Explanipedia

MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning Open

Guoxin Chen, Zile Qiao, Wenqing Wang, Donglei Yu, Xuanzhong Chen , et al. · 2025

Large Reasoning Models (LRMs) often exhibit a tendency for overanalysis in simple tasks, where the models excessively utilize System 2-type, deliberate reasoning, leading to inefficient token generation. Furthermore, these models face chal…

Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation Open

Xiaochuan Liu, Ruihua Song, Xiting Wang, Xu Chen · 2025

Automatic related work generation (RWG) can save people's time and effort when writing a draft of related work section (RWS) for further revision. However, existing methods for RWG always suffer from shallow comprehension due to taking the…

ETVA: Evaluation of Text-to-Video Alignment via Fine-grained Question Generation and Answering Open

K Guan, Zhengfeng Lai, Yuchong Sun, Zhang Peng, Wei Liu , et al. · 2025

Precisely evaluating semantic alignment between text prompts and generated videos remains a challenge in Text-to-Video (T2V) Generation. Existing text-to-video alignment metrics like CLIPScore only generate coarse-grained scores without fi…

Select, Read, and Write: A Multi-Agent Framework of Full-Text-based Related Work Generation Open

Xiaochuan Liu, Ruihua Song, Xiting Wang, Xu Chen · 2025

Two-in-One: Unified Multi-Person Interactive Motion Generation by Latent Diffusion Transformer Open

Boyuan Li, Xihua Wang, Ruihua Song, Wenbing Huang · 2024

Multi-person interactive motion generation, a critical yet under-explored domain in computer character animation, poses significant challenges such as intricate modeling of inter-human interactions beyond individual motions and generating …

BSharedRAG: Backbone Shared Retrieval-Augmented Generation for the E-commerce Domain Open

K Guan, Qian Cao, Yuchong Sun, Xiting Wang, Ruihua Song · 2024

Retrieval Augmented Generation (RAG) system is important in domains such as e-commerce, which has many long-tail entities and frequently updated information. Most existing works adopt separate modules for retrieval and generation, which ma…

LoVA: Long-form Video-to-Audio Generation Open

Xin Cheng, Xihua Wang, Yihan Wu, Youfa Wang, Ruihua Song · 2024

Video-to-audio (V2A) generation is important for video editing and post-processing, enabling the creation of semantics-aligned audio for silent video. However, most existing methods focus on generating short-form audio for short video segm…

Towards Effective and Efficient Continual Pre-training of Large Language Models Open

Jie Chen, Zhipeng Chen, Jiapeng Wang, Kun Zhou, Yutao Zhu , et al. · 2024

Continual pre-training (CPT) has been an important approach for adapting language models to specific domains or tasks. To make the CPT approach more traceable, this paper presents a technical report for continually pre-training Llama-3 (8B…

YuLan: An Open-source Large Language Model Open

Yutao Zhu, Kun Zhou, Kelong Mao, Wentong Chen, Yiding Sun , et al. · 2024

Large language models (LLMs) have become the foundation of many applications, leveraging their extensive capabilities in processing and understanding natural language. While many open-source LLMs have been released with technical reports, …

RoLD: Robot Latent Diffusion for Multi-task Policy Modeling Open

Wenhui Tan, Bei Liu, Junbo Zhang, Ruihua Song, Jianlong Fu · 2024

Modeling generalized robot control policies poses ongoing challenges for language-guided robot manipulation tasks. Existing methods often struggle to efficiently utilize cross-dataset resources or rely on resource-intensive vision-language…

Intelligent Virtual Assistants with LLM-based Process Automation Open

Yanchu Guan, Dong Wang, Zhixuan Chu, Shiyu Wang, Feiyue Ni , et al. · 2023

While intelligent virtual assistants like Siri, Alexa, and Google Assistant have become ubiquitous in modern life, they still face limitations in their ability to follow multi-step instructions and accomplish complex goals articulated in n…

Parrot: Enhancing Multi-Turn Instruction Following for Large Language Models Open

Yuchong Sun, Che Liu, Jinwen Huang, Ruihua Song, Fuzheng Zhang , et al. · 2023

Humans often interact with large language models (LLMs) in multi-turn interaction to obtain desired answers or more information. However, most existing studies overlook the multi-turn instruction following ability of LLMs, in terms of trai…

User Behavior Simulation with Large Language Model based Agents Open

Lei Wang, Jingsen Zhang, Xu Chen, Yankai Lin, Ruihua Song , et al. · 2023

Simulating high quality user behavior data has always been a fundamental problem in human-centered applications, where the major difficulty originates from the intricate mechanism of human decision process. Recently, substantial evidences …

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) Open

Yang Chair, Alexa Liu, Anna Rogers, Walid Magdy, Daniel Preoțiuc-Pietro , et al. · 2023

Message from the Program ChairsIt's hard to believe that we're actually going to be seeing the program come together in Toronto.We're really looking forward to it and to seeing you all there!Most of the work of a program chair is behind th…

Findings of the Association for Computational Linguistics: ACL 2023 Open

Yang Chair, Alexa Liu, Anna Rogers, Walid Magdy, Daniel Preoțiuc-Pietro , et al. · 2023

Message from the Program ChairsIt's hard to believe that we're actually going to be seeing the program come together in Toronto.We're really looking forward to it and to seeing you all there!Most of the work of a program chair is behind th…

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) Open

Yang Chair, Alexa Liu, Anna Rogers, Yang Liu, Jordan Boyd‐Graber , et al. · 2023

Message from the Program ChairsIt's hard to believe that we're actually going to be seeing the program come together in Toronto.We're really looking forward to it and to seeing you all there!Most of the work of a program chair is behind th…

Stylistic Retrieval-based Dialogue System with Unparallel Training Data Open

Hao Fu, Yan Wang, Ruihua Song, Tianran Hu, Jian‐Yun Nie · 2021

The ability of a dialog system to express consistent language style during conversations has a direct, positive impact on its usability and on user satisfaction. Although previous studies have demonstrated that style transfer is feasible w…

SogouQ: The First Large-Scale Test Collection with Click Streams Used in a Shared-Task Evaluation Open

Ruihua Song, Min Zhang, Cheng Luo, Tetsuya Sakai, Yiqun Liu , et al. · 2020

Song, Ruihua Zhang, Min Luo, Cheng Sakai, Tetsuya Liu, Yiqun Dou, ZhichengSearch logs are very precious for information retrieval studies. In this chapter, we will introduce a real Chinese query log dataset, SogouQ, which was released by S…

ScriptWriter: Narrative-Guided Script Generation Open

Yutao Zhu, Ruihua Song, Zhicheng Dou, Jian‐Yun Nie, Jin Zhou · 2020

It is appealing to have a system that generates a story or scripts automatically from a story-line, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this pap…

"Love is as Complex as Math": Metaphor Generation System for Social Chatbot Open

Danning Zheng, Ruihua Song, Tianran Hu, Hao Fu, Zhou Jin · 2020

As the wide adoption of intelligent chatbot in human daily life, user demands for such systems evolve from basic task-solving conversations to more casual and friend-like communication. To meet the user needs and build emotional bond with …

ScriptWriter: Narrative-Guided Script Generation Open

Yutao Zhu, Ruihua Song, Zhicheng Dou, Jian‐Yun Nie, Jin Zhou · 2020

It is appealing to have a system that generates a story or scripts automatically from a storyline, even though this is still out of our reach. In dialogue systems, it would also be useful to drive dialogues by a dialogue plan. In this pape…

Attitude Detection for One-Round Conversation: Jointly Extracting Target-Polarity Pairs Open

Zhaohao Zeng, Ruihua Song, Pingping Lin, Tetsuya Sakai · 2019

We tackle Attitude Detection, which we define as the task of extracting the replier's attitude, i.e., a target-polarity pair, from a given one-round conversation. While previous studies considered Target Extraction and Polarity Classificat…

Understanding People Lifestyles: Construction of Urban Movement Knowledge Graph from GPS Trajectory Open

Chenyi Zhuang, Nicholas Jing Yuan, Ruihua Song, Xing Xie, Qiang Ma · 2017

Technologies are increasingly taking advantage of the explosion in the amount of data generated by social multimedia (e.g., web searches, ad targeting, and urban computing). In this paper, we propose a multi-view learning framework for pre…

A World of Difference: Divergent Word Interpretations Among People Open

Tianran Hu, Ruihua Song, Maya Ravindranath Abtahian, Philip Ding, Xing Xie , et al. · 2017

Divergent word usages reflect differences among people. In this paper, we present a novel angle for studying word usage divergence — word interpretations. We propose an approach that quantifies semantic differences in interpretations among…

A World of Difference: Divergent Word Interpretations among People Open

Tianran Hu, Ruihua Song, Maya Ravindranath Abtahian, Philip Ding, Xing Xie , et al. · 2017

Divergent word usages reflect differences among people. In this paper, we present a novel angle for studying word usage divergence -- word interpretations. We propose an approach that quantifies semantic differences in interpretations amon…

UniClip: Leveraging Web Search for Universal Clipping of Articles on Mobile Open

Ruihua Song, Kazutoshi Umemoto, Jian‐Yun Nie, Xing Xie, Katsumi Tanaka , et al. · 2016

In this paper we address the difficulty of clipping articles from mobile apps. We propose a service called UniClip that allows a user to save the full content of an article by snapping a screenshot part of it. UniClip leverages a huge amou…

Ruihua Song YOU? Author Swipe