Search papers, labs, and topics across Lattice.
7
0
7
0
UltraIR outperforms traditional machine-learning approaches in IR spectroscopy, achieving high accuracy with minimal labeled data across diverse chemical analysis tasks.
Achieving 93.02% accuracy in molecular structure recognition, MinerU.Chem outperforms existing systems, unlocking new possibilities for AI-driven chemistry research.
Benchmark gains in LLMs can be misleading, as they may reflect improved reachability rather than true capability expansion, with significant implications for performance evaluation.
SIVA-RL reveals that outcome-conditioned supervision can dramatically enhance multimodal reasoning performance, outperforming traditional methods across diverse benchmarks.
Tactical analysis in RTS games just got a major upgrade with SAT-RTS, which transforms chaotic state-action data into clear, interpretable insights.
MemNovo rebalances peptide and spectral contributions during decoding, leading to up to 39.1% improvement in peptide precision without additional computational costs.
Current AI agents struggle to reliably rediscover scientific knowledge, with top performers averaging only 21.5 out of a possible score, revealing critical gaps in their research capabilities.
