Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
9 papers published across 1 lab.
Uncovering crucial supporting lemmas for theorem proving by traversing multi-hop dependencies in a formal library's declaration graph.
Simultaneously evaluate $K$ policies in linear contextual bandits with near-optimal sample complexity by sharing information across evaluations via a unified ridge regression estimator.
Multimodal clustering can now adapt to arbitrary instructions, achieving near-perfect V-measures by directly embedding images, text, and instructions.
Most vision-language models fail to correctly bind attributes to objects in complex scenes, but finetuning on synthetic text alone can fix this without harming general performance.
Coding agents fix 40%+ more bugs when they're shown whole files verbatim, not compressed snippets or similar-but-unnecessary code.
Uncovering crucial supporting lemmas for theorem proving by traversing multi-hop dependencies in a formal library's declaration graph.
Simultaneously evaluate $K$ policies in linear contextual bandits with near-optimal sample complexity by sharing information across evaluations via a unified ridge regression estimator.
Multimodal clustering can now adapt to arbitrary instructions, achieving near-perfect V-measures by directly embedding images, text, and instructions.
Most vision-language models fail to correctly bind attributes to objects in complex scenes, but finetuning on synthetic text alone can fix this without harming general performance.
Coding agents fix 40%+ more bugs when they're shown whole files verbatim, not compressed snippets or similar-but-unnecessary code.
A single reward for multiple retrieval actions is a bottleneck; CASI unlocks precise within-set credit assignment, boosting agent performance by 3.51% in production.
Outperforming traditional model selection, a retrieval-based approach finds the best anomaly detector for unseen time series by leveraging similarity to past data, even in challenging OOD scenarios.
LLMs can be steered to generate diverse, relevant responses by explicitly searching for unoccupied semantic "gaps" in their output space, reducing output collision by over 10%.
Weak interactive feedback can dynamically steer LLMs to the correct similarity criterion for test-time decisions, unlocking significant performance gains beyond static mixtures.