Search papers, labs, and topics across Lattice.
4
0
8
Current GUI agents are reactive, but PIRA-Bench offers a challenging new environment for training agents to *proactively* anticipate user intentions from continuous visual inputs, a crucial step towards truly intelligent AI assistants.
Ditch matplotlib for blazing-fast, GPU-powered dimensionality reduction and visualization on your Mac with mlx-vis.
MLLM training gets a 1.36x speed boost with Dynamic Hybrid Parallelism (DHP), which adaptively optimizes parallelism strategies to handle the data heterogeneity that plagues multimodal datasets.
Task-targeted distillation beats standard contrastive learning for training small, high-performance text embedding models.
