Search papers, labs, and topics across Lattice.
6
0
11
2
Skill Optimizers trained through execution feedback can outperform traditional models by over 9 points, revealing a critical gap in agent learning methodologies.
LEGO-RL boosts coding agent performance by up to 8.4% while ensuring robust training signals and execution reliability.
Context interference can significantly degrade the performance of search agents, but a novel context refiner shows how to enhance their reliability and efficiency dramatically.
ReviewDSE achieves a 1.78% reduction in wirelength while exposing and repairing design flaws that traditional methods miss.
Masking just 5% of attention heads in vision-language models tanks performance on long-context tasks, revealing a surprisingly sparse and critical set of "multimodal retrieval heads" that attend to both text and images.
Low-resource language models can get a major boost in translation quality and tokenization efficiency by using reinforcement learning to directly enforce structural constraints like sequence length and linguistic well-formedness during training.
