Search papers, labs, and topics across Lattice.
7
0
9
16
Voice Memory cuts speech recognition error rates by over 10% in noisy environments while ensuring the learned model remains auditable and portable.
ASR models can exhibit drastically different performance depending on user preferences, revealing hidden quality disparities in traditional benchmarks.
SHERLOC boosts code repair agents' effectiveness by improving fault localization accuracy while slashing token usage by over 23%.
Open-SWE-Traces reveals that a hybrid approach to trajectory data can significantly boost the reasoning capabilities of software engineering agents.
Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.
Multimodal models can now achieve state-of-the-art performance in real-world tasks like document understanding and audio-video comprehension with significantly reduced inference latency thanks to novel token-reduction techniques.
Bridging the offline-streaming gap in ASR is now more achievable: a single RNN-Transducer model can deliver high accuracy in both settings, thanks to a novel consistency regularization technique.
