Search papers, labs, and topics across Lattice.
7
0
11
41
Long-horizon agents achieve state-of-the-art performance by decoupling planning credit from execution guidance via structured subtask trees.
Mutation analysis as an adequacy metric for kernel-benchmark oracles is introduced: deterministic rules inject 10 compilable faults into verified CUDA implementations of 188 KernelBench problems, 7{,}384 of them with an independent kill witness; any test protocol is scored by the fraction it detects.
Forecasting future states from video prefixes reveals a significant gap in current models' retrieval capabilities, with LFTR leading the way in bridging this divide.
PowerAtlas achieves optimal electricity-computing scheduling, ensuring compliance with grid rules while maximizing efficiency in volatile AI workloads.
LLM agents struggle in dynamic environments, but EvoMem boosts their performance by capturing the evolution of memory, leading to better adaptability.
OpenMobile proves that high-performing mobile agents can be trained on entirely synthetic, open-source data, closing the gap with closed-source models and enabling broader research.
Uncertainty estimates from LLMs often fail when they're needed most – in low-information scenarios – but a simple post-hoc calibration can fix them.
