56 citations · 91 across the 32 of their papers we have counts for
34 papers
Fine-Grained Analysis of Catastrophic Forgetting in Continual Learning via Algorithmic Stability
Guodong Zheng, Yan Sun, Peng Wang +5
Understanding catastrophic forgetting, in which learning new tasks degrades performance on previously learned tasks, remains a fundamental challenge in continual learning (CL). Exi…
LLM Evolution as an Industry-Scale Ecosystem: A Lifecycle Perspective on Continual Learning
Hao Jiang, Enneng Yang, Guojie Zhu +7
Continual learning capability is critical for Industrial LLMs, as deployed models must be continuously updated to meet evolving requirements and environments, rather than repeatedl…
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
Chu Zhao, Enneng Yang, Jianzhe Zhao +1
Direct Preference Optimization (DPO) guides large language models (LLMs) to generate recommendations aligned with user historical behavior distributions by minimizing preference al…
Mitigating Safety Tax via Distribution-Grounded Refinement in Large Reasoning Models
Yingsha Xie, Tiansheng Huang, Enneng Yang +5
Safety alignment incurs safety tax that perturbs a large reasoning model's (LRM) general reasoning ability. Existing datasets used for safety alignment for an LRM are usually const…
ECHO: Entropy-Confidence Hybrid Optimization for Test-Time Reinforcement Learning
Chu Zhao, Enneng Yang, Yuting Liu +2
Test-time reinforcement learning generates multiple candidate answers via repeated rollouts and performs online updates using pseudo-labels constructed by majority voting. To reduc…
MMGRid: Navigating Temporal-aware and Cross-domain Generative Recommendation via Model Merging
Tianjun Wei, Enneng Yang, Yingpeng Du +3
Model merging (MM) offers an efficient mechanism for integrating multiple specialized models without access to original training data or costly retraining. While MM has demonstrate…
Automatic Pruning Discovery for Large Language Models
Haidong Kang, Lihong Lin, Enneng Yang +2
Large language models (LLMs) have achieved remarkable performance on a wide range of tasks, hindering real-world deployment due to their massive size. Existing pruning methods (e.g…
Model Unmerging: Making Your Models Unmergeable for Secure Model Sharing
Zihao Wang, Enneng Yang, Lu Yin +2
Model merging leverages multiple finetuned expert models to construct a multi-task model with low cost, and is gaining increasing attention. However, as a growing number of finetun…
Causal Negative Sampling via Diffusion Model for Out-of-Distribution Recommendation
Chu Zhao, Eneng Yang, Yizhou Dang +3
Heuristic negative sampling enhances recommendation performance by selecting negative samples of varying hardness levels from predefined candidate pools to guide the model toward l…
OptMerge: Unifying Multimodal LLM Capabilities and Modalities via Model Merging
Yongxian Wei, Runxi Cheng, Weike Jin +7
Foundation models update slowly due to resource-intensive training, whereas domain-specific models evolve rapidly between releases. Model merging seeks to combine multiple expert m…
Data Augmentation as Free Lunch: Exploring the Test-Time Augmentation for Sequential Recommendation
Yizhou Dang, Yuting Liu, Enneng Yang +4
Data augmentation has become a promising method of mitigating data sparsity in sequential recommendation. Existing methods generate new yet effective data during model training to…
Hard Negative Sampling via Large Language Models for Recommendation
Chu Zhao, Enneng Yang, Yuting Liu +2
Hard negative sampling improves recommendation performance by accelerating convergence and sharpening the decision boundary. However, most existing methods rely on heuristic strate…
Efficient and Effective Prompt Tuning via Prompt Decomposition and Compressed Outer Product
Pengxiang Lan, Haoyu Xu, Enneng Yang +4
Prompt tuning (PT) offers a cost-effective alternative to fine-tuning large-scale pre-trained language models (PLMs), requiring only a few parameters in soft prompt tokens added be…
Distributionally Robust Graph Out-of-Distribution Recommendation via Diffusion Model
Chu Zhao, Enneng Yang, Yuliang Liang +3
The distributionally robust optimization (DRO)-based graph neural network methods improve recommendation systems' out-of-distribution (OOD) generalization by optimizing the model's…
Merging Models on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging
Anke Tang, Enneng Yang, Li Shen +4
Deep model merging represents an emerging research direction that combines multiple fine-tuned models to harness their specialized capabilities across different tasks and domains.…
Augmenting Sequential Recommendation with Balanced Relevance and Diversity
Yizhou Dang, Jiahui Zhang, Yuting Liu +5
By generating new yet effective data, data augmentation has become a promising method to mitigate the data sparsity problem in sequential recommendation. Existing works focus on au…
Self-supervised Hierarchical Representation for Medication Recommendation
Yuliang Liang, Yuting Liu, Yizhou Dang +5
Medication recommender is to suggest appropriate medication combinations based on a patient's health history, e.g., diagnoses and procedures. Existing works represent different dia…
Efficient and Effective Weight-Ensembling Mixture of Experts for Multi-Task Model Merging
Li Shen, Anke Tang, Enneng Yang +6
Multi-task learning (MTL) leverages a shared model to accomplish multiple tasks and facilitate knowledge transfer. Recent research on task arithmetic-based MTL demonstrates that me…
SurgeryV2: Bridging the Gap Between Model Merging and Multi-Task Learning with Deep Representation Surgery
Enneng Yang, Li Shen, Zhenyi Wang +5
Model merging-based multitask learning (MTL) offers a promising approach for performing MTL by merging multiple expert models without requiring access to raw training data. However…
Data Augmentation for Sequential Recommendation: A Survey
Yizhou Dang, Enneng Yang, Yuting Liu +4
As an essential branch of recommender systems, sequential recommendation (SR) has received much attention due to its well-consistency with real-world situations. However, the wides…
Symmetric Graph Contrastive Learning against Noisy Views for Recommendation
Chu Zhao, Enneng Yang, Yuliang Liang +3
Graph Contrastive Learning (GCL) leverages data augmentation techniques to produce contrasting views, enhancing the accuracy of recommendation systems through learning the consiste…
Model Merging in LLMs, MLLMs, and Beyond: Methods, Theories, Applications and Opportunities
Enneng Yang, Li Shen, Guibing Guo +4
Model merging is an efficient empowerment technique in the machine learning community that does not require the collection of raw training data and does not require expensive compu…
Graph Representation Learning via Causal Diffusion for Out-of-Distribution Recommendation
Chu Zhao, Enneng Yang, Yuliang Liang +5
Graph Neural Networks (GNNs)-based recommendation algorithms typically assume that training and testing data are drawn from independent and identically distributed (IID) spaces. Ho…
FusionBench: A Unified Library and Comprehensive Benchmark for Deep Model Fusion
Anke Tang, Li Shen, Yong Luo +5
Deep model fusion is an emerging technique that unifies the predictions or parameters of several deep neural networks into a single better-performing model in a cost-effective and…