Search papers, labs, and topics across Lattice.
3
0
6
Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.
Video LLMs can get a free performance boost by using ST-GridPool, a novel technique that enhances visual token representations without any additional training.
Instead of just pruning redundant tokens, ST-SimDiff dramatically cuts MLLM video processing costs by intelligently preserving tokens representing *changes* in the video.
