Search papers, labs, and topics across Lattice.
8
0
10
AutoSR not only recovers complex equations but also retains the entire scientific rationale behind them, revolutionizing how we approach symbolic regression.
Sparsification in attention mechanisms can drastically alter content influence, with higher compression ratios leading to surprising shifts in model output that standard accuracy metrics overlook.
Renormalization can redefine how we understand and address the sim-to-real gap in robotics by leveraging effective parameters that capture omitted dynamics.
A neural scorer fine-tuned on NASA's Earth Observation data outperforms traditional methods, while a zero-shot reranking stage boosts retrieval effectiveness by 28%.
A transparent probe-success rule boosts robot policy selection success rates by over 14 percentage points, revealing the hidden power of pre-deployment evaluations.
Agon reveals that machine-driven research can scale effectively while exposing critical failure modes that still require human oversight.
Multi-agent orchestration prompting is critically under-evaluated, with only 14.9% of models passing the new PerspectiveGap benchmark.
Forget hand-tuning PDE solvers – a new multi-agent framework designs, implements, debugs, and verifies them directly from natural language, outperforming neural and LLM baselines.
