3 papers
cs.CV2026
VastMAT: A Large-Scale Multi-Category Benchmark for Multi-Animal Tracking
Zhizhen Li, Zan Wang, Huidong Peng +4
Multi-animal tracking (MAT) supports the study of animal movement, behavior, and group interactions. However, general multi-object tracking (MOT) benchmarks primarily focus on pede…
cs.AI2026
LISA: Linear-Indexed Sparse Attention for Efficient Long-Context Reasoning
Yu Zhao, Zekun Zhang, Fan Jiang +9
Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost…
cs.CL2024
PGA-SciRE: Harnessing LLM on Data Augmentation for Enhancing Scientific Relation Extraction
Yang Zhou, Shimin Shan, Hongkui Wei +2
Relation Extraction (RE) aims at recognizing the relation between pairs of entities mentioned in a text. Advances in LLMs have had a tremendous impact on NLP. In this work, we prop…