7 papers
Beyond Refusal: A Same-Lineage Study of Aligned and Abliterated LLMs for Vulnerability Analysis
Mingchen Li, Meikang Qiu, Zifan Peng +4
Large language model (LLM)-assisted software security operates at a difficult boundary: the vulnerability-analysis terminology needed for legitimate code review, triage, and repair…
Towards Visual Query Segmentation in the Wild
Bing Fan, Minghao Li, Hanzhi Zhang +6
In this paper, we introduce visual query segmentation (VQS), a new paradigm of visual query localization (VQL) that aims to segment all pixel-level occurrences of an object of inte…
OLC-WA: Drift Aware Tuning-Free Online Classification with Weighted Average
Mohammad Abu Shaira, Yunhe Feng, Heng Fan +1
Real-world data sets often exhibit temporal dynamics characterized by evolving data distributions. Disregarding this phenomenon, commonly referred to as concept drift, can signific…
DP-GTR: Differentially Private Prompt Protection via Group Text Rewriting
Mingchen Li, Heng Fan, Song Fu +2
Prompt privacy is crucial, especially when using online large language models (LLMs), due to the sensitive information often contained within prompts. While LLMs can enhance prompt…
PRVQL: Progressive Knowledge-guided Refinement for Robust Egocentric Visual Query Localization
Bing Fan, Yunhe Feng, Yapeng Tian +4
Egocentric visual query localization (EgoVQL) focuses on localizing the target of interest in space and time from first-person videos, given a visual query. Despite recent progress…
DAM: Dynamic Attention Mask for Long-Context Large Language Model Inference Acceleration
Hanzhi Zhang, Heng Fan, Kewei Sha +2
Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention metho…