<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Y. Wu | 刘均 | 西安交通大学</title><link>https://liujun-xjtu.github.io/zh/authors/y.-wu/</link><atom:link href="https://liujun-xjtu.github.io/zh/authors/y.-wu/index.xml" rel="self" type="application/rss+xml"/><description>Y. Wu</description><generator>HugoBlox Kit (https://hugoblox.com)</generator><language>zh-Hans</language><lastBuildDate>Thu, 01 Jan 2026 00:00:00 +0000</lastBuildDate><item><title>AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality</title><link>https://liujun-xjtu.github.io/zh/publication/agtao-robust-and-stabilized-llm-unlearning-via-adversarial-gating-training-with-adaptive-orthogonali/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/agtao-robust-and-stabilized-llm-unlearning-via-adversarial-gating-training-with-adaptive-orthogonali/</guid><description/></item><item><title>Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models</title><link>https://liujun-xjtu.github.io/zh/publication/beyond-layer-wise-merging-chain-of-merging-for-vision-language-models/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/beyond-layer-wise-merging-chain-of-merging-for-vision-language-models/</guid><description/></item><item><title>Memory-Enriched Thought-by-Thought Framework for Complex Diagram Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/memory-enriched-thought-by-thought-framework-for-complex-diagram-question-answering/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/memory-enriched-thought-by-thought-framework-for-complex-diagram-question-answering/</guid><description/></item><item><title>OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving</title><link>https://liujun-xjtu.github.io/zh/publication/optiverse-a-comprehensive-benchmark-towards-optimization-problem-solving/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/optiverse-a-comprehensive-benchmark-towards-optimization-problem-solving/</guid><description/></item><item><title>PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving</title><link>https://liujun-xjtu.github.io/zh/publication/physprm-a-generative-process-reward-model-with-fine-grained-diagnosis-for-physics-problem-solving/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/physprm-a-generative-process-reward-model-with-fine-grained-diagnosis-for-physics-problem-solving/</guid><description/></item><item><title>SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More</title><link>https://liujun-xjtu.github.io/zh/publication/sketchvl-policy-optimization-via-fine-grained-credit-assignment-for-chart-understanding-and-more/</link><pubDate>Thu, 01 Jan 2026 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/sketchvl-policy-optimization-via-fine-grained-credit-assignment-for-chart-understanding-and-more/</guid><description/></item><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>Cognitive Predictive Coding Network: Rethinking the Generalization in Raven Progressive Matrices</title><link>https://liujun-xjtu.github.io/zh/publication/cognitive-predictive-coding-network-rethinking-the-generalization-in-raven-progressive-matrices/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/cognitive-predictive-coding-network-rethinking-the-generalization-in-raven-progressive-matrices/</guid><description/></item><item><title>Diagram-driven course questions generation</title><link>https://liujun-xjtu.github.io/zh/publication/diagram-driven-course-questions-generation/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/diagram-driven-course-questions-generation/</guid><description/></item><item><title>LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory</title><link>https://liujun-xjtu.github.io/zh/publication/lfsrm-few-shot-diagram-sentence-matching-via-local-feedback-self-regulating-memory/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/lfsrm-few-shot-diagram-sentence-matching-via-local-feedback-self-regulating-memory/</guid><description/></item><item><title>PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning</title><link>https://liujun-xjtu.github.io/zh/publication/physreason-a-comprehensive-benchmark-towards-physics-based-reasoning/</link><pubDate>Wed, 01 Jan 2025 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/physreason-a-comprehensive-benchmark-towards-physics-based-reasoning/</guid><description/></item><item><title>Diagram Visual Grounding: Learning to See with Gestalt-Perceptual Attention</title><link>https://liujun-xjtu.github.io/zh/publication/diagram-visual-grounding-learning-to-see-with-gestalt-perceptual-attention/</link><pubDate>Sun, 01 Jan 2023 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/diagram-visual-grounding-learning-to-see-with-gestalt-perceptual-attention/</guid><description/></item><item><title>GPTR: Gestalt-Perception Transformer for Diagram Object Detection</title><link>https://liujun-xjtu.github.io/zh/publication/gptr-gestalt-perception-transformer-for-diagram-object-detection/</link><pubDate>Sun, 01 Jan 2023 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/gptr-gestalt-perception-transformer-for-diagram-object-detection/</guid><description/></item><item><title>MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering</title><link>https://liujun-xjtu.github.io/zh/publication/matchprompt-prompt-based-open-relation-extraction-with-semantic-consistency-guided-clustering/</link><pubDate>Sat, 01 Jan 2022 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/matchprompt-prompt-based-open-relation-extraction-with-semantic-consistency-guided-clustering/</guid><description/></item><item><title>MuL-GRN: Multi-Level Graph Relation Network for Few-Shot Node Classification</title><link>https://liujun-xjtu.github.io/zh/publication/mul-grn-multi-level-graph-relation-network-for-few-shot-node-classification/</link><pubDate>Sat, 01 Jan 2022 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/mul-grn-multi-level-graph-relation-network-for-few-shot-node-classification/</guid><description/></item><item><title>Spatial-Semantic Collaborative Graph Network for Textbook Question Answering</title><link>https://liujun-xjtu.github.io/zh/publication/spatial-semantic-collaborative-graph-network-for-textbook-question-answering/</link><pubDate>Sat, 01 Jan 2022 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/spatial-semantic-collaborative-graph-network-for-textbook-question-answering/</guid><description/></item><item><title>TGIN: Translation-Based Graph Inference Network for Few-Shot Relational Triplet Extraction</title><link>https://liujun-xjtu.github.io/zh/publication/tgin-translation-based-graph-inference-network-for-few-shot-relational-triplet-extraction/</link><pubDate>Sat, 01 Jan 2022 00:00:00 +0000</pubDate><guid>https://liujun-xjtu.github.io/zh/publication/tgin-translation-based-graph-inference-network-for-few-shot-relational-triplet-extraction/</guid><description/></item></channel></rss>