Jiajun Liu

Balanced Knowledge Distillation for Large Language Models with Mix-of-Experts AAAI 2026 Benchmarking and Enhancing Rule Knowledge-Driven Reasoning of Large Language Models AAAI 2026 Capability Decomposition for Unified Information Extraction via Hierarchical Mixture-of-Experts ACL 2026 Embodied-Reasoner: Synergizing Visual Search, Reasoning, and Action for Embodied Interactive Tasks ACL 2026 Exploring Layer Activation Dynamic of CoT via Knowledge Probe ACL 2026 Knowledge Poisoning Attacks on Medical Multi-Modal Retrieval-Augmented Generation ACL 2026 On the Role of Discriminative Models in Generative Relation Extraction ACL 2026 Optimizing LoRA Allocation of MoE with the Alignment of Topic Correlation AAAI 2026 Robust Membership Inference for Large Language Models under Adversarial Generative Corruption ACL 2026 Acquisition and Application of Novel Knowledge in Large Language Models ACL 2025 Can Large Models Teach Student Models to Solve Mathematical Problems Like Human Beings? A Reasoning Distillation Method via Multi-LoRA Interaction IJCAI 2025 General Scene Adaptation for Vision-and-Language Navigation ICLR 2025 LLM-Guided Semantic-Aware Clustering for Topic Modeling ACL 2025 Medium-Difficulty Samples Constitute Smoothed Decision Boundary for Knowledge Distillation on Pruned Datasets ICLR 2025 On the Consistency of Commonsense in Large Language Models ACL 2025 On-the-Fly Object-aware Representative Point Selection in Point Cloud WACV 2025 Quantifying and Narrowing the Unknown: Interactive Text-to-Video Retrieval via Uncertainty Minimization ICCV 2025 RAGulator: Lightweight Out-of-Context Detectors for Grounded Text Generation EMNLP 2025 RePaViT: Scalable Vision Transformer Acceleration via Structural Reparameterization on Feedforward Network Layers ICML 2025 TokenBinder: Text-Video Retrieval with One-to-Many Alignment Paradigm WACV 2025 Boosting Textural NER with Synthetic Image and Instructive Alignment ACL 2024 Demonstrating Event-Triggered Investigation and Sample Collection for Human Scientists using Field Robots and Large Foundation Models RSS 2024 Domain-Hierarchy Adaptation via Chain of Iterative Reasoning for Few-shot Hierarchical Text Classification IJCAI 2024 Empirical Analysis of Dialogue Relation Extraction with Large Language Models IJCAI 2024 Fast and Continual Knowledge Graph Embedding via Incremental LoRA IJCAI 2024 GTP-ViT: Efficient Vision Transformers via Graph-Based Token Propagation WACV 2024 Incorporating Schema-Aware Description into Document-Level Event Extraction IJCAI 2024 Learning Multi-Granularity and Adaptive Representation for Knowledge Graph Reasoning IJCAI 2024 LLM as Copilot for Coarse-grained Vision-and-Language Navigation ECCV 2024 Meta In-Context Learning Makes Large Language Models Better Zero and Few-Shot Relation Extractors IJCAI 2024 OntoFact: Unveiling Fantastic Fact-Skeleton of LLMs via Ontology-Driven Reinforcement Learning AAAI 2024 Real-time Multi-modal Object Detection and Tracking on Edge for Regulatory Compliance Monitoring IJCAI 2024 Recall, Retrieve and Reason: Towards Better In-Context Relation Extraction IJCAI 2024 Towards Continual Knowledge Graph Embedding via Incremental Distillation AAAI 2024 Unlocking Instructive In-Context Learning with Tabular Prompting for Relational Triple Extraction COLING 2024 Unveiling LoRA Intrinsic Ranks via Salience Analysis NeurIPS 2024 Why Only Text: Empowering Vision-and-Language Navigation with Multi-modal Prompts IJCAI 2024 Dynamic Token Pruning in Plain Vision Transformers for Semantic Segmentation ICCV 2023 Global Knowledge Calibration for Fast Open-Vocabulary Segmentation ICCV 2023 IterDE: An Iterative Knowledge Distillation Framework for Knowledge Graph Embeddings AAAI 2023 OCHID-Fi: Occlusion-Robust Hand Pose Estimation in 3D via RF-Vision ICCV 2023 SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process NeurIPS 2023 Improved Feature Distillation via Projector Ensemble NeurIPS 2022