1 code implementation • NAACL (MIA) 2022 • Gengyu Wang, Cheng Qian, Lin Pan, Haode Qi, Ladislav Kunc, Saloni Potdar
Current virtual assistant (VA) platforms are beholden to the limited number of languages they support.
1 code implementation • 21 May 2025 • Cheng Qian, Hongyi Du, Hongru Wang, Xiusi Chen, Yuji Zhang, Avirup Sil, ChengXiang Zhai, Kathleen McKeown, Heng Ji
ModelingBench also supports multiple valid solutions, capturing the ambiguity and creativity of practical modeling.
1 code implementation • 5 May 2025 • Xiusi Chen, Gaotang Li, Ziqi Wang, Bowen Jin, Cheng Qian, Yu Wang, Hongru Wang, Yu Zhang, Denghui Zhang, Tong Zhang, Hanghang Tong, Heng Ji
The training of RM-R1 consists of two key stages: (1) distillation of high-quality reasoning chains and (2) reinforcement learning with verifiable rewards.
no code implementations • 21 Apr 2025 • Hongru Wang, Cheng Qian, Wanjun Zhong, Xiusi Chen, Jiahao Qiu, Shijue Huang, Bowen Jin, Mengdi Wang, Kam-Fai Wong, Heng Ji
Tool-integrated reasoning (TIR) augments large language models (LLMs) with the ability to invoke external tools, such as search engines and code interpreters, to solve tasks beyond the capabilities of language-only reasoning.
no code implementations • 16 Apr 2025 • Cheng Qian, Emre Can Acikgoz, Qi He, Hongru Wang, Xiusi Chen, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji
In this work, we present the first comprehensive study on reward design for tool selection and application tasks within the RL paradigm.
1 code implementation • 9 Apr 2025 • Shujin Wu, Cheng Qian, Yi R., Fung, Paul Pu Liang, Heng Ji
In this work, we introduce Alice (pro{A}ctive {l}earning w{i}th tea{c}her's D{e}monstrations), a framework that leverages complementary knowledge between teacher and student to enhance the learning process. We probe the knowledge base of the teacher model by eliciting their uncertainty, and then use these insights together with teachers' responses as demonstrations to guide student models in self-generating improved responses for supervision.
1 code implementation • 7 Apr 2025 • Emre Can Acikgoz, Cheng Qian, Hongru Wang, Vardhan Dongre, Xiusi Chen, Heng Ji, Dilek Hakkani-Tür, Gokhan Tur
Recent advances in Large Language Models (LLMs) have propelled conversational AI from traditional dialogue systems into sophisticated agents capable of autonomous actions, contextual awareness, and multi-turn interactions with users.
no code implementations • 4 Apr 2025 • Bingxiang He, Wenbin Zhang, Jiaxi Song, Cheng Qian, Zixuan Fu, Bowen Sun, Ning Ding, Haiwen Hong, Longtao Huang, Hui Xue, Ganqu Cui, Wanxiang Che, Zhiyuan Liu, Maosong Sun
Preference learning is critical for aligning large language models (LLMs) with human values, yet its success hinges on high-quality datasets comprising three core components: Preference \textbf{A}nnotations, \textbf{I}nstructions, and \textbf{R}esponse Pairs.
1 code implementation • 3 Mar 2025 • Kunlun Zhu, Hongyi Du, Zhaochen Hong, Xiaocheng Yang, Shuyi Guo, Zhe Wang, Zhenhailong Wang, Cheng Qian, Xiangru Tang, Heng Ji, Jiaxuan You
Large Language Models (LLMs) have shown remarkable capabilities as autonomous agents, yet existing benchmarks either focus on single-agent tasks or are confined to narrow domains, failing to capture the dynamics of multi-agent coordination and competition.
no code implementations • 22 Feb 2025 • Yuji Zhang, Sha Li, Cheng Qian, Jiateng Liu, Pengfei Yu, Chi Han, Yi R. Fung, Kathleen McKeown, ChengXiang Zhai, Manling Li, Heng Ji
To address it, we propose a novel concept: knowledge overshadowing, where model's dominant knowledge can obscure less prominent knowledge during text generation, causing the model to fabricate inaccurate details.
1 code implementation • 17 Feb 2025 • Cheng Qian, Emre Can Acikgoz, Hongru Wang, Xiusi Chen, Avirup Sil, Dilek Hakkani-Tür, Gokhan Tur, Heng Ji
To support this paradigm, we introduce SMART-ER, a dataset spanning three domains, where reasoning alternates between parametric knowledge and tool-dependent steps, with each step enriched by rationales explaining when tools are necessary.
no code implementations • 13 Feb 2025 • Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, Heng Ji, huan zhang, Tong Zhang
Leveraging Multi-modal Large Language Models (MLLMs) to create embodied agents offers a promising avenue for tackling real-world tasks.
no code implementations • 3 Feb 2025 • Peixuan Han, Cheng Qian, Xiusi Chen, Yuji Zhang, Denghui Zhang, Heng Ji
Large language models (LLMs) have demonstrated exceptional capabilities across a wide range of tasks but also pose significant risks due to their potential to generate harmful content.
1 code implementation • 18 Dec 2024 • Cheng Qian, Peixuan Han, Qinyu Luo, Bingxiang He, Xiusi Chen, Yuji Zhang, Hongyi Du, Jiarui Yao, Xiaocheng Yang, Denghui Zhang, Yunzhu Li, Heng Ji
Language model agents excel in long-session planning and reasoning, but existing benchmarks primarily focus on goal-oriented tasks with explicit objectives, neglecting creative adaptation in unfamiliar environments.
no code implementations • 22 Oct 2024 • Haoran Lin, Xianzhi Yu, Kang Zhao, Lu Hou, Zongyuan Zhan, Stanislav Kamenev, Han Bao, Ting Hu, Mingkai Wang, Qixin Chang, Siyue Sui, Weihao Sun, Jiaxin Hu, Jun Yao, Zekun Yin, Cheng Qian, Ying Zhang, Yinfei Pan, Yu Yang, Weiguo Liu
In this work, we propose FastAttention which pioneers the adaptation of FlashAttention series for NPUs and low-resource GPUs to boost LLM inference efficiency.
1 code implementation • 18 Oct 2024 • Runchu Tian, Yanghao Li, Yuepeng Fu, Siyang Deng, Qinyu Luo, Cheng Qian, Shuo Wang, Xin Cong, Zhong Zhang, Yesai Wu, Yankai Lin, Huadong Wang, Xiaojiang Liu
These experiments reveal that while most current models are robust against the "lost in the middle" issue, there exist significant biases related to the spacing of relevant information pieces.
1 code implementation • 16 Oct 2024 • Yaxi Lu, Shenzhi Yang, Cheng Qian, Guirong Chen, Qinyu Luo, Yesai Wu, Huadong Wang, Xin Cong, Zhong Zhang, Yankai Lin, Weiwen Liu, Yasheng Wang, Zhiyuan Liu, Fangming Liu, Maosong Sun
The labeled data is used to train a reward model that simulates human judgment and serves as an automatic evaluator of the proactiveness of LLM agents.
no code implementations • 11 Oct 2024 • Cheng Qian, Xianglong Shi, Shanshan Yao, Yichen Liu, Fengming Zhou, Zishu Zhang, Junaid Akram, Ali Braytee, Ali Anaissi
We present a refined approach to biomedical question-answering (QA) services by integrating large language models (LLMs) with Multi-BERT configurations.
1 code implementation • 4 Oct 2024 • Shujin Wu, May Fung, Cheng Qian, Jeonghwan Kim, Dilek Hakkani-Tur, Heng Ji
To address this gap, we train LLMs that can ''interact to align'', essentially cultivating the meta-skill of LLMs to implicitly infer the unspoken personalized preferences of the current user through multi-turn conversations, and then dynamically align their following behaviors and responses to these inferred preferences.
no code implementations • 31 Aug 2024 • Cheng Qian, Hainan Zhang, Lei Sha, Zhiming Zheng
With the growing deployment of LLMs in daily applications like chatbots and content generation, efforts to ensure outputs align with human values and avoid harmful content have intensified.
no code implementations • 21 Aug 2024 • Haode Qi, Cheng Qian, Jian Ni, Pratyush Singh, Reza Fazeli, Gengyu Wang, Zhongzheng Shu, Eric Wayne, Juergen Bross
The VA system is expected to be a cost-efficient SaaS service with low training and inference time while achieving high accuracy even with a small number of training samples.
no code implementations • 25 Jul 2024 • Cheng Qian, Julen Urain, Kevin Zakka, Jan Peters
In this work, we introduce PianoMime, a framework for training a piano-playing agent using internet demonstrations.
no code implementations • 17 Jun 2024 • Bingxiang He, Ning Ding, Cheng Qian, Jia Deng, Ganqu Cui, Lifan Yuan, Huan-ang Gao, Huimin Chen, Zhiyuan Liu, Maosong Sun
For the first time, we show that zero-shot generalization during instruction tuning is a form of similarity-based generalization between training and test data at the instance level.
no code implementations • 15 Apr 2024 • Yuan Bi, Cheng Qian, Zhicheng Zhang, Nassir Navab, Zhongliang Jiang
Ultrasound (US) has been widely used in daily clinical practice for screening internal organs and guiding interventions.
no code implementations • 8 Mar 2024 • Jiayan Cao, Xueyu Zhu, Cheng Qian
from object detection and segmentation tasks, while these approaches require manual adjustments for curved objects, involve exhaustive searches on predefined anchors, require complex post-processing steps, and may lack flexibility when applied to real-world scenarios. In this paper, we propose a novel approach, LanePtrNet, which treats lane detection as a process of point voting and grouping on ordered sets: Our method takes backbone features as input and predicts a curve-aware centerness, which represents each lane as a point and assigns the most probable center point to it.
no code implementations • 22 Feb 2024 • Cheng Qian, Xiaoxian Lao, Chunguang Li
Most existing reconstruction-based methods only use normal samples to construct model.
1 code implementation • 14 Feb 2024 • Cheng Qian, Bingxiang He, Zhong Zhuang, Jia Deng, Yujia Qin, Xin Cong, Zhong Zhang, Jie zhou, Yankai Lin, Zhiyuan Liu, Maosong Sun
Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions.
no code implementations • 25 Jan 2024 • Cheng Qian, Shihao Liang, Yujia Qin, Yining Ye, Xin Cong, Yankai Lin, Yesai Wu, Zhiyuan Liu, Maosong Sun
This paper introduces Investigate-Consolidate-Exploit (ICE), a novel strategy for enhancing the adaptability and flexibility of AI agents through inter-task self-evolution.
no code implementations • 23 Oct 2023 • Cheng Qian, Lucas Glass, Nikos Sidiropoulos
Forecasting project expenses is a crucial step for businesses to avoid budget overruns and project failures.
1 code implementation • 8 Oct 2023 • Cheng Qian, Chenyan Xiong, Zhenghao Liu, Zhiyuan Liu
We first validate the efficacy of Toolink in harnessing the model's creativity and CoS ability on ChatGPT.
1 code implementation • 15 Sep 2023 • Cheng Qian, Xinran Zhao, Sherry Tongshuang Wu
Large language models (LLMs) acquire extensive knowledge during pre-training, known as their parametric knowledge.
no code implementations • 28 Jun 2023 • Cheng Qian, Di Xiu, Minghao Tian
In this technical report, we present the 2nd place solution of 2023 Waymo Open Sim Agents Challenge (WOSAC)[4].
2 code implementations • 23 May 2023 • Cheng Qian, Chi Han, Yi R. Fung, Yujia Qin, Zhiyuan Liu, Heng Ji
Additionally, we introduce the Creation Challenge dataset, featuring 2K diverse questions, to emphasize the necessity and benefits of LLMs' tool creation ability.
1 code implementation • 15 May 2023 • Yujia Qin, Cheng Qian, Xu Han, Yankai Lin, Huadong Wang, Ruobing Xie, Zhiyuan Liu, Maosong Sun, Jie zhou
In pilot studies, we find that after continual pre-training, the upgraded PLM remains compatible with the outdated adapted weights to some extent.
no code implementations • 2 May 2023 • Xinyan Li, Cheng Qian, Lucas Glass
Respiratory syncytial virus (RSV) is one of the most dangerous respiratory diseases for infants and young children.
3 code implementations • 17 Apr 2023 • Yujia Qin, Shengding Hu, Yankai Lin, Weize Chen, Ning Ding, Ganqu Cui, Zheni Zeng, Yufei Huang, Chaojun Xiao, Chi Han, Yi Ren Fung, Yusheng Su, Huadong Wang, Cheng Qian, Runchu Tian, Kunlun Zhu, Shihao Liang, Xingyu Shen, Bokai Xu, Zhen Zhang, Yining Ye, Bowen Li, Ziwei Tang, Jing Yi, Yuzhang Zhu, Zhenning Dai, Lan Yan, Xin Cong, Yaxi Lu, Weilin Zhao, Yuxiang Huang, Junxi Yan, Xu Han, Xian Sun, Dahai Li, Jason Phang, Cheng Yang, Tongshuang Wu, Heng Ji, Zhiyuan Liu, Maosong Sun
Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 18 representative tools and show the potential of current foundation models in skillfully utilizing tools.
no code implementations • 29 Mar 2023 • Yu-Hang Xiao, Lei Huang, David Ramírez, Cheng Qian, Hing Cheung So
To mitigate this issue, we present a recovery scheme that incorporates time-varying thresholds.
no code implementations • 16 Jan 2023 • Cheng Qian, Haode Qi, Gengyu Wang, Ladislav Kunc, Saloni Potdar
Out of Scope (OOS) detection in Conversational AI solutions enables a chatbot to handle a conversation gracefully when it is unable to make sense of the end-user query.
1 code implementation • 25 Oct 2022 • Yujia Qin, Cheng Qian, Jing Yi, Weize Chen, Yankai Lin, Xu Han, Zhiyuan Liu, Maosong Sun, Jie zhou
(3) How does the PLM's task knowledge change along the path connecting two minima?
1 code implementation • 8 May 2022 • Chaoqi Yang, Cheng Qian, Jimeng Sun
Our variant GOCPTE shows up to 1:2% and 5:5% fitness improvement on two datasets with about 20% speedup compared to the best model.
no code implementations • 13 Apr 2022 • Rakshith S Srinivasa, Cheng Qian, Brandon Theodorou, Jeffrey Spaeder, Cao Xiao, Lucas Glass, Jimeng Sun
More recently, the issue of diversity and inclusion in clinical trials is gaining importance.
no code implementations • 31 Jan 2022 • Cheng Qian, Kejun Huang, Lucas Glass, Rakshith S. Srinivasa, Jimeng Sun
Tensor completion aims at imputing missing entries from a partially observed tensor.
1 code implementation • 15 Jun 2021 • Chaoqi Yang, Cheng Qian, Navjot Singh, Cao Xiao, M Brandon Westover, Edgar Solomonik, Jimeng Sun
This paper addresses the above challenges by proposing augmented tensor decomposition (ATD), which effectively incorporates data augmentations and self-supervised learning (SSL) to boost downstream classification.
1 code implementation • 14 Jun 2021 • Chaoqi Yang, Navjot Singh, Cao Xiao, Cheng Qian, Edgar Solomonik, Jimeng Sun
Our MTC model explores tensor mode properties and leverages the hierarchy of resolutions to recursively initialize an optimization setup, and optimizes on the coupled system using alternating least squares.
no code implementations • 21 May 2021 • Cheng Qian
When a neuron's activation represents some symbolic element in the environment, each of its synapses can indicate a potential change to the element and its future state.
no code implementations • 11 May 2021 • Cheng Qian, Nikos Kargas, Cao Xiao, Lucas Glass, Nicholas Sidiropoulos, Jimeng Sun
Recovering such missing or noisy (under-reported) elements of the input tensor can be viewed as a generalized tensor completion problem.
no code implementations • 19 Dec 2020 • Yu-Hang Xiao, David Ramírez, Peter J. Schreier, Cheng Qian, Lei Huang
Target detection is an important problem in multiple-input multiple-output (MIMO) radar.
no code implementations • 8 Dec 2020 • Nikos Kargas, Cheng Qian, Nicholas D. Sidiropoulos, Cao Xiao, Lucas M. Glass, Jimeng Sun
Accurate prediction of the transmission of epidemic diseases such as COVID-19 is crucial for implementing effective mitigation measures.
no code implementations • 3 Nov 2020 • Kehan Long, Cheng Qian, Jorge Cortés, Nikolay Atanasov
Control barrier functions are widely used to enforce safety properties in robot motion planning and control.
Motion Planning
Robotics
no code implementations • 8 Oct 2020 • Ardavan Afshar, Kejing Yin, Sherry Yan, Cheng Qian, Joyce C. Ho, Haesun Park, Jimeng Sun
In particular, we define the N-th order tensor Wasserstein loss for the widely used tensor CP factorization and derive the optimization algorithm that minimizes it.
no code implementations • 25 Sep 2020 • Cheng Qian, Abdulkadir C. Yucel
Tensor decomposition methodologies are proposed to reduce the memory requirement of translation operator tensors arising in the fast multipole method-fast Fourier transform (FMM-FFT)-accelerated surface integral equation (SIE) simulators.
no code implementations • 29 Sep 2019 • Yuwen Yang, Feifei Gao, Cheng Qian, Guisheng Liao
Specifically, we first propose the eigenvalue based regression network (ERNet) and classification network (ECNet) to estimate the number of non-coherent sources, where the eigenvalues of the received signal covariance matrix and the source number are used as the input and the supervise label of the networks, respectively.
no code implementations • 27 Jul 2019 • Cheng Qian, Amin Emad, Nicholas D. Sidiropoulos
Time-course gene expression data is a rich source of information that can be used to unravel these complex processes, identify biomarkers of drug sensitivity and predict the response to a drug.
1 code implementation • 4 Jul 2019 • Tianxi Li, Cheng Qian, Elizaveta Levina, Ji Zhu
Graphical models are commonly used to represent conditional dependence relationships between variables.
no code implementations • 29 Oct 2018 • Cheng Qian, Nicholas D. Sidiropoulos, Magda Amiridi, Amin Emad
Predicting the response of cancer cells to drugs is an important problem in pharmacogenomics.