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.CV2024
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…