Liang He

A Survey of Inductive Reasoning for Large Language Models ACL 2026 TamEdit: Trajectory-Aware Meta-Learning for Specificity-Preserving Continual Knowledge Editing ACL 2026 MovieGraph-ToM: Evaluating Long-Range Theory of Mind in Large Language Models via Implicit Social-Causal Graphs AAAI 2026 LifeAlign: Lifelong Alignment for Large Language Models with Memory-Augmented Focalized Preference Optimization AAAI 2026 Optimizing Question Semantic Space for Dynamic Retrieval-Augmented Multi-hop Question Answering ACL 2025 P-React: Synthesizing Topic-Adaptive Reactions of Personality Traits via Mixture of Specialized LoRA Experts ACL 2025 Enhancing Medical Dialogue Generation through Knowledge Refinement and Dynamic Prompt Adjustment ACL 2025 Sentiment-enhanced Multi-hop Connected Graph Attention Network for Multimodal Aspect-Based Sentiment Analysis IJCAI 2025 Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios AAAI 2025 Disentangled Modeling of Preferences and Social Influence for Group Recommendation AAAI 2025 NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning AAAI 2025 Human Simulacra: Benchmarking the Personification of Large Language Models ICLR 2025 DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving ICCV 2025 Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning ICCV 2025 CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering CVPR 2025 AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning CVPR 2025 ACE-M3: Automatic Capability Evaluator for Multimodal Medical Models COLING 2025 RGR-KBQA: Generating Logical Forms for Question Answering Using Knowledge-Graph-Enhanced Large Language Model COLING 2025 AutoMedEval: Harnessing Language Models for Automatic Medical Capability Evaluation ACL 2025 Self-Supervised Speaker Verification with Mini-Batch Prediction Correction INTERSPEECH 2024 Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving NIPS 2024 BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind AAAI 2024 Generative Calibration of Inaccurate Annotation for Label Distribution Learning AAAI 2024 MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models AAAI 2024 A Hierarchical Network for Multimodal Document-Level Relation Extraction AAAI 2024 MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA AAAI 2024 A Regularization-based Transfer Learning Method for Information Extraction via Instructed Graph Decoder COLING 2024 Learning Intrinsic Dimension via Information Bottleneck for Explainable Aspect-based Sentiment Analysis COLING 2024 Let’s Rectify Step by Step: Improving Aspect-based Sentiment Analysis with Diffusion Models COLING 2024 MixRED: A Mix-lingual Relation Extraction Dataset COLING 2024 How Do Humans Write Code? Large Models Do It the Same Way Too EMNLP 2024 C-LLM: Learn to Check Chinese Spelling Errors Character by Character EMNLP 2024 CliMedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models in Clinical Scenarios EMNLP 2024 MGCL: Multi-Granularity Clue Learning for Emotion-Cause Pair Extraction via Cross-Grained Knowledge Distillation EMNLP 2024 Boosting Large Language Models with Continual Learning for Aspect-based Sentiment Analysis EMNLP 2024 DiaHalu: A Dialogue-level Hallucination Evaluation Benchmark for Large Language Models EMNLP 2024 Vanessa: Visual Connotation and Aesthetic Attributes Understanding Network for Multimodal Aspect-based Sentiment Analysis EMNLP 2024 DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models ICLR 2024 Joint Multimodal Aspect Sentiment Analysis with Aspect Enhancement and Syntactic Adaptive Learning IJCAI 2024 YOLOPitch: A Time-Frequency Dual-Branch YOLO Model for Pitch Estimation INTERSPEECH 2024 Cross-modal Features Interaction-and-Aggregation Network with Self-consistency Training for Speech Emotion Recognition INTERSPEECH 2024 Speech Topic Classification Based on Multi-Scale and Graph Attention Networks INTERSPEECH 2024 Hypernetwork-Assisted Parameter-Efficient Fine-Tuning with Meta-Knowledge Distillation for Domain Knowledge Disentanglement NAACL 2024 MTANet: Multi-band Time-frequency Attention Network for Singing Melody Extraction from Polyphonic Music INTERSPEECH 2023 A Study on Visualization of Voiceprint Feature INTERSPEECH 2023 Dynamic Fully-Connected Layer for Large-Scale Speaker Verification INTERSPEECH 2023 LoGoNet: Towards Accurate 3D Object Detection With Local-to-Global Cross-Modal Fusion CVPR 2023 SKD-NER: Continual Named Entity Recognition via Span-based Knowledge Distillation with Reinforcement Learning EMNLP 2023 DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds ICCV 2023 Generative Label Enhancement with Gaussian Mixture and Partial Ranking AAAI 2023 HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization ICLR 2023 A Disentangled-Attention Based Framework with Persona-Aware Prompt Learning for Dialogue Generation AAAI 2023 Black-box Prompt Tuning for Vision-Language Model as a Service IJCAI 2023 Disentangled CVAEs with Contrastive Learning for Explainable Recommendation AAAI 2023 UReader: Universal OCR-free Visually-situated Language Understanding with Multimodal Large Language Model EMNLP 2023 Robust Training for Speaker Verification against Noisy Labels INTERSPEECH 2023 A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck COLING 2022 ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis SEMEVAL 2022 An Information Minimization Based Contrastive Learning Model for Unsupervised Sentence Embeddings Learning COLING 2022 Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detection ECCV 2022 A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition INTERSPEECH 2022 A Multi-grained based Attention Network for Semi-supervised Sound Event Detection INTERSPEECH 2022 ECNU_ICA at SemEval-2022 Task 10: A Simple and Unified Model for Monolingual and Crosslingual Structured Sentiment Analysis NAACL 2022 Shifting More Attention to Visual Backbone: Query-Modulated Refinement Networks for End-to-End Visual Grounding CVPR 2022 CUP: Curriculum Learning based Prompt Tuning for Implicit Event Argument Extraction IJCAI 2022 Curriculum Prompt Learning with Self-Training for Abstractive Dialogue Summarization EMNLP 2022 Multi-Scale Distribution Deep Variational Autoencoder for Explanation Generation ACL 2022 ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning IJCNLP 2021 Co-evolution Transformer for Protein Contact Prediction NIPS 2021 Looking Wider for Better Adaptive Representation in Few-Shot Learning AAAI 2021 ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning SEMEVAL 2021 ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline SEMEVAL 2021 Attending via both Fine-tuning and Compressing IJCNLP 2021 ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline IJCNLP 2021 End-to-End Cross-Lingual Spoken Language Understanding Model with Multilingual Pretraining INTERSPEECH 2021 Automated Cross-prompt Scoring of Essay Traits AAAI 2021 ECNUICA at SemEval-2021 Task 11: Rule based Information Extraction Pipeline ACL 2021 ECNU_ICA_1 SemEval-2021 Task 4: Leveraging Knowledge-enhanced Graph Attention Networks for Reading Comprehension of Abstract Meaning ACL 2021 Attending via both Fine-tuning and Compressing ACL 2021 Is “hot pizza” Positive or Negative? Mining Target-aware Sentiment Lexicons EACL 2021 KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals EMNLP 2021 SentiX: A Sentiment-Aware Pre-Trained Model for Cross-Domain Sentiment Analysis COLING 2020 ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation COLING 2020 Integrating BERT and Score-based Feature Gates for Chinese Grammatical Error Diagnosis AACL 2020 SEEK: Segmented Embedding of Knowledge Graphs ACL 2020 SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing ACL 2020 THUEE System for NIST SRE19 CTS Challenge INTERSPEECH 2020 ECNU-SenseMaker at SemEval-2020 Task 4: Leveraging Heterogeneous Knowledge Resources for Commonsense Validation and Explanation SEMEVAL 2020 Exploiting Noisy Data in Distant Supervision Relation Classification NAACL 2019 Large Margin Softmax Loss for Speaker Verification INTERSPEECH 2019 Multi-Scale Time-Frequency Attention for Acoustic Event Detection INTERSPEECH 2019 Towards Discriminative Representations and Unbiased Predictions: Class-Specific Angular Softmax for Speech Emotion Recognition INTERSPEECH 2019 EmojiIt at SemEval-2018 Task 2: An Effective Attention-Based Recurrent Neural Network Model for Emoji Prediction with Characters Gated Words SEMEVAL 2018 MTGAN: Speaker Verification through Multitasking Triplet Generative Adversarial Networks INTERSPEECH 2018 Speaker Embedding Extraction with Phonetic Information INTERSPEECH 2018 Investigating Various Diarization Algorithms for Speaker in the Wild (SITW) Speaker Recognition Challenge INTERSPEECH 2016 Improving Deep Neural Networks Based Speaker Verification Using Unlabeled Data INTERSPEECH 2016 THU-EE System Description for NIST LRE 2015 INTERSPEECH 2016