7 papers
IRIS: Implicit Reward-Guided Internal Sifting for Mitigating Multimodal Hallucination
Yuanshuai Li, Yuping Yan, Jirui Han +3
Hallucination remains a fundamental challenge for Multimodal Large Language Models (MLLMs). While Direct Preference Optimization (DPO) is a key alignment framework, existing approa…
Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities
Zhiyuan Peng, Zihan Ye, Shreyank N Gowda +3
Zero-shot Learning (ZSL) aims to enable image classifiers to recognize images from unseen classes that were not included during training. Unlike traditional supervised classificati…
When Alignment Fails: Multimodal Adversarial Attacks on Vision-Language-Action Models
Yuping Yan, Yuhan Xie, Yixin Zhang +3
Vision-Language-Action models (VLAs) have recently demonstrated remarkable progress in embodied environments, enabling robots to perceive, reason, and act through unified multimoda…
Mitigating Visual Hallucinations via Semantic Curriculum Preference Optimization in MLLMs
Yuanshuai Li, Yuping Yan, Junfeng Tang +3
Multimodal Large Language Models (MLLMs) have significantly improved the performance of various tasks, but continue to suffer from visual hallucinations, a critical issue where gen…
TriCon-SF: A Triple-Shuffle and Contribution-Aware Serial Federated Learning Framework for Heterogeneous Healthcare Data
Yuping Yan, Yizhi Wang, Yuanshuai Li +1
Serial pipeline training is an efficient paradigm for handling data heterogeneity in cross-silo federated learning with low communication overhead. However, even without centralize…
Think Small, Plan Smart: Minimalist Symbolic Abstraction and Heuristic Subspace Search for LLM-Guided Task Planning
Junfeng Tang, Yuping Yan, Zihan Ye +4
Reliable task planning is pivotal for achieving long-horizon autonomy in real-world robotic systems. Large language models (LLMs) offer a promising interface for translating comple…