<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>J. Ma | 刘均 | 西安交通大学</title><link>https://liujun-xjtu.github.io/zh/authors/j.-ma/</link><atom:link href="https://liujun-xjtu.github.io/zh/authors/j.-ma/index.xml" rel="self" type="application/rss+xml"/><description>J. Ma</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>zh-Hans</language><lastBuildDate>Wed, 01 Jan 2025 00:00:00 +0000</lastBuildDate><item><title>ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding</title><link>https://liujun-xjtu.github.io/zh/publication/chartsketcher-reasoning-with-multimodal-feedback-and-reflection-for-chart-understanding/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/chartsketcher-reasoning-with-multimodal-feedback-and-reflection-for-chart-understanding/</guid><description/></item><item><title>Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models</title><link>https://liujun-xjtu.github.io/zh/publication/debate-on-graph-a-flexible-and-reliable-reasoning-framework-for-large-language-models/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/debate-on-graph-a-flexible-and-reliable-reasoning-framework-for-large-language-models/</guid><description/></item><item><title>Deliberation on Priors: Trustworthy Reasoning of LLMs on Knowledge Graphs</title><link>https://liujun-xjtu.github.io/zh/publication/deliberation-on-priors-trustworthy-reasoning-of-llms-on-knowledge-graphs/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/deliberation-on-priors-trustworthy-reasoning-of-llms-on-knowledge-graphs/</guid><description/></item><item><title>EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding</title><link>https://liujun-xjtu.github.io/zh/publication/evochart-a-benchmark-and-a-self-training-approach-towards-real-world-chart-understanding/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/evochart-a-benchmark-and-a-self-training-approach-towards-real-world-chart-understanding/</guid><description/></item><item><title>Metapath and Hypergraph Structure-based Multi-Channel Graph Contrastive Learning for Student Performance Prediction</title><link>https://liujun-xjtu.github.io/zh/publication/metapath-and-hypergraph-structure-based-multi-channel-graph-contrastive-learning-for-student-perform/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/metapath-and-hypergraph-structure-based-multi-channel-graph-contrastive-learning-for-student-perform/</guid><description/></item><item><title>Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/look-listen-and-answer-overcoming-biases-for-audio-visual-question-answering/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/look-listen-and-answer-overcoming-biases-for-audio-visual-question-answering/</guid><description/></item><item><title>Robust Visual Question Answering: Datasets, Methods, and Future Challenges</title><link>https://liujun-xjtu.github.io/zh/publication/robust-visual-question-answering-datasets-methods-and-future-challenges/</link><pubDate>Mon, 01 Jan 2024 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/robust-visual-question-answering-datasets-methods-and-future-challenges/</guid><description/></item><item><title>Diagram Perception Networks for Textbook Question Answering via Joint Optimization</title><link>https://liujun-xjtu.github.io/zh/publication/diagram-perception-networks-for-textbook-question-answering-via-joint-optimization/</link><pubDate>Sun, 01 Jan 2023 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/diagram-perception-networks-for-textbook-question-answering-via-joint-optimization/</guid><description/></item><item><title>Dynamic Dual Graph Networks for Textbook Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/dynamic-dual-graph-networks-for-textbook-question-answering/</link><pubDate>Sun, 01 Jan 2023 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/dynamic-dual-graph-networks-for-textbook-question-answering/</guid><description/></item><item><title>XTQA: Span-Level Explanations for Textbook Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/xtqa-span-level-explanations-for-textbook-question-answering/</link><pubDate>Sun, 01 Jan 2023 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/xtqa-span-level-explanations-for-textbook-question-answering/</guid><description/></item><item><title>Weakly Supervised Learning for Textbook Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/weakly-supervised-learning-for-textbook-question-answering/</link><pubDate>Sat, 01 Jan 2022 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/weakly-supervised-learning-for-textbook-question-answering/</guid><description/></item><item><title>Multi-Task Learning for Visual Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/multi-task-learning-for-visual-question-answering/</link><pubDate>Fri, 01 Jan 2021 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/multi-task-learning-for-visual-question-answering/</guid><description/></item><item><title>Relation-aware Fine-grained Reasoning Network for Textbook Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/relation-aware-fine-grained-reasoning-network-for-textbook-question-answering/</link><pubDate>Fri, 01 Jan 2021 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/relation-aware-fine-grained-reasoning-network-for-textbook-question-answering/</guid><description/></item><item><title>Rule-Enhanced Iterative Complementation for Knowledge Graph Reasoning</title><link>https://liujun-xjtu.github.io/zh/publication/rule-enhanced-iterative-complementation-for-knowledge-graph-reasoning/</link><pubDate>Fri, 01 Jan 2021 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/rule-enhanced-iterative-complementation-for-knowledge-graph-reasoning/</guid><description/></item><item><title>Fine-grained 3D-Attention Prototypes for Few-Shot Learning</title><link>https://liujun-xjtu.github.io/zh/publication/fine-grained-3d-attention-prototypes-for-few-shot-learning/</link><pubDate>Wed, 01 Jan 2020 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/fine-grained-3d-attention-prototypes-for-few-shot-learning/</guid><description/></item><item><title>Jointly Optimized Neural Coreference Resolution with Mutual Attention</title><link>https://liujun-xjtu.github.io/zh/publication/jointly-optimized-neural-coreference-resolution-with-mutual-attention/</link><pubDate>Tue, 01 Jan 2019 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/jointly-optimized-neural-coreference-resolution-with-mutual-attention/</guid><description/></item><item><title>DFT-extractor: A System to Extract Domain-specific Faceted Taxonomies from Wikipedia</title><link>https://liujun-xjtu.github.io/zh/publication/dft-extractor-a-system-to-extract-domain-specific-faceted-taxonomies-from-wikipedia/</link><pubDate>Fri, 01 Jan 2016 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/dft-extractor-a-system-to-extract-domain-specific-faceted-taxonomies-from-wikipedia/</guid><description/></item><item><title>Motif-based Hyponym Relation Extraction from Wikipedia Hyperlinks</title><link>https://liujun-xjtu.github.io/zh/publication/motif-based-hyponym-relation-extraction-from-wikipedia-hyperlinks/</link><pubDate>Fri, 01 Jan 2016 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/motif-based-hyponym-relation-extraction-from-wikipedia-hyperlinks/</guid><description/></item></channel></rss>