Search papers, labs, and topics across Lattice.
Affiliation:
4
0
7
2
Exploring the quotient space of equivalent GEM repairs unlocks a more efficient path to discovering distinct biological mechanisms, outperforming standard exploration under verifier-induced equivalence.
PertMind reveals that leveraging cellular perturbation data can significantly enhance LLMs' biological reasoning capabilities without extensive task-specific retraining.
Hard-assigned predictors in MoP-JEPA enable accurate planning in stochastic environments, achieving up to 42 times better performance than traditional methods.
Current LLM watermarks are surprisingly easy to spoof: a small 4B model, trained on just 100 examples using reinforcement learning, can fool them over 60% of the time.
