Search Results for author: Xinyi Yang

Found 28 papers, 11 papers with code

Understanding Aha Moments: from External Observations to Internal Mechanisms

no code implementations3 Apr 2025 Shu Yang, Junchao Wu, Xin Chen, Yunze Xiao, Xinyi Yang, Derek F. Wong, Di Wang

We demonstrate that the "aha moment" is externally manifested in a more frequent use of anthropomorphic tones for self-reflection and an adaptive adjustment of uncertainty based on problem difficulty.

Rethinking Prompt-based Debiasing in Large Language Models

no code implementations12 Mar 2025 Xinyi Yang, Runzhe Zhan, Derek F. Wong, Shu Yang, Junchao Wu, Lidia S. Chao

Investigating bias in large language models (LLMs) is crucial for developing trustworthy AI.

Prompt Engineering

Policy-to-Language: Train LLMs to Explain Decisions with Flow-Matching Generated Rewards

no code implementations18 Feb 2025 Xinyi Yang, Liang Zeng, Heng Dong, Chao Yu, Xiaoran Wu, Huazhong Yang, Yu Wang, Milind Tambe, Tonghan Wang

As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain their policies in natural language will be vital for reliable coexistence.

Learning to Plan with Personalized Preferences

no code implementations2 Feb 2025 Manjie Xu, Xinyi Yang, Wei Liang, Chi Zhang, Yixin Zhu

Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly in collaborative roles.

DENIAHL: In-Context Features Influence LLM Needle-In-A-Haystack Abilities

1 code implementation28 Nov 2024 Hui Dai, Dan Pechi, Xinyi Yang, Garvit Banga, Raghav Mantri

The Needle-in-a-haystack (NIAH) test is a general task used to assess language models' (LMs') abilities to recall particular information from long input context.

3D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensing

no code implementations31 Oct 2024 Binghao Huang, YiXuan Wang, Xinyi Yang, Yiyue Luo, Yunzhu Li

Tactile and visual perception are both crucial for humans to perform fine-grained interactions with their environment.

Imitation Learning

DetectRL: Benchmarking LLM-Generated Text Detection in Real-World Scenarios

1 code implementation31 Oct 2024 Junchao Wu, Runzhe Zhan, Derek F. Wong, Shu Yang, Xinyi Yang, Yulin Yuan, Lidia S. Chao

More importantly, we analyzed the potential impact of writing styles, model types, attack methods, the text lengths, and real-world human writing factors on different types of detectors.

Benchmarking LLM-generated Text Detection +1

VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Tasks

no code implementations7 Oct 2024 Ziyan Jiang, Rui Meng, Xinyi Yang, Semih Yavuz, Yingbo Zhou, Wenhu Chen

Our results show that VLM2Vec achieves an absolute average improvement of 10% to 20% over existing multimodal embedding models on both in-distribution and out-of-distribution datasets in MMEB.

Information Retrieval Language Modeling +7

ReGenesis: LLMs can Grow into Reasoning Generalists via Self-Improvement

no code implementations3 Oct 2024 Xiangyu Peng, Congying Xia, Xinyi Yang, Caiming Xiong, Chien-Sheng Wu, Chen Xing

We show that ReGenesis achieves superior performance on all in-domain and OOD settings tested compared to existing methods.

CityLight: A Universal Model for Coordinated Traffic Signal Control in City-scale Heterogeneous Intersections

no code implementations4 Jun 2024 Jinwei Zeng, Chao Yu, Xinyi Yang, Wenxuan Ao, Qianyue Hao, Jian Yuan, Yong Li, Yu Wang, Huazhong Yang

Our method, CityLight, features a universal representation module that not only aligns the state representations of intersections by reindexing their phases based on their semantics and designing heterogeneity-preserving observations, but also encodes the narrowed relative traffic relation types to project the neighborhood intersections onto a uniform relative traffic impact space.

Traffic Signal Control

Prefix Text as a Yarn: Eliciting Non-English Alignment in Foundation Language Model

no code implementations25 Apr 2024 Runzhe Zhan, Xinyi Yang, Derek F. Wong, Lidia S. Chao, Yue Zhang

While supervised fine-tuning (SFT) has been a straightforward approach for tailoring the output of foundation large language model (LLM) to specific preferences, concerns have been raised about the depth of this alignment, with some critiques suggesting it is merely "superficial".

Language Modeling Language Modelling +3

Transfer Learning of Real Image Features with Soft Contrastive Loss for Fake Image Detection

no code implementations25 Mar 2024 Ziyou Liang, Weifeng Liu, Run Wang, Mengjie Wu, Boheng Li, Yuyang Zhang, Lina Wang, Xinyi Yang

In the last few years, the artifact patterns in fake images synthesized by different generative models have been inconsistent, leading to the failure of previous research that relied on spotting subtle differences between real and fake.

Contrastive Learning Fake Image Detection +1

FOFO: A Benchmark to Evaluate LLMs' Format-Following Capability

1 code implementation28 Feb 2024 Congying Xia, Chen Xing, Jiangshu Du, Xinyi Yang, Yihao Feng, ran Xu, Wenpeng Yin, Caiming Xiong

This paper presents FoFo, a pioneering benchmark for evaluating large language models' (LLMs) ability to follow complex, domain-specific formats, a crucial yet underexamined capability for their application as AI agents.

A Dual Curriculum Learning Framework for Multi-UAV Pursuit-Evasion in Diverse Environments

no code implementations19 Dec 2023 Jiayu Chen, Guosheng Li, Chao Yu, Xinyi Yang, Botian Xu, Huazhong Yang, Yu Wang

In this work, we introduce a dual curriculum learning framework, named DualCL, which addresses multi-UAV pursuit-evasion in diverse environments and demonstrates zero-shot transfer ability to unseen scenarios.

Reinforcement Learning (RL) Zero-shot Generalization

MASP: Scalable GNN-based Planning for Multi-Agent Navigation

no code implementations5 Dec 2023 Xinyi Yang, Xinting Yang, Chao Yu, Jiayu Chen, Wenbo Ding, Huazhong Yang, Yu Wang

The high-level policy, the Goal Matcher, leverages a graph-based Self-Encoder and Cross-Encoder to optimize goal assignment by updating the agent and the goal graphs.

Reinforcement Learning (RL) Zero-shot Generalization

Active Neural Topological Mapping for Multi-Agent Exploration

no code implementations1 Nov 2023 Xinyi Yang, Yuxiang Yang, Chao Yu, Jiayu Chen, Jingchen Yu, Haibing Ren, Huazhong Yang, Yu Wang

In this paper, we propose Multi-Agent Neural Topological Mapping (MANTM) to improve exploration efficiency and generalization for multi-agent exploration tasks.

Deep Reinforcement Learning

Human-in-the-loop Machine Translation with Large Language Model

1 code implementation13 Oct 2023 Xinyi Yang, Runzhe Zhan, Derek F. Wong, Junchao Wu, Lidia S. Chao

The large language model (LLM) has garnered significant attention due to its in-context learning mechanisms and emergent capabilities.

In-Context Learning Language Modeling +6

Interpretable Sequence Clustering

1 code implementation3 Sep 2023 Junjie Dong, Xinyi Yang, Mudi Jiang, Lianyu Hu, Zengyou He

Categorical sequence clustering plays a crucial role in various fields, but the lack of interpretability in cluster assignments poses significant challenges.

Clustering

Learning Graph-Enhanced Commander-Executor for Multi-Agent Navigation

1 code implementation8 Feb 2023 Xinyi Yang, Shiyu Huang, Yiwen Sun, Yuxiang Yang, Chao Yu, Wei-Wei Tu, Huazhong Yang, Yu Wang

Goal-conditioned hierarchical reinforcement learning (HRL) provides a promising direction to tackle this challenge by introducing a hierarchical structure to decompose the search space, where the low-level policy predicts primitive actions in the guidance of the goals derived from the high-level policy.

Hierarchical Reinforcement Learning Multi-agent Reinforcement Learning +2

Intelligent Reflecting Surface assisted Integrated Sensing and Communication System

no code implementations11 Nov 2022 Zhiqing Wei, Xinyi Yang, Chunwei Meng, Xiaoyu Yang, Kaifeng Han, Chen Qiu, Huici Wu

This paper proves the efficiency of IRS enabled ISAC system, which motivates the implementation of IRS to enhance the sensing capability in ISAC system.

Integrated sensing and communication ISAC

Learning Efficient Multi-Agent Cooperative Visual Exploration

no code implementations12 Oct 2021 Chao Yu, Xinyi Yang, Jiaxuan Gao, Huazhong Yang, Yu Wang, Yi Wu

In this paper, we extend the state-of-the-art single-agent visual navigation method, Active Neural SLAM (ANS), to the multi-agent setting by introducing a novel RL-based planning module, Multi-agent Spatial Planner (MSP). MSP leverages a transformer-based architecture, Spatial-TeamFormer, which effectively captures spatial relations and intra-agent interactions via hierarchical spatial self-attentions.

Reinforcement Learning (RL) Visual Navigation

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

1 code implementation ICLR 2021 Tao Yu, Chien-Sheng Wu, Xi Victoria Lin, Bailin Wang, Yi Chern Tan, Xinyi Yang, Dragomir Radev, Richard Socher, Caiming Xiong

We present GraPPa, an effective pre-training approach for table semantic parsing that learns a compositional inductive bias in the joint representations of textual and tabular data.

Inductive Bias Language Modeling +4

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