6 papers
Reinforcement Learning with Robust Rubric Rewards
Ya-Qi Yu, Hao Wang, Fangyu Hong +15
While Reinforcement Learning with Verifiable Rewards (RLVR) is effective for deterministically checkable tasks, many vision-language tasks are partially verifiable, demanding multi…
Visual Preference Optimization with Rubric Rewards
Ya-Qi Yu, Fangyu Hong, Xiangyang Qu +15
The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often…
IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization
Heyang Zhou, JiaJia Chen, Xiaolu Chen +3
As Generative Engines revolutionize information retrieval by synthesizing direct answers from retrieved sources, ensuring source visibility becomes a significant challenge. Improvi…
Caption Injection for Optimization in Generative Search Engine
Xiaolu Chen, Jie Bao, Haojie Wu +2
Generative Search Engine (GSE) leverages the Retrieval-Augmented Generation (RAG) technique and the Large Language Model (LLM) to integrate multi-source information and provide use…
Role-Augmented Intent-Driven Generative Search Engine Optimization
Xiaolu Chen, Haojie Wu, Jie Bao +4
Generative search engines (GSEs), which combine large language models (LLMs) with retrieval-augmented generation (RAG), are reshaping how users access Web information and making so…
CuDA2: An approach for Incorporating Traitor Agents into Cooperative Multi-Agent Systems
Zhen Chen, Yong Liao, Youpeng Zhao +2
Cooperative Multi-Agent Reinforcement Learning (CMARL) strategies are well known to be vulnerable to adversarial perturbations. Previous works on adversarial attacks have primarily…