概览
新闻动态
成员信息
科学研究
联系我们
中文 (简体)
中文 (简体)
English
Biqing Qi
最新
Neural Residual Diffusion Models for Deep Scalable Vision Generation
Safe-SD: Safe and Traceable Stable Diffusion with Text Prompt Trigger for Invisible Generative Watermarking
Towards Building Specialized Generalist AI with System 1 and System 2 Fusion
Enhancing Adversarial Transferability via Information Bottleneck Constraints
Exploring Adversarial Robustness of Deep State Space Models
Fast and Slow Generating: An Empirical Study on Large and Small Language Models Collaborative Decoding
Intuitive Fine-Tuning: Towards Simplifying Alignment into a Single Process
Online DPO: Online Direct Preference Optimization with Fast-Slow Chasing
UltraMedical: Building Specialized Generalists in Biomedicine
CoGenesis: A Framework Collaborating Large and Small Language Models for Secure Context-Aware Instruction Following
SMR: State Memory Replay for Long Sequence Modeling
On Large Language Models' Hallucination with Regard to Known Facts
PaD: Program-aided Distillation Specializes Large Models in Reasoning
Contrastive Augmented Graph2Graph Memory Interaction for Few Shot Continual Learning
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation
Interactive Continual Learning: Fast and Slow Thinking
Large Language Models are Zero Shot Hypothesis Proposers
CRaSh: Clustering, Removing, and Sharing Enhance Fine-tuning without Full Large Language Model
Improving Robustness of Intent Detection Under Adversarial Attacks: A Geometric Constraint Perspective
引用
×