Search papers, labs, and topics across Lattice.
5
0
8
27
Video LLMs can significantly improve their QA performance by integrating spatio-temporal evidence, bridging the gap between accuracy and visual perception.
LLM agents struggle in dynamic environments, but EvoMem boosts their performance by capturing the evolution of memory, leading to better adaptability.
VLAA-GUI's innovative framework allows autonomous agents to not only verify their success but also adaptively recover from failures, achieving human-level performance in GUI tasks.
Forget slow, end-to-end models: building real-time voice agents hinges on a cascaded streaming pipeline, as demonstrated by a new tutorial achieving sub-second latency.
A unified Vision-Language Model and Diffusion architecture unlocks surprisingly effective optical flow forecasting from noisy web data, enabling language-conditioned robot control and video generation.
