54 citations · 131 across the 84 of their papers we have counts for
7 papers · 1 filter
PertMind: Eliciting Emergent Biological Reasoning in LLM via Reinforcement Learning on Cellular Perturbation Data
Zhenchao Tang, Xiaogang Xu, Tianxu Lv +16
Large language models can describe mechanisms, yet scalable post-training still depends on costly, manually curated biological reasoning traces. Here we show that cellular perturba…
GDRO: Group-level Reward Post-training Suitable for Diffusion Models
Yiyang Wang, Xi Chen, Xiaogang Xu +2
Recent advancements adopt online reinforcement learning (RL) from LLMs to text-to-image rectified flow diffusion models for reward alignment. The use of group-level rewards success…
Generative Distribution Distillation
Jiequan Cui, Beier Zhu, Qingshan Xu +6
In this paper, we formulate the knowledge distillation (KD) as a conditional generative problem and propose the \textit{Generative Distribution Distillation (GenDD)} framework. A n…
LPO: Towards Accurate GUI Agent Interaction via Location Preference Optimization
Jiaqi Tang, Yu Xia, Yi-Feng Wu +9
The advent of autonomous agents is transforming interactions with Graphical User Interfaces (GUIs) by employing natural language as a powerful intermediary. Despite the predominanc…
DR-Encoder: Encode Low-rank Gradients with Random Prior for Large Language Models Differentially Privately
Huiwen Wu, Deyi Zhang, Xiaohan Li +3
The emergence of the Large Language Model (LLM) has shown their superiority in a wide range of disciplines, including language understanding and translation, relational logic reaso…
CG-FedLLM: How to Compress Gradients in Federated Fune-tuning for Large Language Models
Huiwen Wu, Xiaogang Xu, Deyi Zhang +3
The success of current Large-Language Models (LLMs) hinges on extensive training data that is collected and stored centrally, called Centralized Learning (CL). However, such a coll…
Refine, Discriminate and Align: Stealing Encoders via Sample-Wise Prototypes and Multi-Relational Extraction
Shuchi Wu, Chuan Ma, Kang Wei +4
This paper introduces RDA, a pioneering approach designed to address two primary deficiencies prevalent in previous endeavors aiming at stealing pre-trained encoders: (1) suboptima…