collaborators

11 papers

cs.AI2026

One Rewrite to Fix Them All? Type-Aware Repair Allocation for Text-to-Image Prompt Optimization

Haoyue Liu, Xiaoyu Ma, Ye Chen +2

Text-to-image (T2I) generators often fail to follow their prompts faithfully, producing wrong counts, swapped attributes, ambiguous relations, and illegible text. Prompt optimizati…

cs.AI2026

Select Smarter, Not More: Prompt-Aware Evaluation Scheduling with Submodular Guarantees

Xiaoyu Ma, Yiwen Li, Haoyue Liu +4

Automatic prompt optimization (APO) hinges on the quality of its evaluation signal, yet scoring every prompt candidate on the full training set is prohibitively expensive. Existing…

cs.CL2026

Adaptive Prompt Structure Factorization: A Framework for Self-Discovering and Optimizing Compositional Prompt Programs

Haoyue Liu, Zhichao Wang, Yongxin Guo +2

Automated prompt optimization is crucial for eliciting reliable reasoning from large language models (LLMs), yet most API-only prompt optimizers iteratively edit monolithic prompts…

cs.CR2026

PIDP-Attack: Combining Prompt Injection with Database Poisoning Attacks on Retrieval-Augmented Generation Systems

Haozhen Wang, Haoyue Liu, Jionghao Zhu +3

Large Language Models (LLMs) have demonstrated remarkable performance across a wide range of applications. However, their practical deployment is often hindered by issues such as o…

cs.CL2025

Multi-Physics: A Comprehensive Benchmark for Multimodal LLMs Reasoning on Chinese Multi-Subject Physics Problems

Zhongze Luo, Zhenshuai Yin, Yongxin Guo +3

While multimodal LLMs (MLLMs) demonstrate remarkable reasoning progress, their application in specialized scientific domains like physics reveals significant gaps in current evalua…

cs.AI2025

GRPO-A: Guided Group Relative Policy Optimization with Adaptive Guidance

Yongxin Guo, Wenbo Deng, Zhenglin Cheng +1

Reinforcement Learning with Verifiable Rewards (RLVR) has markedly enhanced the reasoning abilities of large language models (LLMs). Its success, however, largely depends on strong…