no code implementations • 3 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.
no code implementations • 12 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.
no code implementations • 18 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.
no code implementations • 2 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.
1 code implementation • 28 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.
no code implementations • 31 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.
1 code implementation • 31 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.
no code implementations • 7 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.
no code implementations • 3 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.
no code implementations • 24 Sep 2024 • Jiayu Chen, Chao Yu, Guosheng Li, Wenhao Tang, Shilong Ji, Xinyi Yang, Botian Xu, Huazhong Yang, Yu Wang
Multi-UAV pursuit-evasion, where pursuers aim to capture evaders, poses a key challenge for UAV swarm intelligence.
Deep Reinforcement Learning
Multi-agent Reinforcement Learning
no code implementations • 4 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.
no code implementations • 25 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".
no code implementations • 25 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.
1 code implementation • 28 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.
no code implementations • 19 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.
no code implementations • 5 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.
no code implementations • 1 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.
1 code implementation • 13 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.
no code implementations • 25 Sep 2023 • Zhiqing Wei, Haotian Liu, Xinyi Yang, Wangjun Jiang, Huici Wu, Xingwang Li, Zhiyong Feng
The future mobile communication systems will support intelligent applications such as Internet of Vehicles (IoV) and Extended Reality (XR).
1 code implementation • 3 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.
1 code implementation • NeurIPS 2023 • Can Qin, Shu Zhang, Ning Yu, Yihao Feng, Xinyi Yang, Yingbo Zhou, Huan Wang, Juan Carlos Niebles, Caiming Xiong, Silvio Savarese, Stefano Ermon, Yun Fu, ran Xu
Visual generative foundation models such as Stable Diffusion show promise in navigating these goals, especially when prompted with arbitrary languages.
1 code implementation • CVPR 2024 • Shu Zhang, Xinyi Yang, Yihao Feng, Can Qin, Chia-Chih Chen, Ning Yu, Zeyuan Chen, Huan Wang, Silvio Savarese, Stefano Ermon, Caiming Xiong, ran Xu
Incorporating human feedback has been shown to be crucial to align text generated by large language models to human preferences.
1 code implementation • 8 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
2 code implementations • 9 Jan 2023 • Chao Yu, Xinyi Yang, Jiaxuan Gao, Jiayu Chen, Yunfei Li, Jijia Liu, Yunfei Xiang, Ruixin Huang, Huazhong Yang, Yi Wu, Yu Wang
Simply waiting for every robot being ready for the next action can be particularly time-inefficient.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
no code implementations • 11 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.
1 code implementation • 23 Mar 2022 • Tian Xie, Xinyi Yang, Angela S. Lin, Feihong Wu, Kazuma Hashimoto, Jin Qu, Young Mo Kang, Wenpeng Yin, Huan Wang, Semih Yavuz, Gang Wu, Michael Jones, Richard Socher, Yingbo Zhou, Wenhao Liu, Caiming Xiong
At the core of the struggle is the need to script every single turn of interactions between the bot and the human user.
no code implementations • 12 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.
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.
Ranked #8 on
Semantic Parsing
on spider