Search papers, labs, and topics across Lattice.
Affiliation:
4
0
5
4
State-corruption attacks can be drastically reduced from 84.7% to just 2.3% with PIPES, while still preserving agent performance.
Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.
Nemotron 3 Super proves you can achieve comparable accuracy to existing 120B models, but with significantly higher inference throughput, by combining Mamba, Attention, and Mixture-of-Experts.
Current benchmarks mislead on the security of AI agents against indirect prompt injection; robust defenses require dynamic replanning, constrained LLM-based security checks, and human interaction.
