Guangxuan Xiao (@Guangxuan_Xiao)
2025-10-14 | โค๏ธ 1122 | ๐ 161
Excited to share our new work: StreamingVLM! ๐
We tackle a major challenge for Vision-Language Models (VLMs): understanding infinite video streams in real-time without latency blowing up or running out of memory.
Paper: https://arxiv.org/abs/2510.09608 Code: https://github.com/mit-han-lab/streaming-vlm https://x.com/Guangxuan_Xiao/status/1977913044790333714/video/1
๐ Related
Auto-generated bookmark