Search papers, labs, and topics across Lattice.
Southeast University
2
0
6
Achieving 134 FPS with under 50 ms latency, ViCoStream redefines the capabilities of VideoLLMs for real-time streaming applications.
Chain-of-thought prompting makes large language models smarter, but it also makes them less safe, a problem this paper tackles by forcing models to think about safety *before* reasoning.
