12 papers
Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos
Yang Wang, Yanan Ma, Yiqi Liu +7
Social media videos often communicate meanings that go beyond their visible actions, captions, or speech. A mundane clip may become humorous, ironic, or satire only through the int…
TALAN: Task-Aligned Latent Adaptation Networks for Targeted Post-Training of Large Language Models
Chengkai Zhang, Ziteng Liu, Junpu Wang +4
Targeted post-training aims to improve reasoning, math, and code without degrading strengths. Low-rank adapters are efficient but task-global; activation interventions are input-aw…
Selective Coupling of Decoupled Informative Regions: Masked Attention Alignment for Data-Free Quantization of Vision Transformers
Biao Qian, Yang Wang, Yong Wu +1
Data-Free Quantization (DFQ) addresses data security concerns by synthesizing samples, without accessing real data. It has garnered increasing attention in the context of Vision Tr…
Hybrid Adversarial Defence for Natural Language Understanding Tasks
Manar Abouzaid, Yang Wang, Chenghua Lin +1
Large Language Models (LLMs) are vulnerable both to hallucination and adversarial manipulation. Although these problems are closely related, existing defences typically address the…
SafeGene: Reusable Adapters for Transferable Safety Alignment
Yanghan Wang, Zhiqiang Kou, Fu Feng +2
Open-weight LLMs are increasingly fine-tuned into customized assistants, but downstream fine-tuning can weaken safety alignment and make models more vulnerable to malicious prompts…
Evaluating LLM-Based Grant Proposal Review via Structured Perturbations
William Thorne, Joseph James, Yang Wang +2
As AI-assisted grant proposals outpace manual review capacity in a kind of ``Malthusian trap'' for the research ecosystem, this paper investigates the capabilities and limitations…