87 citations · 634 across the 83 of their papers we have counts for
83 papers
Stasis, Stasis, Triple Stasis
Keith R. Dienes, Lucien Heurtier, Fei Huang +2
Many theories of BSM physics predict the existence of large or infinite towers of decaying states. In a previous paper (arXiv:2111.04753) we pointed out that this can give rise to…
VDialogUE: A Unified Evaluation Benchmark for Visually-grounded Dialogue
Yunshui Li, Binyuan Hui, Zhaochao Yin +6
Visually-grounded dialog systems, which integrate multiple modes of communication such as text and visual inputs, have become an increasingly popular area of investigation. However…
ModelScope-Agent: Building Your Customizable Agent System with Open-source Large Language Models
Chenliang Li, Hehong Chen, Ming Yan +11
Large language models (LLMs) have recently demonstrated remarkable capabilities to comprehend human intentions, engage in reasoning, and design planning-like behavior. To further u…
Geo-Encoder: A Chunk-Argument Bi-Encoder Framework for Chinese Geographic Re-Ranking
Yong Cao, Ruixue Ding, Boli Chen +5
Chinese geographic re-ranking task aims to find the most relevant addresses among retrieved candidates, which is crucial for location-related services such as navigation maps. Unli…
Four years of multi-modal odometry and mapping on the rail vehicles
Yusheng Wang, Weiwei Song, Yi Zhang +5
Precise, seamless, and efficient train localization as well as long-term railway environment monitoring is the essential property towards reliability, availability, maintainability…
Wider and Deeper LLM Networks are Fairer LLM Evaluators
Xinghua Zhang, Bowen Yu, Haiyang Yu +5
Measuring the quality of responses generated by LLMs is a challenging task, particularly when it comes to evaluating whether the response is aligned with human preference. A novel…
A Preliminary Study of the Intrinsic Relationship between Complexity and Alignment
Yingxiu Zhao, Bowen Yu, Binyuan Hui +4
Training large language models (LLMs) with open-domain instruction data has yielded remarkable success in aligning to end tasks and human preferences. Extensive research has highli…
Global well-posedness and optimal time decay rates of solutions to the pressureless Euler-Navier-Stokes system
Feimin Huang, Houzhi Tang, Weiyuan Zou
In this paper, we present a new framework for the global well-posedness and large-time behavior of a two-phase flow system, which consists of the pressureless Euler equations and i…
PolyLM: An Open Source Polyglot Large Language Model
Xiangpeng Wei, Haoran Wei, Huan Lin +15
Large language models (LLMs) demonstrate remarkable ability to comprehend, reason, and generate following nature language instructions. However, the development of LLMs has been pr…
Muon collider signatures for a with a maximal coupling in
Jin Sun, Fei Huang, Xiao-Gang He
The gauged model is a candidate model for explaining the muon g-2 anomaly because the in the model has a natural normal coupling to muon. Due to other experi…
BUS:Efficient and Effective Vision-language Pre-training with Bottom-Up Patch Summarization
Chaoya Jiang, Haiyang Xu, Wei Ye +7
Vision Transformer (ViT) based Vision-Language Pre-training (VLP) models have demonstrated impressive performance in various tasks. However, the lengthy visual token sequences fed…
Unified Language Representation for Question Answering over Text, Tables, and Images
Bowen Yu, Cheng Fu, Haiyang Yu +2
When trying to answer complex questions, people often rely on multiple sources of information, such as visual, textual, and tabular data. Previous approaches to this problem have f…
CATS: A Pragmatic Chinese Answer-to-Sequence Dataset with Large Scale and High Quality
Liang Li, Ruiying Geng, Chengyang Fang +6
There are three problems existing in the popular data-to-text datasets. First, the large-scale datasets either contain noise or lack real application scenarios. Second, the dataset…
Universal Information Extraction with Meta-Pretrained Self-Retrieval
Xin Cong. Bowen Yu, Mengcheng Fang, Tingwen Liu +5
Universal Information Extraction~(Universal IE) aims to solve different extraction tasks in a uniform text-to-structure generation manner. Such a generation procedure tends to stru…
Speech-Text Dialog Pre-training for Spoken Dialog Understanding with Explicit Cross-Modal Alignment
Tianshu Yu, Haoyu Gao, Ting-En Lin +6
Recently, speech-text pre-training methods have shown remarkable success in many speech and natural language processing tasks. However, most previous pre-trained models are usually…
Combined analysis of the and reactions
Neng-Chang Wei, Ai-Chao Wang, Fei Huang
The recently released data on differential cross sections for from the A2 and BGOOD Collaborations are used to examine the theoretical model constructed in our prev…
Preference Ranking Optimization for Human Alignment
Feifan Song, Bowen Yu, Minghao Li +4
Large language models (LLMs) often contain misleading content, emphasizing the need to align them with human values to ensure secure AI systems. Reinforcement learning from human f…
Vanishing dissipation limit for non-isentropic Navier-Stokes equations with shock data
Feimin Huang, Teng Wang
This paper is concerned with the vanishing dissipation limiting problem of one-dimensional non-isentropic Navier-Stokes equations with shock data. The limiting problem was solved i…
Distinguishing thermal histories of dark matter from structure formation
Fei Huang, Yuan-Zhen Li, Jiang-Hao Yu
It is important to understand the implications of current observational constraints and potential signatures on the thermal history of dark matter. In this paper, we build the conn…
Multimodal Recommendation Dialog with Subjective Preference: A New Challenge and Benchmark
Yuxing Long, Binyuan Hui, Caixia Yuan1 +3
Existing multimodal task-oriented dialog data fails to demonstrate the diverse expressions of user subjective preferences and recommendation acts in the real-life shopping scenario…
Nuclear effects in extracting and a probe for short-range correlations
Xing-Hua Yang, Fei Huang, Ji Xu
We investigate the neutral-current neutrino-nucleon deep inelastic scattering with particular emphasis on short-range correlation and EMC effect, as well as their impact on the wea…
NaSGEC: a Multi-Domain Chinese Grammatical Error Correction Dataset from Native Speaker Texts
Yue Zhang, Bo Zhang, Haochen Jiang +4
We introduce NaSGEC, a new dataset to facilitate research on Chinese grammatical error correction (CGEC) for native speaker texts from multiple domains. Previous CGEC research prim…
Global Solutions of the Two-Dimensional Riemann Problem with Four-Shock Interactions for the Euler Equations for Potential Flow
Gui-Qiang G. Chen, Alexander Cliffe, Feimin Huang +2
We present a rigorous approach and related techniques to construct global solutions of the 2-D Riemann problem with four-shock interactions for the Euler equations for potential fl…
Unsupervised Dialogue Topic Segmentation with Topic-aware Utterance Representation
Haoyu Gao, Rui Wang, Ting-En Lin +4
Dialogue Topic Segmentation (DTS) plays an essential role in a variety of dialogue modeling tasks. Previous DTS methods either focus on semantic similarity or dialogue coherence to…