2 papers
cs.CL2025
Unshackling Context Length: An Efficient Selective Attention Approach through Query-Key Compression
Haoyu Wang, Tong Teng, Tianyu Guo +4
Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either e…
cs.CV2024
Cross-video Identity Correlating for Person Re-identification Pre-training
Jialong Zuo, Ying Nie, Hanyu Zhou +5
Recent researches have proven that pre-training on large-scale person images extracted from internet videos is an effective way in learning better representations for person re-ide…