway Extraction from CT Images
In the first stage, the total airway mask and CT images are provided to the subnetwork, and the intrapulmonary airway mask and corresponding CT scans to the subnetwork in the second stage.
UniNL: Aligning Representation Learning with Scoring Function for OOD Detection via Unified Neighborhood Learning
Specifically, we design a K-nearest neighbor contrastive learning (KNCL) objective for representation learning and introduce a KNN-based scoring function for OOD detection.
Disentangling Confidence Score Distribution for Out-of-Domain Intent Detection with Energy-Based Learning
In this paper, we propose a simple but strong energy-based score function to detect OOD where the energy scores of OOD samples are higher than IND samples.
Watch the Neighbors: A Unified K-Nearest Neighbor Contrastive Learning Framework for OOD Intent Discovery
For OOD clustering stage, we propose a KCC method to form compact clusters by mining true hard negative samples, which bridges the gap between clustering and representation learning.
Distribution Calibration for Out-of-Domain Detection with Bayesian Approximation
Out-of-Domain (OOD) detection is a key component in a task-oriented dialog system, which aims to identify whether a query falls outside the predefined supported intent set.
Generalized Intent Discovery: Learning from Open World Dialogue System
Traditional intent classification models are based on a pre-defined intent set and only recognize limited in-domain (IND) intent classes.
Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings.
Dynamically Disentangling Social Bias from Task-Oriented Representations with Adversarial Attack
In this paper, we propose an adversarial disentangled debiasing model to dynamically decouple social bias attributes from the intermediate representations trained on the main task.
Modeling Discriminative Representations for Out-of-Domain Detection with Supervised Contrastive Learning
Detecting Out-of-Domain (OOD) or unknown intents from user queries is essential in a task-oriented dialog system.
Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System
Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set.
GM-MLIC: Graph Matching based Multi-Label Image Classification
Multi-Label Image Classification (MLIC) aims to predict a set of labels that present in an image.
