Xiangliang Zhang

A Survey of Multimodal Mathematical Reasoning: From Perception, Alignment to Reasoning ACL 2026 MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training ACL 2026 RiskLab: A Controlled Toolkit for Probing Emergent Risks in LLM-Based Multi-Agent Systems ACL 2026 Adaptive and Context-rich Generative Self-supervised Learning on Graphs AAAI 2026 Too Correct to Learn: Reinforcement Learning on Saturated Reasoning Data ACL 2026 SPA: Achieving Consensus in LLM Alignment via Self-Priority Optimization AAAI 2026 Better Datasets Start from RefineLab: Automatic Optimization for High-Quality Dataset Refinement AAAI 2026 RMO: Towards Better LLM Alignment via Reshaping Reward Margin Distributions AAAI 2026 Justice or Prejudice? Quantifying Biases in LLM-as-a-Judge ICLR 2025 Artificial Intelligence in Spectroscopy: Advancing Chemistry from Prediction To Generation and Beyond IJCAI 2025 Unlocking the Potential of Black-box Pre-trained GNNs for Graph Few-shot Learning AAAI 2025 Cross-Lingual Pitfalls: Automatic Probing Cross-Lingual Weakness of Multilingual Large Language Models ACL 2025 SEUF: Is Unlearning One Expert Enough for Mixture-of-Experts LLMs? ACL 2025 Shaping the Safety Boundaries: Understanding and Defending Against Jailbreaks in Large Language Models ACL 2025 CLIPErase: Efficient Unlearning of Visual-Textual Associations in CLIP ACL 2025 Beyond Single-Value Metrics: Evaluating and Enhancing LLM Unlearning with Cognitive Diagnosis ACL 2025 Towards Fair Graph Learning without Demographic Information AISTATS 2025 TRUSTEVAL: A Dynamic Evaluation Toolkit on Trustworthiness of Generative Foundation Models NAACL 2025 Invisible Entropy: Towards Safe and Efficient Low-Entropy LLM Watermarking EMNLP 2025 Quest2DataAgent: Automating End-to-End Scientific Data Collection EMNLP 2025 Dissecting Logical Reasoning in LLMs: A Fine-Grained Evaluation and Supervision Study EMNLP 2025 DataGen: Unified Synthetic Dataset Generation via Large Language Models ICLR 2025 Position: TrustLLM: Trustworthiness in Large Language Models ICML 2024 1+1>2: Can Large Language Models Serve as Cross-Lingual Knowledge Aggregators? EMNLP 2024 Defending Jailbreak Prompts via In-Context Adversarial Game EMNLP 2024 Large Language Model Based Multi-agents: A Survey of Progress and Challenges IJCAI 2024 RAt: Injecting Implicit Bias for Text-To-Image Prompt Refinement Models EMNLP 2024 HonestLLM: Toward an Honest and Helpful Large Language Model NIPS 2024 SaSR-Net: Source-Aware Semantic Representation Network for Enhancing Audio-Visual Question Answering EMNLP 2024 SceMQA: A Scientific College Entrance Level Multimodal Question Answering Benchmark ACL 2024 MinT: Boosting Generalization in Mathematical Reasoning via Multi-view Fine-tuning COLING 2024 Attack-free Evaluating and Enhancing Adversarial Robustness on Categorical Data ICML 2024 Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators NIPS 2024 Uncertainty-Aware Yield Prediction with Multimodal Molecular Features AAAI 2024 Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation NIPS 2024 Learning towards Selective Data Augmentation for Dialogue Generation AAAI 2023 Generalizing Math Word Problem Solvers via Solution Diversification AAAI 2023 Don’t be Blind to Questions: Question-Oriented Math Word Problem Solving AACL 2023 UniMath: A Foundational and Multimodal Mathematical Reasoner EMNLP 2023 Improving the Robustness of Summarization Systems with Dual Augmentation ACL 2023 Few-shot Low-resource Knowledge Graph Completion with Reinforced Task Generation ACL 2023 Compositional Mathematical Encoding for Math Word Problems ACL 2023 Let GPT be a Math Tutor: Teaching Math Word Problem Solvers with Customized Exercise Generation EMNLP 2023 Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency ICLR 2023 Don’t be Blind to Questions: Question-Oriented Math Word Problem Solving IJCNLP 2023 Character As Pixels: A Controllable Prompt Adversarial Attacking Framework for Black-Box Text Guided Image Generation Models IJCAI 2023 Graph-based Molecular Representation Learning IJCAI 2023 What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks NIPS 2023 Cross-Domain Few-Shot Graph Classification with a Reinforced Task Coordinator AAAI 2023 Towards Efficient and Domain-Agnostic Evasion Attack with High-Dimensional Categorical Inputs AAAI 2023 Poisoning with Cerberus: Stealthy and Colluded Backdoor Attack against Federated Learning AAAI 2023 MWP-BERT: Numeracy-Augmented Pre-training for Math Word Problem Solving NAACL 2022 Towards Improving Faithfulness in Abstractive Summarization NIPS 2022 GNN-Retro: Retrosynthetic Planning with Graph Neural Networks AAAI 2022 SAIL: Self-Augmented Graph Contrastive Learning AAAI 2022 Scientific Paper Extractive Summarization Enhanced by Citation Graphs EMNLP 2022 ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture EMNLP 2022 Analogical Math Word Problems Solving with Enhanced Problem-Solution Association EMNLP 2022 Towards Understanding the Robustness Against Evasion Attack on Categorical Data ICLR 2022 Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion IJCAI 2022 Few-Shot Learning on Graphs IJCAI 2022 Unsupervised Mitigating Gender Bias by Character Components: A Case Study of Chinese Word Embedding NAACL 2022 PAGE: A Simple and Optimal Probabilistic Gradient Estimator for Nonconvex Optimization ICML 2021 Solving Math Word Problems with Teacher Supervision IJCAI 2021 Data-Efficient Language Shaped Few-shot Image Classification EMNLP 2021 Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation AAAI 2021 Characterizing the Evasion Attackability of Multi-label Classifiers AAAI 2021 Does Head Label Help for Long-Tailed Multi-Label Text Classification AAAI 2021 Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation ACL 2021 Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation IJCNLP 2021 Weakly-Supervised Multi-view Multi-instance Multi-label Learning IJCAI 2020 Robust Federated Learning via Collaborative Machine Teaching AAAI 2020 Temporal Positive-unlabeled Learning for Biomedical Hypothesis Generation via Risk Estimation NIPS 2020 Multi-View Multiple Clusterings Using Deep Matrix Factorization AAAI 2020 Multi-Order Attentive Ranking Model for Sequential Recommendation AAAI 2019 Submodular Optimization over Streams with Inhomogeneous Decays AAAI 2019 Improving Cross-lingual Entity Alignment via Optimal Transport IJCAI 2019 Multi-View Multiple Clustering IJCAI 2019 ActiveHNE: Active Heterogeneous Network Embedding IJCAI 2019 Task-Guided and Semantic-Aware Ranking for Academic Author-Paper Correlation Inference IJCAI 2018 Mining Streaming and Temporal Data: from Representation to Knowledge IJCAI 2018 A Scalable Community Detection Algorithm for Large Graphs Using Stochastic Block Models IJCAI 2015