刘均 | Jun Liu
  • 基本信息
  • 科研情况
  • 教学情况
  • English CV
  • Publications
    • AGT^AO: Robust and Stabilized LLM Unlearning via Adversarial Gating Training with Adaptive Orthogonality
    • Beyond Layer-Wise Merging: Chain-of-Merging for Vision-Language Models
    • Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving
    • Explainable Visual Question Answering: A Survey on Methods, Datasets and Evaluation
    • Exploring Knowledge Conflicts for Faithful LLM Reasoning: Benchmark and Method
    • GeoLaux: A Benchmark for Evaluating MLLMs Geometry Performance on Long-Step Problems Requiring Auxiliary Lines
    • GKG-LLM: A unified framework for generalized knowledge graph construction
    • Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
    • MAPS: Multi-Agent Personality Shaping for Collaborative Reasoning
    • MARS: Multi-Agent Adaptive Reasoning with Socratic Guidance for Automated Prompt Optimization
    • MAXS: Meta-Adaptive Exploration with LLM Agents
    • Memory-Enriched Thought-by-Thought Framework for Complex Diagram Question Answering
    • MUR: Momentum Uncertainty guided Reasoning for Large Language Models
    • Neurodynamics-Driven Coupled Neural P Systems for Multi-Focus Image Fusion
    • OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
    • PhysPRM: A Generative Process Reward Model with Fine-grained Diagnosis for Physics Problem Solving
    • Reasoning step by step via a neural-symbolic geometry problem solver
    • SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More
    • Spiking Neural P Systems Incorporating Winner-take-all Mechanism
    • Towards Efficient and Robust Linguistic Emotion Diagnosis for Mental Health via Multi-Agent Instruction Refinement
    • A Unified Optimal Transport Framework for Cross-Modal Retrieval with Noisy Labels
    • Are Large Language Models Really Good Logical Reasoners? A Comprehensive Evaluation and Beyond
    • B2BGAN: A Backbone-to-Branches GAN-based Oversampling Approach for Class-Imbalanced Tabular Data
    • Causal-R: A Causal-Reasoning Geometry Problem Solver for Optimized Solution Exploration
    • ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
    • CoFFT: Chain of Foresight-Focus Thought for Visual Language Models
    • Cognitive Predictive Coding Network: Rethinking the Generalization in Raven Progressive Matrices
    • Debate on Graph: a Flexible and Reliable Reasoning Framework for Large Language Models
    • Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
    • Deliberation on Priors: Trustworthy Reasoning of LLMs on Knowledge Graphs
    • Diagram-driven course questions generation
    • EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
    • Genius: A Generalizable and Purely Unsupervised Self-Training Framework For Advanced Reasoning
    • GeoTree: A Dynamic Tree-based Geometry Problem Solver through LLM-Symbolic Reasoning
    • GlFoMR: A Glance-then-Focus Multimodal Reasoning Framework for Diagram Question Answering
    • Hierarchy-Based Diagram-Sentence Matching on Dual-Modal Graphs
    • Interactive Evolution: A Neural-Symbolic Self-Training Framework For Large Language Models
    • LFSRM: Few-Shot Diagram-Sentence Matching via Local-Feedback Self-Regulating Memory
    • Logic-Aware Knowledge Graph Reasoning for Structural Sparsity under LLM Supervision
    • Machine Memory Intelligence: Inspired by Human Memory Mechanisms
    • Metapath and Hypergraph Structure-based Multi-Channel Graph Contrastive Learning for Student Performance Prediction
    • PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning
    • ResoFilter: Fine-grained Synthetic Data Filtering for LLMs through Data-Parameter Resonance Analysis
    • Rethinking Continual Knowledge Graph Embedding: Benchmarks and Analysis
    • SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
    • VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning
    • When Multi-focus Image Fusion Meets Nonlinear Spiking Neural P Systems
    • A Semantic Mention Graph Augmented Model for Document-Level Event Argument Extraction
    • A Symbolic Rule Integration Framework with Logic Transformer for Inductive Relation Prediction
    • Alignment Relation is What You Need for Diagram Parsing
    • CoG-DQA: Chain-of-Guiding Learning with Large Language Models for Diagram Question Answering
    • Context-Aware Commonsense Knowledge Graph Reasoning with Path-Guided Explanations
    • E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator
    • FPrompt-PLM: Flexible-Prompt on Pretrained Language Model for Continual Few-Shot Relation Extraction
    • Interest-Driven Community Detection on Attributed Heterogeneous Information Networks
    • Knowledge Graph Representation Learning with Relation-guided Aggregation and Interaction
    • LAFA: Multimodal Knowledge Graph Completion with Link Aware Fusion and Aggregation
    • Learnable Convolutional Attention Network for Knowledge Graph Completion
    • Learning Path Recommendation with Multi-behavior User Modeling and Cascading Deep Q Networks
    • Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
    • Mixed Geometry Message and Trainable Convolutional Attention Network for KG Completion
    • Multi-View Cognition with Path Search for One-Shot Part Labeling
    • PathReasoner: Modeling Reasoning Path with Equivalent Extension for Logical Question Answering
    • QGEval: Benchmarking Multi-dimensional Evaluation for Question Generation
    • Robust Visual Question Answering: Datasets, Methods, and Future Challenges
    • RTRL: Relation-aware Transformer with Reinforcement Learning for Deep Question Generation
    • Symbol-LLM: Towards Foundational Symbol-centric Interface For Large Language Models
    • TDGI: Translation-Guided Double-Graph Inference for Document-Level Relation Extraction
    • Untargeted Adversarial Attack on Knowledge Graph Embeddings
    • When Phrases Meet Probabilities: Enabling Open Relation Extraction with Cooperating Large Language Models
    • B2-Sampling: Fusing Balanced and Biased Sampling for Graph Contrastive Learning
    • Diagram Perception Networks for Textbook Question Answering via Joint Optimization
    • Diagram Visual Grounding: Learning to See with Gestalt-Perceptual Attention
    • DisAVR: Disentangled Adaptive Visual Reasoning Network for Diagram Question Answering
    • Dynamic Dual Graph Networks for Textbook Question Answering
    • GBTTE: Graph Attention Network Based Bus Travel Time Estimation
    • GPTR: Gestalt-Perception Transformer for Diagram Object Detection
    • Incorporating Logic Rules with Textual Representations for Interpretable Knowledge Graph Reasoning
    • Mind Reasoning Manners: Enhancing Type Perception for Generalized Zero-shot Logical Reasoning over Text
    • MoCA: Incorporating Domain Pretraining and Cross Attention for Textbook Question Answering
    • Relation-Aware Multi-Positive Contrastive Knowledge Graph Completion
    • RPMG-FSS: Robust Prior Mask Guided Few-Shot Semantic Segmentation
    • SocialSift: Target Query Discovery on Online Social Media With Deep Reinforcement Learning
    • Synthesize, Prompt and Transfer: Zero-shot Conversational Question Generation
    • TECHS: Temporal Logical Graph Networks for Explainable Extrapolation Reasoning
    • XTQA: Span-Level Explanations for Textbook Question Answering
    • Answering Knowledge-based Visual Questions via the Exploration of Question Purpose
    • BusWTE: Realtime Bus Waiting Time Estimation of GPS Missing via Multi-Task Learning
    • Computer Science Diagram Understanding with Topology Parsing
    • Du-Bus: A Realtime Bus Waiting Time Estimation System Based On Multi-source Data
    • Fusing Topology Contexts and Logical Rules in Language Models for KG Completion
    • Generating Relevant and Informative Questions for Open-domain Conversations
    • Incorporating Context Graph with Logical Reasoning for Inductive Relation Prediction
    • Incorporating Prior Type Information for Few-shot Knowledge Graph Completion
    • Inductive Relation Prediction with Logical Reasoning Using Contrastive Representations
    • Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
    • MatchPrompt: Prompt-based Open Relation Extraction with Semantic Consistency Guided Clustering
    • MuL-GRN: Multi-Level Graph Relation Network for Few-Shot Node Classification
    • Multistructure Contrastive Learning for Event Representation
    • Spatial-Semantic Collaborative Graph Network for Textbook Question Answering
    • TGIN: Translation-Based Graph Inference Network for Few-Shot Relational Triplet Extraction
    • TN-ZSTAD: Transferable Network for Zero-Shot Temporal Activity Detection
    • Weakly Supervised Learning for Textbook Question Answering
    • Auto-FSL: Searching the Attribute Consistent Network for Few-Shot Learning
    • Contrastive Graph Representations for Logical Formulas Embedding
    • CSDQA: Diagram Question Answering in Computer Science
    • Fs-DSM: Few-Shot Diagram-Sentence Matching via Cross-Modal Attention Graph Model
    • Keep and Select: Improving Hierarchical Context Modeling for Multi-turn Response Generation
    • Multi-Task Learning for Visual Question Answering
    • Relation-aware Fine-grained Reasoning Network for Textbook Question Answering
    • Reliable Recommendation with Review-level Explanations
    • Rule-Enhanced Iterative Complementation for Knowledge Graph Reasoning
    • 知识森林：理论、方法与实践
    • Faceted Text Segmentation via Multi-Task Learning
    • Few-Shot Activity Recognition with Cross-Modal Memory Network
    • Fine-grained 3D-Attention Prototypes for Few-Shot Learning
    • Weakly Supervised Group Mask Network for Object Detection
    • ZSTAD: Zero-Shot Temporal Activity Detection
    • AHNG: Representation Learning on Attributed Heterogeneous Network
    • Deep Top-k Ranking for Image-Sentence Matching
    • Jointly Optimized Neural Coreference Resolution with Mutual Attention
    • Knowledge Forest: A Novel Model to Organize Knowledge Fragments
    • Scheduled Sampling for One-Shot Learning via Matching Network
    • A Deep Multi-Modal CNN for Multi-Instance Multi-Label Image Classification
    • Android Malware Familial Classification via Frequent Subgraph Analysis
    • CTDroid: Leveraging a Corpus of Technical Blogs for Android Malware Analysis
    • Facet Annotation by Extending CNN with a Matching Strategy
    • Graph Embedding based Familial Analysis of Android Malware
    • Graph Embedding based Query Construction over Knowledge Graphs
    • Towards Empty Answers in SPARQL: Approximating Querying with RDF Embedding
    • DAPASA: Detecting Android Piggybacked Apps through Sensitive Subgraph Analysis
    • Internet Traffic Classification Based on Expanding Vector of Flow
    • Knowledge Engineering with Big Data (BigKE)
    • DFT-extractor: A System to Extract Domain-specific Faceted Taxonomies from Wikipedia
    • Faceted Exploring for Domain Knowledge over Linked Open Data
    • Faceted Fusion of RDF Data
    • Frequent Subgraph based Familial Classification of Android Malware
    • Mining Learning-Dependency between Knowledge Units from Text
    • Motif-based Hyponym Relation Extraction from Wikipedia Hyperlinks
    • Sparse Multi-Modal Topical Coding for Image Annotation
    • Topological Analysis of Knowledge Maps
  • Research
  • Teaching

PhysReason: A Comprehensive Benchmark towards Physics-Based Reasoning

2025-01-01·
X. Zhang
,
Y. Dong
,
Y. Wu
,
J. Huang
,
C. Jia
,
B. Fernando
,
M. Shou
,
L. Zhang
,
J. Liu
· 0 min read
publication
Last updated on 2025-01-01
← Metapath and Hypergraph Structure-based Multi-Channel Graph Contrastive Learning for Student Performance Prediction 2025-01-01
ResoFilter: Fine-grained Synthetic Data Filtering for LLMs through Data-Parameter Resonance Analysis 2025-01-01 →
Languages:
English
中文 (简体)

© 2026 刘均 | 西安交通大学计算机学院

Made with Hugo Blox — Open Source. Build yours →