Search papers, labs, and topics across Lattice.
Affiliation:
6
0
10
Non-CUDA hardware no longer requires costly post-training pipelines: conditioning memory rewards strictly on adopted code enables zero-shot LLM agents to synthesize NPU kernels that outperform vendor libraries by up to 44x.
Personalized AI agents can achieve up to 20.9% better task success by learning from user feedback in real-time, reshaping the landscape of human-AI collaboration.
Agents fall short in machine learning development, often locked in narrow loops while humans adapt and innovate across tasks.
KPR redefines software collaboration by transforming external contributions into auditable knowledge packages, minimizing the risks of merging unverified code.
Forget manual curation鈥攁ligning policy gradients with a validation set adaptively selects RL training data, leading to more stable LLM training and improved performance.
LiDAR semantic segmentation models can now generalize across drastically different viewpoints thanks to a novel geometric consistency approach that enforces prediction consistency across augmented views.
