Search papers, labs, and topics across Lattice.
4
0
9
MemoryVLA++ achieves up to 28% performance gains in robotic manipulation tasks by integrating memory and imagination, transforming how robots handle temporal dependencies.
Low Word Error Rate can be a mirage: compressing speech to "pure" semantic tokens, even with near-perfect WER, produces unintelligible speech when used for generation.
Current mobile GUI agents are surprisingly inept at everyday smartphone tasks, achieving only 62% success on a new benchmark of real-world Android apps.
Forget specialized architectures: StepAudio 2.5 proves a single audio-language foundation, shaped by RLHF, can dominate ASR, TTS, and real-time dialogue simultaneously.
