10 papers
HAS: Highlight-guided Attention Steering for Multimodal LLM Video Summarization
Rui Chu, Yingjie Lao
Video understanding has become more and more important with the growth of Artificial Intelligence (AI) for video generation. Recently, Multimodal Large Language Model(M-LLM) has sh…
CLDRoute: Conditional Latent Diffusion for Routability Map Generation in Physical Design
Kiran Thorat, Nicole Meng, Caiwen Ding +2
Accurate routability estimation during physical design is important for reducing costly post-routing iterations. Prior learning-based methods treat this task as deterministic predi…
Probabilistic Concept-Aware Steering for Trustworthy LLM Inference
Brian Becker, Rui Chu, Yingjie Lao
Steering vectors (SVs), an inference-time intervention technique for large language models (LLMs), guide the generation process by adding a concept-specific direction vector to int…
AnchorKV: Safety-Aware KV Cache Compression via Soft Penalty with a Refusal Anchor
Ning Ni, Yingjie Lao
Large language models (LLMs) outperform earlier architectures on generative inference and long-context tasks, but their large size introduces significant challenges in memory usage…
DebiasRAG: A Tuning-Free Path to Fair Generation in Large Language Models through Retrieval-Augmented Generation
Rui Chu, Bingyin Zhao, Thanh Quoc Hung Le +6
Large language models (LLMs) have achieved unprecedented success due to their exceptional generative capabilities. However, because they depend on knowledge encapsulated from train…
3DEditSafe: Defending 3D Editing Pipelines from Unsafe Generation
Nicole Meng, Zheyuan Liu, Meng Jiang +1
Recent advances in 3D generative editing, particularly pipelines based on 3D Gaussian Splatting (3DGS), have achieved high-fidelity, multi-view-consistent scene manipulation from t…
VisInject: Disruption != Injection -- A Dual-Dimension Evaluation of Universal Adversarial Attacks on Vision-Language Models
Pang Liu, Yingjie Lao
Universal adversarial attacks on aligned multimodal large language models are increasingly reported with attack success rates in the 60-80% range, suggesting the visual modality is…
GIF: A Conditional Multimodal Generative Framework for IR Drop Imaging in Chip Layouts
Kiran Thorat, Nicole Meng, Mostafa Karami +3
IR drop analysis is essential in physical chip design to ensure the power integrity of on-chip power delivery networks. Traditional Electronic Design Automation (EDA) tools have be…
UIBDiffusion: Universal Imperceptible Backdoor Attack for Diffusion Models
Yuning Han, Bingyin Zhao, Rui Chu +3
Recent studies show that diffusion models (DMs) are vulnerable to backdoor attacks. Existing backdoor attacks impose unconcealed triggers (e.g., a gray box and eyeglasses) that con…
Fully Attentional Networks with Self-emerging Token Labeling
Bingyin Zhao, Zhiding Yu, Shiyi Lan +4
Recent studies indicate that Vision Transformers (ViTs) are robust against out-of-distribution scenarios. In particular, the Fully Attentional Network (FAN) - a family of ViT backb…