Search Results for author:
Found 35 papers, 14 papers with code
Dialogue Response Generation via Contrastive Latent Representation Learning
In this work, we aim to construct a robust sentence representation learning model, that is specifically designed for dialogue response generation, with Transformer-based encoder-decoder structure.
Reinforcement Learning from Reflective Feedback (RLRF): Aligning and Improving LLMs via Fine-Grained Self-Reflection
Despite the promise of RLHF in aligning LLMs with human preferences, it often leads to superficial alignment, prioritizing stylistic changes over improving downstream performance of LLMs.
YTCommentQA: Video Question Answerability in Instructional Videos
Experiments with answerability classification tasks demonstrate the complexity of YTCommentQA and emphasize the need to comprehend the combined role of visual and script information in video reasoning.
When Model Meets New Normals: Test-time Adaptation for Unsupervised Time-series Anomaly Detection
Time-series anomaly detection deals with the problem of detecting anomalous timesteps by learning normality from the sequence of observations.
StableVITON: Learning Semantic Correspondence with Latent Diffusion Model for Virtual Try-On
Given a clothing image and a person image, an image-based virtual try-on aims to generate a customized image that appears natural and accurately reflects the characteristics of the clothing image.
Relax: Composable Abstractions for End-to-End Dynamic Machine Learning
Dynamic shape computations have become critical in modern machine learning workloads, especially in emerging large language models.
Expression Domain Translation Network for Cross-domain Head Reenactment
Specifically, to maintain the geometric consistency of expressions between the input and output of the expression domain translation network, we employ a 3D geometric-aware loss function that reduces the distances between the vertices in the 3D mesh of the human and anime.
Label Shift Adapter for Test-Time Adaptation under Covariate and Label Shifts
Test-time adaptation (TTA) aims to adapt a pre-trained model to the target domain in a batch-by-batch manner during inference.
Reference-based Image Composition with Sketch via Structure-aware Diffusion Model
Recent remarkable improvements in large-scale text-to-image generative models have shown promising results in generating high-fidelity images.
Improving Scene Text Recognition for Character-Level Long-Tailed Distribution
However, STR models show a large performance degradation on languages with a numerous number of characters (e. g., Chinese and Korean), especially on characters that rarely appear due to the long-tailed distribution of characters in such languages.
RobustSwap: A Simple yet Robust Face Swapping Model against Attribute Leakage
However, we observed that previous approaches still suffer from source attribute leakage, where the source image's attributes interfere with the target image's.
Open World Classification with Adaptive Negative Samples
Open world classification is a task in natural language processing with key practical relevance and impact.
Ranking-Enhanced Unsupervised Sentence Representation Learning
In this work, we show that the semantic meaning of a sentence is also determined by nearest-neighbor sentences that are similar to the input sentence.
Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment
Editing hairstyle is unique and challenging due to the complexity and delicacy of hairstyle.
High-Resolution Virtual Try-On with Misalignment and Occlusion-Handled Conditions
Image-based virtual try-on aims to synthesize an image of a person wearing a given clothing item.
Ranked #2 on
Virtual Try-on
on VITON-HD
HairFIT: Pose-Invariant Hairstyle Transfer via Flow-based Hair Alignment and Semantic-Region-Aware Inpainting
Hairstyle transfer is the task of modifying a source hairstyle to a target one.
Continuous-Time Video Generation via Learning Motion Dynamics with Neural ODE
In order to perform unconditional video generation, we must learn the distribution of the real-world videos.
Data Augmentation using Random Image Cropping for High-resolution Virtual Try-On (VITON-CROP)
Image-based virtual try-on provides the capacity to transfer a clothing item onto a photo of a given person, which is usually accomplished by warping the item to a given human pose and adjusting the warped item to the person.
AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment
We present a novel Animation CelebHeads dataset (AnimeCeleb) to address an animation head reenactment.
Collage: Seamless Integration of Deep Learning Backends with Automatic Placement
Given the fast-evolving nature of the DL ecosystem, this manual approach often slows down continuous innovations across different layers; it prevents hardware vendors from the fast deployment of their cutting-edge libraries, DL framework developers must repeatedly adjust their hand-coded rules to accommodate new versions of libraries, and machine learning practitioners need to wait for the integration of new technologies and often encounter unsatisfactory performance.
hSDB-instrument: Instrument Localization Database for Laparoscopic and Robotic Surgeries
Localization information for all instruments is provided in the form of a bounding box for object detection.
Rethinking Generalization Performance of Surgical Phase Recognition with Expert-Generated Annotations
For gastrectomy for gastric cancer has more complex twenty-one surgical phases, we generate consensus annotation by the revision process with five specialists.
Improving Face Recognition with Large Age Gaps by Learning to Distinguish Children
Despite the unprecedented improvement of face recognition, existing face recognition models still show considerably low performances in determining whether a pair of child and adult images belong to the same identity.
Semi-Autonomous Teleoperation via Learning Non-Prehensile Manipulation Skills
In this paper, we present a semi-autonomous teleoperation framework for a pick-and-place task using an RGB-D sensor.
What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers
GPT-3 shows remarkable in-context learning ability of large-scale language models (LMs) trained on hundreds of billion scale data.
Learning Slice-Aware Representations with Mixture of Attentions
Real-world machine learning systems are achieving remarkable performance in terms of coarse-grained metrics like overall accuracy and F-1 score.
Handling Long-Tail Queries with Slice-Aware Conversational Systems
We have been witnessing the usefulness of conversational AI systems such as Siri and Alexa, directly impacting our daily lives.
VITON-HD: High-Resolution Virtual Try-On via Misalignment-Aware Normalization
The task of image-based virtual try-on aims to transfer a target clothing item onto the corresponding region of a person, which is commonly tackled by fitting the item to the desired body part and fusing the warped item with the person.
Ranked #3 on
Virtual Try-on
on VITON-HD
Neural model robustness for skill routing in large-scale conversational AI systems: A design choice exploration
Ensuring model robustness or resilience in the skill routing component is an important problem since skills may dynamically change their subscription in the ontology after the skill routing model has been deployed to production.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
K-Hairstyle: A Large-scale Korean Hairstyle Dataset for Virtual Hair Editing and Hairstyle Classification
In response, we introduce a novel large-scale Korean hairstyle dataset, K-hairstyle, containing 500, 000 high-resolution images.
A scalable framework for learning from implicit user feedback to improve natural language understanding in large-scale conversational AI systems
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request.
Vid-ODE: Continuous-Time Video Generation with Neural Ordinary Differential Equation
Video generation models often operate under the assumption of fixed frame rates, which leads to suboptimal performance when it comes to handling flexible frame rates (e. g., increasing the frame rate of the more dynamic portion of the video as well as handling missing video frames).
Learning with Limited Data for Multilingual Reading Comprehension
This paper studies the problem of supporting question answering in a new language with limited training resources.
