Search Results for author: Yuliang Li

Found 21 papers, 8 papers with code

LAVE: LLM-Powered Agent Assistance and Language Augmentation for Video Editing

no code implementations15 Feb 2024 Bryan Wang, Yuliang Li, Zhaoyang Lv, Haijun Xia, Yan Xu, Raj Sodhi

Based on these findings, we propose design implications to inform the future development of agent-assisted content editing.

Video Editing

Human-Centered Planning

no code implementations8 Nov 2023 Yuliang Li, Nitin Kamra, Ruta Desai, Alon Halevy

The vision of creating AI-powered personal assistants also involves creating structured outputs, such as a plan for one's day, or for an overseas trip.

Reimagining Retrieval Augmented Language Models for Answering Queries

no code implementations1 Jun 2023 Wang-Chiew Tan, Yuliang Li, Pedro Rodriguez, Richard James, Xi Victoria Lin, Alon Halevy, Scott Yih

We present a reality check on large language models and inspect the promise of retrieval augmented language models in comparison.

Question Answering Retrieval

Region-wise matching for image inpainting based on adaptive weighted low-rank decomposition

no code implementations22 Mar 2023 Shenghai Liao, Xuya Liu, Ruyi Han, Shujun Fu, Yuanfeng Zhou, Yuliang Li

A non-convex weighted low-rank decomposition (NC-WLRD) model for LRMA is also proposed to reconstruct all degraded patch matrices grouped by the proposed RwM algorithm.

Image Inpainting Matrix Completion

Localisation And Imaging Methods for Moving Target Ghost Imaging Radar Based On Correlation Intensity Weighting

no code implementations22 Jun 2022 Yuliang Li

Ghost imaging radar is a new system of gaze imaging radar with high detection sensitivity, super-resolution and better anti-interference performance, but the relative motion between the radar system and the target will make the target imaging deteriorate.

Position Super-Resolution +1

Annotating Columns with Pre-trained Language Models

1 code implementation5 Apr 2021 Yoshihiko Suhara, Jinfeng Li, Yuliang Li, Dan Zhang, Çağatay Demiralp, Chen Chen, Wang-Chiew Tan

Inferring meta information about tables, such as column headers or relationships between columns, is an active research topic in data management as we find many tables are missing some of this information.

Columns Property Annotation Column Type Annotation +3

Deep or Simple Models for Semantic Tagging? It Depends on your Data [Experiments]

no code implementations11 Jul 2020 Jinfeng Li, Yuliang Li, Xiaolan Wang, Wang-Chiew Tan

We embark on a systematic study to investigate the following question: Are deep models the best performing model for all semantic tagging tasks?

TAG

Enhancing Review Comprehension with Domain-Specific Commonsense

no code implementations6 Apr 2020 Aaron Traylor, Chen Chen, Behzad Golshan, Xiaolan Wang, Yuliang Li, Yoshihiko Suhara, Jinfeng Li, Cagatay Demiralp, Wang-Chiew Tan

In this paper, we introduce xSense, an effective system for review comprehension using domain-specific commonsense knowledge bases (xSense KBs).

Aspect Extraction Knowledge Distillation +3

Deep Entity Matching with Pre-Trained Language Models

1 code implementation1 Apr 2020 Yuliang Li, Jinfeng Li, Yoshihiko Suhara, AnHai Doan, Wang-Chiew Tan

Our experiments show that a straightforward application of language models such as BERT, DistilBERT, or RoBERTa pre-trained on large text corpora already significantly improves the matching quality and outperforms previous state-of-the-art (SOTA), by up to 29% of F1 score on benchmark datasets.

Data Augmentation Entity Resolution

Towards Productionizing Subjective Search Systems

no code implementations31 Mar 2020 Aaron Feng, Shuwei Chen, Yuliang Li, Hiroshi Matsuda, Hidekazu Tamaki, Wang-Chiew Tan

Also, we found that the existing search algorithms do not meet the search quality standard required by production systems.

Benchmarking Language Modelling +1

Snippext: Semi-supervised Opinion Mining with Augmented Data

1 code implementation7 Feb 2020 Zhengjie Miao, Yuliang Li, Xiaolan Wang, Wang-Chiew Tan

A novelty of Snippext is its clever use of a two-prong approach to achieve state-of-the-art (SOTA) performance with little labeled training data through: (1) data augmentation to automatically generate more labeled training data from existing ones, and (2) a semi-supervised learning technique to leverage the massive amount of unlabeled data in addition to the (limited amount of) labeled data.

Data Augmentation Language Modelling +1

Teddy: A System for Interactive Review Analysis

1 code implementation15 Jan 2020 Xiong Zhang, Jonathan Engel, Sara Evensen, Yuliang Li, Çağatay Demiralp, Wang-Chiew Tan

They contain a wealth of information about the opinions and experiences of users, which can help better understand consumer decisions and improve user experience with products and services.

Fast LLMMSE filter for low-dose CT imaging

no code implementations23 Mar 2019 Fengling Wang, Bowen Lin, Shujun Fu, Shiling Xie, Zhigang Zhao, Yuliang Li

Low-dose X-ray CT technology is one of important directions of current research and development of medical imaging equipment.

Subjective Databases

no code implementations25 Feb 2019 Yuliang Li, Aaron Xixuan Feng, Jinfeng Li, Saran Mumick, Alon Halevy, Vivian Li, Wang-Chiew Tan

In order to support experiential queries, a database system needs to model subjective data and also be able to process queries where the user can express varied subjective experiences in words chosen by the user, in addition to specifying predicates involving objective attributes.

Databases

Optical Fringe Patterns Filtering Based on Multi-Stage Convolution Neural Network

no code implementations2 Jan 2019 Bowen Lin, Shujun Fu, Caiming Zhang, Fengling Wang, Yuliang Li

Optical fringe patterns are often contaminated by speckle noise, making it difficult to accurately and robustly extract their phase fields.

Denoising

VERIFAS: A Practical Verifier for Artifact Systems

1 code implementation29 May 2017 Yuliang Li, Alin Deutsch, Victor Vianu

Data-driven workflows, of which IBM's Business Artifacts are a prime exponent, have been successfully deployed in practice, adopted in industrial standards, and have spawned a rich body of research in academia, focused primarily on static analysis.

Databases Logic in Computer Science

SpinArt: A Spin-based Verifier for Artifact Systems

1 code implementation26 May 2017 Yuliang Li, Alin Deutsch, Victor Vianu

Data-driven workflows, of which IBM's Business Artifacts are a prime exponent, have been successfully deployed in practice, adopted in industrial standards, and have spawned a rich body of research in academia, focused primarily on static analysis.

Databases Formal Languages and Automata Theory

Verification of Hierarchical Artifact Systems

1 code implementation4 Apr 2016 Alin Deutsch, Yuliang Li, Victor Vianu

Data-driven workflows, of which IBM's Business Artifacts are a prime exponent, have been successfully deployed in practice, adopted in industrial standards, and have spawned a rich body of research in academia, focused primarily on static analysis.

Databases

Cannot find the paper you are looking for? You can Submit a new open access paper.