activity
20242026
collaborators
Showing cs.LGShow all

8 papers · 1 filter

cs.LG2026

Federated Large Language Models: Current Progress and Future Directions

Yuhang Yao, Jianyi Zhang, Junda Wu +11

Large Language Models have achieved impressive performance across diverse applications, yet their training typically depends on centralized data collection, raising serious privacy…

cs.LG2026

Simultaneous Multi-objective Alignment Across Verifiable and Non-verifiable Rewards

Yiran Shen, Yu Xia, Jonathan Chang +1

Aligning large language models to human preferences is inherently multidimensional, yet most pipelines collapse heterogeneous signals into a single objective. We seek to answer wha…

cs.LG2026

Learning to Hint for Reinforcement Learning

Yu Xia, Canwen Xu, Zhewei Yao +2

Group Relative Policy Optimization (GRPO) is widely used for reinforcement learning with verifiable rewards, but it often suffers from advantage collapse: when all rollouts in a gr…

cs.LG2026

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…

cs.LG2025

In-context Ranking Preference Optimization

Junda Wu, Rohan Surana, Zhouhang Xie +6

Recent developments in Direct Preference Optimization (DPO) allow large language models (LLMs) to function as implicit ranking models by maximizing the margin between preferred and…

cs.LG2025

From Selection to Generation: A Survey of LLM-based Active Learning

Yu Xia, Subhojyoti Mukherjee, Zhouhang Xie +31

Active Learning (AL) has been a powerful paradigm for improving model efficiency and performance by selecting the most informative data points for labeling and training. In recent…