Search papers, labs, and topics across Lattice.
8
0
11
6
ORCA not only boosts performance by 26.4 points but also restores critical speaker identity cues that traditional models overlook.
LatentASR transforms frozen ASR models into adaptive systems that intelligently allocate compute resources, achieving significant WER reductions on challenging inputs without the need for extensive retraining.
Leveraging lecture context can boost technical term recognition in Mandarin ASR systems by over 15% without sacrificing overall accuracy.
AI2 methods can now be transformed from bespoke protocols into reusable workflows, significantly enhancing the efficiency of molecular simulations in complex chemical systems.
Achieving superior accuracy in simulating complex 3D object dynamics without relying on rigid inductive biases could revolutionize physics-based modeling in AI.
AgentX can autonomously iterate on recommendation algorithms, outpacing human-driven processes and fundamentally changing how we approach system development.
LALMs struggle to ground their responses in audio, exhibiting surprising failures in temporal reasoning and music understanding that HalluAudio exposes.
Bridging the gap between audio reconstruction and language modeling objectives yields neural audio codecs that are both more acoustically faithful and linguistically predictable.
