Liang He

13

Papers

104

Total Citations

Papers (13)

DriveArena: A Closed-loop Generative Simulation Platform for Autonomous Driving

NLSR: Neuron-Level Safety Realignment of Large Language Models Against Harmful Fine-Tuning

CL-MoE: Enhancing Multimodal Large Language Model with Dual Momentum Mixture-of-Experts for Continual Visual Question Answering

Human Simulacra: Benchmarking the Personification of Large Language Models

A Hierarchical Network for Multimodal Document-Level Relation Extraction

Aspect Enhancement and Text Simplification in Multimodal Aspect-Based Sentiment Analysis for Multi-Aspect and Multi-Sentiment Scenarios

Disentangled Modeling of Preferences and Social Influence for Group Recommendation

Lark: Low-Rank Updates After Knowledge Localization for Few-shot Class-Incremental Learning

MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models

MELO: Enhancing Model Editing with Neuron-Indexed Dynamic LoRA

BDIQA: A New Dataset for Video Question Answering to Explore Cognitive Reasoning through Theory of Mind

Generative Calibration of Inaccurate Annotation for Label Distribution Learning

AVF-MAE++: Scaling Affective Video Facial Masked Autoencoders via Efficient Audio-Visual Self-Supervised Learning