1 citations · 2 across the 9 of their papers we have counts for
5 papers · 1 filter
CausalVAE as a Plug-in for World Models: Towards Reliable Counterfactual Dynamics
Ziyi Ding, Xianxin Lai, Weiyu Chen +2
In this work, CausalVAE is introduced as a plug-in structural module for latent world models and is attached to diverse encoder-transition backbones. Across the reported benchmarks…
Safe Delta: Consistently Preserving Safety when Fine-Tuning LLMs on Diverse Datasets
Ning Lu, Shengcai Liu, Jiahao Wu +5
Large language models (LLMs) have shown great potential as general-purpose AI assistants across various domains. To fully leverage this potential in specific applications, many com…
Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond
Weiyu Chen, Baijiong Lin, Xiaoyuan Zhang +4
Many modern deep learning applications require balancing multiple objectives that are often conflicting. Examples include multi-task learning, fairness-aware learning, and the alig…
Pareto Merging: Multi-Objective Optimization for Preference-Aware Model Merging
Weiyu Chen, James Kwok
Model merging, which combines multiple models into a single model, has gained popularity in recent years. By efficiently integrating the capabilities of various models, this signif…
Efficient Pareto Manifold Learning with Low-Rank Structure
Weiyu Chen, James T. Kwok
Multi-task learning, which optimizes performance across multiple tasks, is inherently a multi-objective optimization problem. Various algorithms are developed to provide discrete t…