Search Results for author: Cheng Chang

Found 23 papers, 10 papers with code

Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applications

no code implementations6 Apr 2025 Cheng Chang, Jingwei Ge, Jiazhe Guo, Zelin Guo, Binghong Jiang, Li Li

Driving scenario data play an increasingly vital role in the development of intelligent vehicles and autonomous driving.

Autonomous Driving RAG +2

Is Your LLM Secretly a World Model of the Internet? Model-Based Planning for Web Agents

1 code implementation10 Nov 2024 Yu Gu, Kai Zhang, Yuting Ning, Boyuan Zheng, Boyu Gou, Tianci Xue, Cheng Chang, Sanjari Srivastava, Yanan Xie, Peng Qi, Huan Sun, Yu Su

We advocate model-based planning for web agents that employs a world model to simulate and deliberate over the outcome of each candidate action before committing to one.

model

Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents

1 code implementation7 Oct 2024 Boyu Gou, Ruohan Wang, Boyuan Zheng, Yanan Xie, Cheng Chang, Yiheng Shu, Huan Sun, Yu Su

The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms.

Natural Language Visual Grounding Navigate +1

Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles

no code implementations1 Jul 2024 Ryan Louie, Ananjan Nandi, William Fang, Cheng Chang, Emma Brunskill, Diyi Yang

To address this, we develop Roleplay-doh, a novel human-LLM collaboration pipeline that elicits qualitative feedback from a domain-expert, which is transformed into a set of principles, or natural language rules, that govern an LLM-prompted roleplay.

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models

1 code implementation21 May 2024 Zhangyue Yin, Qiushi Sun, Qipeng Guo, Zhiyuan Zeng, Xiaonan Li, Tianxiang Sun, Cheng Chang, Qinyuan Cheng, Ding Wang, Xiaofeng Mou, Xipeng Qiu, Xuanjing Huang

Recent advancements in Chain-of-Thought prompting have facilitated significant breakthroughs for Large Language Models (LLMs) in complex reasoning tasks.

Answer Selection

A conservative hybrid physics-informed neural network method for Maxwell-Ampère-Nernst-Planck equations

no code implementations10 Dec 2023 Cheng Chang, Zhouping Xin, Tieyong Zeng

However, when the spatial dimension is one, the original curl-free relaxation component is inapplicable, and the approximation formula for dummy variables, which works well in a 2-dimensional scenario, fails to provide a reasonable output in the 1-dimensional case.

A hybrid data driven-physics constrained Gaussian process regression framework with deep kernel for uncertainty quantification

no code implementations13 May 2022 Cheng Chang, Tieyong Zeng

The proposed model learns from both data and physics constraints through the training of a deep neural network, which serves as part of the covariance function in GPR.

GPR regression +1

Modeling the US-China trade conflict: a utility theory approach

no code implementations23 Oct 2020 Yuhan Zhang, Cheng Chang

This paper models the US-China trade conflict and attempts to analyze the (optimal) strategic choices.

Explore-Exploit Graph Traversal for Image Retrieval

1 code implementation CVPR 2019 Cheng Chang, Guangwei Yu, Chundi Liu, Maksims Volkovs

Given a nearest neighbor graph produced by the global descriptor model, we traverse it by alternating between exploit and explore steps.

Image Retrieval Retrieval

Affordable On-line Dialogue Policy Learning

no code implementations EMNLP 2017 Cheng Chang, Runzhe Yang, Lu Chen, Xiang Zhou, Kai Yu

The key to building an evolvable dialogue system in real-world scenarios is to ensure an affordable on-line dialogue policy learning, which requires the on-line learning process to be safe, efficient and economical.

Dialogue Management

On-line Dialogue Policy Learning with Companion Teaching

no code implementations EACL 2017 Lu Chen, Runzhe Yang, Cheng Chang, Zihao Ye, Xiang Zhou, Kai Yu

On-line dialogue policy learning is the key for building evolvable conversational agent in real world scenarios.

Dialogue Management

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