4 citations · 7 across the 14 of their papers we have counts for
15 papers
Knowing When to Trust Images: Reliability-Aware Multi-modal Entity Alignment
Chenxiao Li, Yunhe Feng, Dongfang Liu +3
The visual modality, i.e., images, plays a key role in multi-modal entity alignment (MMEA). Existing approaches often directly fuse the image with other modalities to align differe…
LD-RSVIS: A Large-Scale and Diverse Benchmark for Referring Surgical Video Instrument Segmentation
Zan Wang, Yunhe Feng, Dong Nie +4
Referring surgical video instrument segmentation (RSVIS) aims at segmenting the instrument in a surgical video, given a textual description. Despite recent progress, current models…
TileMix: Tile-Centric Mixed-Precision Attention for LLM Inference Acceleration
Hanzhi Zhang, Qiao Zhang, Qinglei Cao +4
Long-context prefill in large language models (LLMs) incurs substantial computation and memory traffic because dense self-attention computes quadratic query-key scores. Existing me…
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…
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…
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…
Unlocking Cross-Lingual Sentiment Analysis through Emoji Interpretation: A Multimodal Generative AI Approach
Rafid Ishrak Jahan, Heng Fan, Haihua Chen +1
Emojis have become ubiquitous in online communication, serving as a universal medium to convey emotions and decorative elements. Their widespread use transcends language and cultur…
MNIST-Fraction: Enhancing Math Education with AI-Driven Fraction Detection and Analysis
Pegah Ahadian, Yunhe Feng, Karl Kosko +2
Mathematics education, a crucial and basic field, significantly influences students' learning in related subjects and their future careers. Utilizing artificial intelligence to int…
LoReTrack: Efficient and Accurate Low-Resolution Transformer Tracking
Shaohua Dong, Yunhe Feng, Qing Yang +2
High-performance Transformer trackers have shown excellent results, yet they often bear a heavy computational load. Observing that a smaller input can immediately and conveniently…
Benchmarking the Robustness of UAV Tracking Against Common Corruptions
Xiaoqiong Liu, Yunhe Feng, Shu Hu +2
The robustness of unmanned aerial vehicle (UAV) tracking is crucial in many tasks like surveillance and robotics. Despite its importance, little attention is paid to the performanc…
S3LLM: Large-Scale Scientific Software Understanding with LLMs using Source, Metadata, and Document
Kareem Shaik, Dali Wang, Weijian Zheng +4
The understanding of large-scale scientific software poses significant challenges due to its diverse codebase, extensive code length, and target computing architectures. The emerge…
Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning
Shaohua Dong, Yunhe Feng, Qing Yang +3
Multimodal (e.g., RGB-Depth/RGB-Thermal) fusion has shown great potential for improving semantic segmentation in complex scenes (e.g., indoor/low-light conditions). Existing approa…