17 papers
Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration
Shuhao Li, Guodong Du, Anhao Zhao +3
Large language models have made strong reasoning gains through supervised fine-tuning, reinforcement learning, and on-policy distillation, yet these post-training methods are usual…
Skill Weaving: Efficient LLM Improvement via Modular Skillpacks
Zhuo Li, Guodong Du, Zesheng Shi +5
Large language models increasingly require specialization across diverse domains, yet existing approaches struggle to balance multi-domain capacities with strict memory and inferen…
Dynamic Model Merging Made Slim
Guodong Du, Wanyu Lin
Model merging consolidates independently fine-tuned checkpoints without joint training or access to task data. Dynamic methods retain task-specific capacity, but must divide a limi…
Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate Hallucination
Yangneng Chen, Junlin Li, Weijun Yao +4
Large Vision-Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet their reliability is persistently undermined by hallucinations-generating text that…
D-QRELO: Training- and Data-Free Delta Compression for Large Language Models via Quantization and Residual Low-Rank Approximation
Junlin Li, Shuangyong Song, Guodong Du +6
Supervised Fine-Tuning (SFT) accelerates taskspecific large language models (LLMs) development, but the resulting proliferation of finetuned models incurs substantial memory overhe…
NeurIPT: Foundation Model for Neural Interfaces
Zitao Fang, Chenxuan Li, Hongting Zhou +7
Electroencephalography (EEG) has wide-ranging applications, from clinical diagnosis to brain-computer interfaces (BCIs). With the increasing volume and variety of EEG data, there h…
Multi-objective Large Language Model Alignment with Hierarchical Experts
Zhuo Li, Guodong Du, Weiyang Guo +8
Aligning large language models (LLMs) to simultaneously satisfy multiple objectives remains a significant challenge, especially given the diverse and often conflicting nature of hu…
Neural Parameter Search for Slimmer Fine-Tuned Models and Better Transfer
Guodong Du, Zitao Fang, Jing Li +10
Foundation models and their checkpoints have significantly advanced deep learning, boosting performance across various applications. However, fine-tuned models often struggle outsi…
Multi-Modality Expansion and Retention for LLMs through Parameter Merging and Decoupling
Junlin Li, Guodong DU, Jing Li +8
Fine-tuning Large Language Models (LLMs) with multimodal encoders on modality-specific data expands the modalities that LLMs can handle, leading to the formation of Multimodal LLMs…
Knowledge Fusion of Large Language Models Via Modular SkillPacks
Guodong Du, Zhuo Li, Xuanning Zhou +9
Cross-capability transfer is a key challenge in large language model (LLM) research, with applications in multi-task integration, model compression, and continual learning. Recent…
To See a World in a Spark of Neuron: Disentangling Multi-task Interference for Training-free Model Merging
Zitao Fang, Guodong DU, Shuyang Yu +6
Fine-tuning pre-trained models on targeted datasets enhances task-specific performance but often comes at the expense of generalization. Model merging techniques, which integrate m…
Enhancing Accuracy and Feature Insights in Hydration Free Energy Predictions for Small Molecules with Machine Learning
Mingjun Han, Yukai Zhang, Taotao Yu +3
The accurate prediction of solvation free energy is of significant importance as it governs the behavior of solutes in solution. In this work, we apply a variety of machine learnin…
Parameter Competition Balancing for Model Merging
Guodong Du, Junlin Lee, Jing Li +8
While fine-tuning pretrained models has become common practice, these models often underperform outside their specific domains. Recently developed model merging techniques enable t…
Impacts of Darwinian Evolution on Pre-trained Deep Neural Networks
Guodong Du, Runhua Jiang, Senqiao Yang +5
Darwinian evolution of the biological brain is documented through multiple lines of evidence, although the modes of evolutionary changes remain unclear. Drawing inspiration from th…
Evolutionary Neural Architecture Search for 3D Point Cloud Analysis
Yisheng Yang, Guodong Du, Chean Khim Toa +2
Neural architecture search (NAS) automates neural network design by using optimization algorithms to navigate architecture spaces, reducing the burden of manual architecture design…
Knowledge Fusion By Evolving Weights of Language Models
Guodong Du, Jing Li, Hanting Liu +5
Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different d…
CADE: Cosine Annealing Differential Evolution for Spiking Neural Network
Runhua Jiang, Guodong Du, Shuyang Yu +3
Spiking neural networks (SNNs) have gained prominence for their potential in neuromorphic computing and energy-efficient artificial intelligence, yet optimizing them remains a form…