Qi Zhu

How Should We Enhance the Safety of Large Reasoning Models: An Empirical Study ACL 2026 SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL ACL 2026 DeepPhy: Benchmarking Agentic VLMs on Physical Reasoning AAAI 2026 Rethinking Expert Trajectory Utilization in LLM Post-training for Mathematical Reasoning ACL 2026 PulseMind: A Multi-Modal Medical Model for Real-World Clinical Diagnosis AAAI 2026 When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors ACL 2026 Mutual Reinforcement of LLM Dialogue Synthesis and Summarization Capabilities for Few-Shot Dialogue Summarization NAACL 2025 Multi-expert collaboration and knowledge enhancement network for multimodal emotion recognition MICCAI 2025 Cost-effective Active Learning for Nucleus Detection Using Crowdsourced Annotations with Dynamic Weighting Adjustment MICCAI 2025 AdaptPFL: Unlocking Cross-Device Palmprint Recognition via Adaptive Personalized Federated Learning with Feature Decoupling IJCAI 2025 Directly Forecasting Belief for Reinforcement Learning with Delays ICML 2025 FourierMamba: Fourier Learning Integration with State Space Models for Image Deraining ICML 2025 Spectro-Riemannian Graph Neural Networks ICLR 2025 HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Bases ACL 2025 UAlign: Leveraging Uncertainty Estimations for Factuality Alignment on Large Language Models ACL 2025 Self-Error-Instruct: Generalizing from Errors for LLMs Mathematical Reasoning ACL 2025 Can LLMs Understand Unvoiced Speech? Exploring EMG-to-Text Conversion with LLMs ACL 2025 On Large Language Model Continual Unlearning ICLR 2025 Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 When Large Vision-Language Model Meets Large Remote Sensing Imagery: Coarse-to-Fine Text-Guided Token Pruning ICCV 2025 DAMM-Diffusion: Learning Divergence-Aware Multi-Modal Diffusion Model for Nanoparticles Distribution Prediction CVPR 2025 Where am I? Cross-View Geo-localization with Natural Language Descriptions ICCV 2025 Split Adaptation for Pre-trained Vision Transformers CVPR 2025 SkySense-O: Towards Open-World Remote Sensing Interpretation with Vision-Centric Visual-Language Modeling CVPR 2025 CombatVLA: An Efficient Vision-Language-Action Model for Combat Tasks in 3D Action Role-Playing Games ICCV 2025 ClusterUCB: Efficient Gradient-Based Data Selection for Targeted Fine-Tuning of LLMs EMNLP 2025 BYOKG-RAG: Multi-Strategy Graph Retrieval for Knowledge Graph Question Answering EMNLP 2025 Empowering Resampling Operation for Ultra-High-Definition Image Enhancement with Model-Aware Guidance CVPR 2024 Variational Delayed Policy Optimization NIPS 2024 Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval NIPS 2024 Fine-Tuning Graph Neural Networks by Preserving Graph Generative Patterns AAAI 2024 REGLO: Provable Neural Network Repair for Global Robustness Properties AAAI 2024 Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios ACL 2024 Parallelizing non-linear sequential models over the sequence length ICLR 2024 Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays ICML 2024 Missingness-resilient Video-enhanced Multimodal Disfluency Detection INTERSPEECH 2024 State-wise safe reinforcement learning with pixel observations L4DC 2024 Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models NAACL 2024 Learning Semantic Degradation-Aware Guidance for Recognition-Driven Unsupervised Low-Light Image Enhancement AAAI 2023 KPT: Keyword-Guided Pre-training for Grounded Dialog Generation AAAI 2023 Building Multi-domain Dialog State Trackers from Single-domain Dialogs EMNLP 2023 Exploring Temporal Frequency Spectrum in Deep Video Deblurring ICCV 2023 Efficient Global Robustness Certification of Neural Networks via Interleaving Twin-Network Encoding (Extended Abstract) IJCAI 2023 Leapfrog Diffusion Model for Stochastic Trajectory Prediction CVPR 2023 May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations NIPS 2023 Deja Vu: Continual Model Generalization for Unseen Domains ICLR 2023 Semi-supervised Semantics-guided Adversarial Training for Robust Trajectory Prediction ICCV 2023 FouriDown: Factoring Down-Sampling into Shuffling and Superposing NIPS 2023 ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format EMNLP 2023 Patton: Language Model Pretraining on Text-Rich Networks ACL 2023 Enforcing Hard Constraints with Soft Barriers: Safe Reinforcement Learning in Unknown Stochastic Environments ICML 2023 Federated Class-Incremental Learning CVPR 2022 Non-Transferable Learning: A New Approach for Model Ownership Verification and Applicability Authorization ICLR 2022 A Unified Dialogue User Simulator for Few-shot Data Augmentation EMNLP 2022 GEMv2: Multilingual NLG Benchmarking in a Single Line of Code EMNLP 2022 Continual Prompt Tuning for Dialog State Tracking ACL 2022 Weak Adaptation Learning: Addressing Cross-Domain Data Insufficiency With Weak Annotator ICCV 2021 Transfer Learning of Graph Neural Networks with Ego-graph Information Maximization NIPS 2021 Addressing Class Imbalance in Federated Learning AAAI 2021 Simple is not Easy: A Simple Strong Baseline for TextVQA and TextCaps AAAI 2021 Chop Chop BERT: Visual Question Answering by Chopping VisualBERT’s Heads IJCAI 2021 Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training data NIPS 2021 When does Further Pre-training MLM Help? An Empirical Study on Task-Oriented Dialog Pre-training EMNLP 2021 Facet-Aware Evaluation for Extractive Summarization ACL 2020 ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems ACL 2020 ConvLab: Multi-Domain End-to-End Dialog System Platform ACL 2019 FFNet: Video Fast-Forwarding via Reinforcement Learning CVPR 2018 Heterogeneous Supervision for Relation Extraction: A Representation Learning Approach EMNLP 2017 Life-iNet: A Structured Network-Based Knowledge Exploration and Analytics System for Life Sciences ACL 2017