Search papers, labs, and topics across Lattice.
5
0
8
5
Training voice agents in an audio-native environment can more than double their task success rates and enhance efficiency without external dependencies.
The Qwen3-Omni model can reconstruct complex narratives from garbled audio inputs, revealing a hidden layer of reasoning that challenges our understanding of audio language processing.
Constraint-First Reasoning reveals that explicitly managing answer-space constraints can dramatically enhance the accuracy of mathematical problem-solving in language models.
Robots can now think (and act) much faster: ElegantVLA intelligently allocates compute within Vision-Language-Action models, leading to up to 3.77x speedups without sacrificing performance.
LLMs can achieve a "free lunch" in reasoning tasks, simultaneously improving accuracy and reducing token usage by simply training them to solve multiple problems in parallel.
