Kaixin Ma

80 papers A* 11A 1B 4C 1Misc 1Journal 43Unranked 15
YearRankTypeTitle / Venue / Authors
2026 J jnl
NarrativeTrack: Evaluating Video Language Models Beyond the Frame.
CoRR
Hyeonjeong Ha, Jinjin Ge, Bo Feng, Kaixin Ma, Gargi Chakraborty
2026 J jnl
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models.
Trans. Mach. Learn. Res.
Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Hongming Zhang, Zhisong Zhang, Haitao Mi, Dong Yu
2026 — conf
WebRollback: Enhancing Web Agents with Explicit Rollback Mechanisms.
EACL (Volume 2: Short Papers)
Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, Dong Yu
2025 A* conf
COLUMBUS: Evaluating COgnitive Lateral Understanding Through Multiple-Choice reBUSes.
AAAI
Koen Kraaijveld, Yifan Jiang, Kaixin Ma, Filip Ilievski
2025 — conf
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots.
NAACL (System Demonstrations)
Hongming Zhang, Xiaoman Pan, Hongwei Wang, Kaixin Ma, Wenhao Yu, Dong Yu
2025 A* conf
DSBench: How Far Are Data Science Agents from Becoming Data Science Experts?
ICLR
Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, Dong Yu
2025 — conf
DivScene: Towards Open-Vocabulary Object Navigation with Large Vision Language Models in Diverse Scenes.
EMNLP (Findings)
Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
2025 J jnl
Enhancing Web Agents with Explicit Rollback Mechanisms.
CoRR
Zhisong Zhang, Tianqing Fang, Kaixin Ma, Wenhao Yu, Hongming Zhang, Haitao Mi, Dong Yu
2025 J jnl
Leopard: A Vision Language Model for Text-Rich Multi- Image Tasks.
Trans. Mach. Learn. Res.
Mengzhao Jia, Wenhao Yu, Kaixin Ma, Tianqing Fang, Zhihan Zhang, Siru Ouyang, Hongming Zhang, Dong Yu, Meng Jiang
2025 — conf
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization.
ACL (1)
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu
2025 A* conf
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph.
ICLR
Siru Ouyang, Wenhao Yu, Kaixin Ma, Zilin Xiao, Zhihan Zhang, Mengzhao Jia, Jiawei Han, Hongming Zhang, Dong Yu
2025 A* conf
Retrieval-augmented GUI Agents with Generative Guidelines.
EMNLP
Ran Xu, Kaixin Ma, Wenhao Yu, Hongming Zhang, Joyce C. Ho, Carl Yang, Dong Yu
2025 J jnl
Retrieval-augmented GUI Agents with Generative Guidelines.
CoRR
Ran Xu, Kaixin Ma, Wenhao Yu, Hongming Zhang, Joyce C. Ho, Carl Yang, Dong Yu
2025 J jnl
SO-Bench: A Structural Output Evaluation of Multimodal LLMs.
CoRR
Di Feng, Kaixin Ma, Feng Nan, Haofeng Chen, Bohan Zhai, David Griffiths, Mingfei Gao, Zhe Gan, Eshan Verma, Yinfei Yang, Zhifeng Chen, Afshin Dehghan
2025 J jnl
Understanding and Enhancing Mamba-Transformer Hybrids for Memory Recall and Language Modeling.
CoRR
Hyunji Lee, Wenhao Yu, Hongming Zhang, Kaixin Ma, Jiyeon Kim, Dong Yu, Minjoon Seo
2025 J jnl
VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models.
CoRR
Ce Zhang, Kaixin Ma, Tianqing Fang, Wenhao Yu, Hongming Zhang, Zhisong Zhang, Yaqi Xie, Katia P. Sycara, Haitao Mi, Dong Yu
2025 A* conf
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model.
EMNLP
Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, Dong Yu
2025 J jnl
WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model.
CoRR
Tianqing Fang, Hongming Zhang, Zhisong Zhang, Kaixin Ma, Wenhao Yu, Haitao Mi, Dong Yu
2024 J jnl
COLUMBUS: Evaluating COgnitive Lateral Understanding through Multiple-choice reBUSes.
CoRR
Koen Kraaijveld, Yifan Jiang, Kaixin Ma, Filip Ilievski
2024 A* conf
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models.
EMNLP
Wenhao Yu, Hongming Zhang, Xiaoman Pan, Peixin Cao, Kaixin Ma, Jian Li, Hongwei Wang, Dong Yu
2024 J jnl
Cognitive Kernel: An Open-source Agent System towards Generalist Autopilots.
CoRR
Hongming Zhang, Xiaoman Pan, Hongwei Wang, Kaixin Ma, Wenhao Yu, Dong Yu
2024 J jnl
DOCBENCH: A Benchmark for Evaluating LLM-based Document Reading Systems.
CoRR
Anni Zou, Wenhao Yu, Hongming Zhang, Kaixin Ma, Deng Cai, Zhuosheng Zhang, Hai Zhao, Dong Yu
2024 J jnl
DSBench: How Far Are Data Science Agents to Becoming Data Science Experts?
CoRR
Liqiang Jing, Zhehui Huang, Xiaoyang Wang, Wenlin Yao, Wenhao Yu, Kaixin Ma, Hongming Zhang, Xinya Du, Dong Yu
2024 A* conf
Dense X Retrieval: What Retrieval Granularity Should We Use?
EMNLP
Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, Dong Yu
2024 J jnl
DivScene: Benchmarking LVLMs for Object Navigation with Diverse Scenes and Objects.
CoRR
Zhaowei Wang, Hongming Zhang, Tianqing Fang, Ye Tian, Yue Yang, Kaixin Ma, Xiaoman Pan, Yangqiu Song, Dong Yu
2024 J jnl
Leopard: A Vision Language Model For Text-Rich Multi-Image Tasks.
CoRR
Mengzhao Jia, Wenhao Yu, Kaixin Ma, Tianqing Fang, Zhihan Zhang, Siru Ouyang, Hongming Zhang, Meng Jiang, Dong Yu
2024 A* conf
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning.
NeurIPS
Yifan Jiang, Jiarui Zhang, Kexuan Sun, Zhivar Sourati, Kian Ahrabian, Kaixin Ma, Filip Ilievski, Jay Pujara
2024 J jnl
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning.
CoRR
Yifan Jiang, Jiarui Zhang, Kexuan Sun, Zhivar Sourati, Kian Ahrabian, Kaixin Ma, Filip Ilievski, Jay Pujara
2024 J jnl
OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization.
CoRR
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Hongming Zhang, Tianqing Fang, Zhenzhong Lan, Dong Yu
2024 J jnl
RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph.
CoRR
Siru Ouyang, Wenhao Yu, Kaixin Ma, Zilin Xiao, Zhihan Zhang, Mengzhao Jia, Jiawei Han, Hongming Zhang, Dong Yu
2024 — conf
SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense.
SemEval@NAACL
Yifan Jiang, Filip Ilievski, Kaixin Ma
2024 J jnl
SemEval-2024 Task 9: BRAINTEASER: A Novel Task Defying Common Sense.
CoRR
Yifan Jiang, Filip Ilievski, Kaixin Ma
2024 — conf
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.
ACL (1)
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu
2024 J jnl
WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models.
CoRR
Hongliang He, Wenlin Yao, Kaixin Ma, Wenhao Yu, Yong Dai, Hongming Zhang, Zhenzhong Lan, Dong Yu
2023 A* conf
A Study of Situational Reasoning for Traffic Understanding.
KDD
Jiarui Zhang, Filip Ilievski, Kaixin Ma, Aravinda Kollaa, Jonathan Francis, Alessandro Oltramari
2023 J jnl
A Study of Situational Reasoning for Traffic Understanding.
CoRR
Jiarui Zhang, Filip Ilievski, Kaixin Ma, Aravinda Kollaa, Jonathan Francis, Alessandro Oltramari
2023 A* conf
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models.
EMNLP
Yifan Jiang, Filip Ilievski, Kaixin Ma, Zhivar Sourati
2023 J jnl
BRAINTEASER: Lateral Thinking Puzzles for Large Language Models.
CoRR
Yifan Jiang, Filip Ilievski, Kaixin Ma, Zhivar Sourati
2023 — ch.
Building Robust and Explainable AI with Commonsense Knowledge Graphs and Neural Models.
Compendium of Neurosymbolic Artificial Intelligence
Filip Ilievski, Kaixin Ma, Alessandro Oltramari, Peifeng Wang, Jay Pujara
2023 J jnl
Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models.
CoRR
Wenhao Yu, Hongming Zhang, Xiaoman Pan, Kaixin Ma, Hongwei Wang, Dong Yu
2023 — conf
Chain-of-Skills: A Configurable Model for Open-Domain Question Answering.
ACL (1)
Kaixin Ma, Hao Cheng, Yu Zhang, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2023 J jnl
Chain-of-Skills: A Configurable Model for Open-domain Question Answering.
CoRR
Kaixin Ma, Hao Cheng, Yu Zhang, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2023 J jnl
Dense X Retrieval: What Retrieval Granularity Should We Use?
CoRR
Tong Chen, Hongwei Wang, Sihao Chen, Wenhao Yu, Kaixin Ma, Xinran Zhao, Hongming Zhang, Dong Yu
2023 C conf
Generalizable Neuro-Symbolic Systems for Commonsense Question Answering.
NeSy
Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee
2023 — —
Hybrid Knowledge Architectures for Question Answering
Kaixin Ma
2023 B conf
Knowledge-enhanced Agents for Interactive Text Games.
K-CAP
Prateek Chhikara, Jiarui Zhang, Filip Ilievski, Jonathan Francis, Kaixin Ma
2023 J jnl
Knowledge-enhanced Agents for Interactive Text Games.
CoRR
Prateek Chhikara, Jiarui Zhang, Filip Ilievski, Jonathan Francis, Kaixin Ma
2023 J jnl
LASER: LLM Agent with State-Space Exploration for Web Navigation.
CoRR
Kaixin Ma, Hongming Zhang, Hongwei Wang, Xiaoman Pan, Dong Yu
2023 A conf
Transferring Procedural Knowledge Across Commonsense Tasks.
ECAI
Yifan Jiang, Filip Ilievski, Kaixin Ma
2023 J jnl
Transferring Procedural Knowledge across Commonsense Tasks.
CoRR
Yifan Jiang, Filip Ilievski, Kaixin Ma
2022 — conf
A Study of Zero-shot Adaptation with Commonsense Knowledge.
AKBC
Jiarui Zhang, Filip Ilievski, Kaixin Ma, Jonathan Francis, Alessandro Oltramari
2022 J jnl
An Empirical Investigation of Commonsense Self-Supervision with Knowledge Graphs.
CoRR
Jiarui Zhang, Filip Ilievski, Kaixin Ma, Jonathan Francis, Alessandro Oltramari
2022 B conf
Coalescing Global and Local Information for Procedural Text Understanding.
COLING
Kaixin Ma, Filip Ilievski, Jonathan Francis, Eric Nyberg, Alessandro Oltramari
2022 J jnl
Coalescing Global and Local Information for Procedural Text Understanding.
CoRR
Kaixin Ma, Filip Ilievski, Jonathan Francis, Eric Nyberg, Alessandro Oltramari
2022 J jnl
Generalizable Neuro-symbolic Systems for Commonsense Question Answering.
CoRR
Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee
2022 — conf
Open Domain Question Answering with A Unified Knowledge Interface.
ACL (1)
Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2022 — conf
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge.
EMNLP (Findings)
Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2022 J jnl
Open-domain Question Answering via Chain of Reasoning over Heterogeneous Knowledge.
CoRR
Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2022 J jnl
Utilizing Background Knowledge for Robust Reasoning over Traffic Situations.
CoRR
Jiarui Zhang, Filip Ilievski, Aravinda Kollaa, Jonathan Francis, Kaixin Ma, Alessandro Oltramari
2021 Misc conf
Audio-Visual Event Recognition Through the Lens of Adversary.
ICASSP
Juncheng B. Li, Kaixin Ma, Shuhui Qu, Po-Yao Huang, Florian Metze
2021 — conf
Building Goal-oriented Document-grounded Dialogue Systems.
DialDoc@ACL-IJCNLP
Xi Chen, Faner Lin, Yeju Zhou, Kaixin Ma, Jonathan Francis, Eric Nyberg, Alessandro Oltramari
2021 J jnl
Dimensions of Commonsense Knowledge.
CoRR
Filip Ilievski, Alessandro Oltramari, Kaixin Ma, Bin Zhang, Deborah L. McGuinness, Pedro A. Szekely
2021 J jnl
Dimensions of commonsense knowledge.
Knowl. Based Syst.
Filip Ilievski, Alessandro Oltramari, Kaixin Ma, Bin Zhang, Deborah L. McGuinness, Pedro A. Szekely
2021 — conf
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models.
EMNLP (1)
Kaixin Ma, Filip Ilievski, Jonathan Francis, Satoru Ozaki, Eric Nyberg, Alessandro Oltramari
2021 J jnl
Exploring Strategies for Generalizable Commonsense Reasoning with Pre-trained Models.
CoRR
Kaixin Ma, Filip Ilievski, Jonathan Francis, Satoru Ozaki, Eric Nyberg, Alessandro Oltramari
2021 — ch.
Generalizable Neuro-Symbolic Systems for Commonsense Question Answering.
Neuro-Symbolic Artificial Intelligence
Alessandro Oltramari, Jonathan Francis, Filip Ilievski, Kaixin Ma, Roshanak Mirzaee
2021 A* conf
Knowledge-driven Data Construction for Zero-shot Evaluation in Commonsense Question Answering.
AAAI
Kaixin Ma, Filip Ilievski, Jonathan Francis, Yonatan Bisk, Eric Nyberg, Alessandro Oltramari
2021 J jnl
Open Domain Question Answering over Virtual Documents: A Unified Approach for Data and Text.
CoRR
Kaixin Ma, Hao Cheng, Xiaodong Liu, Eric Nyberg, Jianfeng Gao
2021 B conf
PTWA: Pre-Training with Word Attention for Chinese Named Entity Recognition.
IJCNN
Kaixin Ma, Meiling Liu, Tiejun Zhao, Jiyun Zhou, Yang Yu
2020 J jnl
Audio-Visual Event Recognition through the lens of Adversary.
CoRR
Juncheng B. Li, Kaixin Ma, Shuhui Qu, Po-Yao Huang, Florian Metze
2020 J jnl
Knowledge-driven Self-supervision for Zero-shot Commonsense Question Answering.
CoRR
Kaixin Ma, Filip Ilievski, Jonathan Francis, Yonatan Bisk, Eric Nyberg, Alessandro Oltramari
2020 J jnl
Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection.
CoRR
Yikang Li, Pulkit Goel, Varsha Kuppur Rajendra, Har Simrat Singh, Jonathan Francis, Kaixin Ma, Eric Nyberg, Alessandro Oltramari
2020 — ch.
Neuro-Symbolic Architectures for Context Understanding.
Knowledge Graphs for eXplainable Artificial Intelligence
Alessandro Oltramari, Jonathan Francis, Cory A. Henson, Kaixin Ma, Ruwan Wickramarachchi
2020 J jnl
Neuro-symbolic Architectures for Context Understanding.
CoRR
Alessandro Oltramari, Jonathan Francis, Cory A. Henson, Kaixin Ma, Ruwan Wickramarachchi
2020 J jnl
Quantum witness of a damped and driven qubit by sequential intermediate measurements with uniform and nonuniform time intervals.
Quantum Inf. Process.
Longyan Gong, Kaixin Ma, Xiaoxin Zhao, Wei-Wen Cheng, Shengmei Zhao
2019 — conf
Bend but Don't Break? Multi-Challenge Stress Test for QA Models.
MRQA@EMNLP
Hemant Pugaliya, James Route, Kaixin Ma, Yixuan Geng, Eric Nyberg
2019 B conf
ElderReact: A Multimodal Dataset for Recognizing Emotional Response in Aging Adults.
ICMI
Kaixin Ma, Xinyu Wang, Xinru Yang, Mingtong Zhang, Jeffrey M. Girard, Louis-Philippe Morency
2019 J jnl
Towards Generalizable Neuro-Symbolic Systems for Commonsense Question Answering.
CoRR
Kaixin Ma, Jonathan Francis, Quanyang Lu, Eric Nyberg, Alessandro Oltramari
2018 — conf
Challenging Reading Comprehension on Daily Conversation: Passage Completion on Multiparty Dialog.
NAACL-HLT
Kaixin Ma, Tomasz Jurczyk, Jinho D. Choi
2017 — conf
Text-based Speaker Identification on Multiparty Dialogues Using Multi-document Convolutional Neural Networks.
ACL (Student Research Workshop)
Kaixin Ma, Catherine Xiao, Jinho D. Choi