1 citations · 6 across the 25 of their papers we have counts for
7 papers · 1 filter
MAny: Merge Anything for Multimodal Continual Instruction Tuning
Zijian Gao, Wangwang Jia, Xingxing Zhang +6
Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic fo…
Scaffold-Conditioned Preference Triplets for Controllable Molecular Optimization with Large Language Models
Yi Xiong, Liang Xiong, Xiaohong Ji +4
Molecular property optimization is central to drug discovery, yet many deep learning methods rely on black-box scoring and offer limited control over scaffold preservation, often p…
Online Self-Preferring Language Models
Yuanzhao Zhai, Zhuo Zhang, Kele Xu +6
Aligning with human preference datasets has been critical to the success of large language models (LLMs). Reinforcement learning from human feedback (RLHF) employs a costly reward…
Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
Yuanzhao Zhai, Yiying Li, Zijian Gao +5
Model-based offline reinforcement learning (RL) has made remarkable progress, offering a promising avenue for improving generalization with synthetic model rollouts. Existing works…
Uncertainty-Penalized Reinforcement Learning from Human Feedback with Diverse Reward LoRA Ensembles
Yuanzhao Zhai, Han Zhang, Yu Lei +5
Reinforcement learning from human feedback (RLHF) emerges as a promising paradigm for aligning large language models (LLMs). However, a notable challenge in RLHF is overoptimizatio…
Self-Supervised Exploration via Temporal Inconsistency in Reinforcement Learning
Zijian Gao, Kele Xu, Yuanzhao Zhai +4
Under sparse extrinsic reward settings, reinforcement learning has remained challenging, despite surging interests in this field. Previous attempts suggest that intrinsic reward ca…
Nuclear Norm Maximization Based Curiosity-Driven Learning
Chao Chen, Zijian Gao, Kele Xu +5
To handle the sparsity of the extrinsic rewards in reinforcement learning, researchers have proposed intrinsic reward which enables the agent to learn the skills that might come in…