3 papers
cs.CL2025
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…
cs.CL2025
Poly-FEVER: A Multilingual Fact Verification Benchmark for Hallucination Detection in Large Language Models
Hanzhi Zhang, Sumera Anjum, Heng Fan +3
Hallucinations in generative AI, particularly in Large Language Models (LLMs), pose a significant challenge to the reliability of multilingual applications. Existing benchmarks for…
cs.CV2025
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…