Search Results for author:
Found 37 papers, 17 papers with code
Can Your Model Tell a Negation from an Implicature? Unravelling Challenges With Intent Encoders
The triplet task gauges the model's understanding of two semantic concepts paramount in real-world conversational systems-- negation and implicature.
Semi-Supervised Dialogue Abstractive Summarization via High-Quality Pseudolabel Selection
Semi-supervised dialogue summarization (SSDS) leverages model-generated summaries to reduce reliance on human-labeled data and improve the performance of summarization models.
Abstractive Text Summarization
Natural Language Understanding
MAGID: An Automated Pipeline for Generating Synthetic Multi-modal Datasets
Development of multimodal interactive systems is hindered by the lack of rich, multimodal (text, images) conversational data, which is needed in large quantities for LLMs.
TofuEval: Evaluating Hallucinations of LLMs on Topic-Focused Dialogue Summarization
We find that there are diverse errors and error distributions in model-generated summaries and that non-LLM based metrics can capture all error types better than LLM-based evaluators.
Adaptive Shortcut Debiasing for Online Continual Learning
We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment.
Toward Robustness in Multi-label Classification: A Data Augmentation Strategy against Imbalance and Noise
Multi-label classification poses challenges due to imbalanced and noisy labels in training data.
One Size Fits All for Semantic Shifts: Adaptive Prompt Tuning for Continual Learning
We identify the inadequacy of universal and specific prompting in handling these dynamic shifts.
Enhancing Abstractiveness of Summarization Models through Calibrated Distillation
Our experiments show that DisCal outperforms prior methods in abstractive summarization distillation, producing highly abstractive and informative summaries.
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding
To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the subsequent token.
Prompt-Guided Transformers for End-to-End Open-Vocabulary Object Detection
Prompt-OVD is an efficient and effective framework for open-vocabulary object detection that utilizes class embeddings from CLIP as prompts, guiding the Transformer decoder to detect objects in both base and novel classes.
Re-thinking Federated Active Learning based on Inter-class Diversity
In this work, we first demonstrate that the superiority of two selector models depends on the global and local inter-class diversity.
Q-HyViT: Post-Training Quantization for Hybrid Vision Transformer with Bridge Block Reconstruction
To overcome these challenges, we propose a new post-training quantization method, which is the first to quantize efficient hybrid ViTs (MobileViTv1, MobileViTv2, Mobile-Former, EfficientFormerV1, EfficientFormerV2) with a significant margin (an average improvement of 8. 32\% for 8-bit and 26. 02\% for 6-bit) compared to existing PTQ methods (EasyQuant, FQ-ViT, and PTQ4ViT).
Generating Instance-level Prompts for Rehearsal-free Continual Learning
However, we observe that the use of a prompt pool creates a domain scalability problem between pre-training and continual learning.
Meta-Query-Net: Resolving Purity-Informativeness Dilemma in Open-set Active Learning
Unlabeled data examples awaiting annotations contain open-set noise inevitably.
Time Is MattEr: Temporal Self-supervision for Video Transformers
Understanding temporal dynamics of video is an essential aspect of learning better video representations.
e-CLIP: Large-Scale Vision-Language Representation Learning in E-commerce
Understanding vision and language representations of product content is vital for search and recommendation applications in e-commerce.
Dataset Condensation via Efficient Synthetic-Data Parameterization
The great success of machine learning with massive amounts of data comes at a price of huge computation costs and storage for training and tuning.
ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
Cross-domain few-shot learning (CD-FSL), where there are few target samples under extreme differences between source and target domains, has recently attracted huge attention.
FedRN: Exploiting k-Reliable Neighbors Towards Robust Federated Learning
Robustness is becoming another important challenge of federated learning in that the data collection process in each client is naturally accompanied by noisy labels.
An Extendable, Efficient and Effective Transformer-based Object Detector
Transformers have been widely used in numerous vision problems especially for visual recognition and detection.
Online Continual Learning on a Contaminated Data Stream with Blurry Task Boundaries
A large body of continual learning (CL) methods, however, assumes data streams with clean labels, and online learning scenarios under noisy data streams are yet underexplored.
Meta-Learning for Online Update of Recommender Systems
It is featured with an adaptive learning rate for each parameter-interaction pair for inducing a recommender to quickly learn users' up-to-date interest.
Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
This data enables self-supervised pre-training on the target domain, in addition to supervised pre-training on the source domain.
Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspective
In this survey, we study the research landscape for data collection and data quality primarily for deep learning applications.
Task-Agnostic Undesirable Feature Deactivation Using Out-of-Distribution Data
A deep neural network (DNN) has achieved great success in many machine learning tasks by virtue of its high expressive power.
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Transformers are transforming the landscape of computer vision, especially for recognition tasks.
Ranked #12 on
Object Detection
on COCO 2017 val
Chameleon Sampling: Diverse and Pure Example Selection for Online Continual Learning with Noisy Labels
Specifically, we argue the importance of both diversity and purity of examples in the episodic memory of continual learning models.
Coherence-based Label Propagation over Time Series for Accelerated Active Learning
Time-series data are ubiquitous these days, but lack of the labels in time-series data is regarded as a hurdle for its broad applicability.
Influential Rank: A New Perspective of Post-training for Robust Model against Noisy Labels
Deep neural network can easily overfit to even noisy labels due to its high capacity, which degrades the generalization performance of a model.
Robust Learning by Self-Transition for Handling Noisy Labels
In the seeding phase, the network is updated using all the samples to collect a seed of clean samples.
Learning from Noisy Labels with Deep Neural Networks: A Survey
Deep learning has achieved remarkable success in numerous domains with help from large amounts of big data.
Carpe Diem, Seize the Samples Uncertain "At the Moment" for Adaptive Batch Selection
Compared with existing batch selection methods, the results showed that Recency Bias reduced the test error by up to 20. 97% in a fixed wall-clock training time.
How does Early Stopping Help Generalization against Label Noise?
In this paper, we claim that such overfitting can be avoided by "early stopping" training a deep neural network before the noisy labels are severely memorized.
MLAT: Metric Learning for kNN in Streaming Time Series
Learning a good distance measure for distance-based classification in time series leads to significant performance improvement in many tasks.
Prestopping: How Does Early Stopping Help Generalization Against Label Noise?
In this paper, we claim that such overfitting can be avoided by "early stopping" training a deep neural network before the noisy labels are severely memorized.
SELFIE: Refurbishing Unclean Samples for Robust Deep Learning
Owing to the extremely high expressive power of deep neural networks, their side effect is to totally memorize training data even when the labels are extremely noisy.
Ranked #14 on
Learning with noisy labels
on ANIMAL
Ada-Boundary: Accelerating the DNN Training via Adaptive Boundary Batch Selection
Neural networks can converge faster with help from a smarter batch selection strategy.
