Search papers, labs, and topics across Lattice.
Inner Mongolia University
7
0
11
FineCombo-TTS achieves unprecedented precision in speech synthesis by seamlessly integrating text descriptions with reference speech, allowing for fine-grained control over acoustic attributes.
GF-DiT achieves up to 6.01× throughput improvement and 95% latency reduction by dynamically adapting GPU parallelism in response to workload demands.
Timeflies reveals that accurately forecasting time series requires not just predicting values, but also understanding whether observations will occur at all.
Achieve state-of-the-art forecasting by mapping heterogeneous time series data into a unified latent space, enabling nuanced interaction modeling.
Forget static emotion labels – EmoTransCap lets you generate speech captions that actually track how emotions evolve in a conversation.
Escaping the curse of dimensionality in multistage stochastic optimization is now possible: multilevel Monte Carlo methods can reduce scenario complexity from exponential to polynomial.
Turns out, robotic manipulation policies struggle with tasks requiring memory, and this benchmark reveals the architectural design choices that actually matter for improving performance.
