1 citations · 3 across the 15 of their papers we have counts for
5 papers · 1 filter
Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient Descent
Junda Wu, Yuxin Xiong, Xintong Li +9
Recent MLLMs have shown emerging visual understanding and reasoning abilities after being pre-trained on large-scale multimodal datasets. Unlike pre-training, where MLLMs receive r…
Regularized Multi-LLMs Collaboration for Enhanced Score-based Causal Discovery
Xiaoxuan Li, Yao Liu, Ruoyu Wang +1
As the significance of understanding the cause-and-effect relationships among variables increases in the development of modern systems and algorithms, learning causality from obser…
OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language Models
Junda Wu, Xintong Li, Ruoyu Wang +9
Offline evaluation of LLMs is crucial in understanding their capacities, though current methods remain underexplored in existing research. In this work, we focus on the offline eva…
Independence Constrained Disentangled Representation Learning from Epistemological Perspective
Ruoyu Wang, Lina Yao
Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables…
ASFT: Aligned Supervised Fine-Tuning through Absolute Likelihood
Ruoyu Wang, Jiachen Sun, Shaowei Hua +1
Direct Preference Optimization (DPO) is a method for enhancing model performance by directly optimizing for the preferences or rankings of outcomes, instead of traditional loss fun…