Search Results for author: Yang Han

Found 14 papers, 5 papers with code

From Generalist to Specialist: A Survey of Large Language Models for Chemistry

1 code implementation28 Dec 2024 Yang Han, Ziping Wan, Lu Chen, Kai Yu, Xin Chen

Large Language Models (LLMs) have significantly transformed our daily life and established a new paradigm in natural language processing (NLP).

scientific discovery Survey

Counterfactual Uncertainty Quantification of Factual Estimand of Efficacy from Before-and-After Treatment Repeated Measures Randomized Controlled Trials

no code implementations14 Nov 2024 Xingya Wang, Yang Han, Yushi Liu, Szu-Yu Tang, Jason C. Hsu

The ideal estimand for comparing treatment $Rx$ with a control $C$ is the $\textit{counterfactual}$ efficacy $Rx:C$, the expected differential outcome between $Rx$ and $C$ if each patient were given $\textit{both}$.

counterfactual Uncertainty Quantification

AlignSum: Data Pyramid Hierarchical Fine-tuning for Aligning with Human Summarization Preference

1 code implementation1 Oct 2024 Yang Han, Yiming Wang, Rui Wang, Lu Chen, Kai Yu

This demonstrates that AlignSum significantly enhances the alignment of language models with human summarization preferences.

Text Summarization

J2N -- Nominal Adjective Identification and its Application

1 code implementation22 Sep 2024 Lemeng Qi, Yang Han, Zhuotong Xie

This paper explores the challenges posed by nominal adjectives (NAs) in natural language processing (NLP) tasks, particularly in part-of-speech (POS) tagging.

Chunking coreference-resolution +4

Research on fusing topological data analysis with convolutional neural network

no code implementations19 Jun 2024 Yang Han, Qin Guangjun, Liu Ziyuan, Hu Yongqing, Liu Guangnan, Dai Qinglong

This method combines numerical distribution features captured by CNN with topological structure features captured by TDA to improve the feature learning and representation ability of CNN.

Decision Making Topological Data Analysis

Reward Generalization in RLHF: A Topological Perspective

no code implementations15 Feb 2024 Tianyi Qiu, Fanzhi Zeng, Jiaming Ji, Dong Yan, Kaile Wang, Jiayi Zhou, Yang Han, Josef Dai, Xuehai Pan, Yaodong Yang

As a solution, we introduce a theoretical framework for investigating reward generalization in reinforcement learning from human feedback (RLHF), focusing on the topology of information flow at both macro and micro levels.

Generalization Bounds Language Modelling +1

Identifying outliers in astronomical images with unsupervised machine learning

no code implementations19 May 2022 Yang Han, Zhiqiang Zou, Nan Li, Yanli Chen

For comparison, we construct three methods, which are built upon the k-nearest neighbors (KNN), Convolutional Auto-Encoder (CAE)+ KNN, and CAE + KNN + Attention Mechanism (attCAE KNN) separately.

Astronomy BIG-bench Machine Learning

AKB-48: A Real-World Articulated Object Knowledge Base

no code implementations CVPR 2022 Liu Liu, Wenqiang Xu, Haoyuan Fu, Sucheng Qian, Yang Han, Cewu Lu

To bridge the gap, we present AKB-48: a large-scale Articulated object Knowledge Base which consists of 2, 037 real-world 3D articulated object models of 48 categories.

Object Object Reconstruction +1

Shuffle Transformer with Feature Alignment for Video Face Parsing

no code implementations16 Jun 2021 Rui Zhang, Yang Han, Zilong Huang, Pei Cheng, Guozhong Luo, Gang Yu, Bin Fu

This is a short technical report introducing the solution of the Team TCParser for Short-video Face Parsing Track of The 3rd Person in Context (PIC) Workshop and Challenge at CVPR 2021.

Face Parsing

Deep-AIR: A Hybrid CNN-LSTM Framework for Air Quality Modeling in Metropolitan Cities

no code implementations25 Mar 2021 Yang Han, Qi Zhang, Victor O. K. Li, Jacqueline C. K. Lam

Our proposed framework creates 1x1 convolution layers to strengthen the learning of cross-feature spatial interaction between air pollution and important urban dynamic features, particularly road density, building density/height, and street canyon effect.

Evaluating the Discrimination Ability of Proper Multivariate Scoring Rules

no code implementations29 Jan 2021 Carol Alexander, Michael Coulon, Yang Han, Xiaochun Meng

Proper scoring rules are commonly applied to quantify the accuracy of distribution forecasts.

Methodology Statistical Finance Applications

A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition

1 code implementation20 May 2020 Dongwei Jiang, Wubo Li, Ruixiong Zhang, Miao Cao, Ne Luo, Yang Han, Wei Zou, Xiangang Li

In this paper, we conduct a further study on MPC and focus on three important aspects: the effect of pre-training data speaking style, its extension on streaming model, and how to better transfer learned knowledge from pre-training stage to downstream tasks.

speech-recognition Speech Recognition +2

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