Search papers, labs, and topics across Lattice.
Affiliation:
9
0
10
Ockhamareto catches 49.9% of bugs with 2.60 tests on average, outperforming the best existing methods while using fewer resources.
Python remains the overwhelming choice for code generation in LLMs, but many selections are based on convenience rather than project needs, revealing critical flaws in model reasoning.
COMPAS boosts code generation performance by 15% while slashing costs by over 86%, revealing the critical interplay between task difficulty and optimization choices.
Agent Plans in open-source repositories reveal critical insights into how AI coding tools can be effectively guided through structured task-oriented artifacts.
Runtime diagnoses from multi-faceted bug reproduction tests can significantly boost patch generation effectiveness, leading to a 75.7% resolution rate on verified issues.
LLMs underperform traditional ML methods in software fairness tasks, challenging the assumption that they offer a silver bullet solution for bias mitigation.
Despite advances in VLMs, understanding software architecture diagrams remains surprisingly difficult, with even top models struggling to surpass 70% accuracy on a new benchmark designed to test diagram reasoning and visual grounding.
LLMs can learn reusable code optimization skills from slow/fast program pairs, enabling significant efficiency improvements without runtime feedback.
Even when LLMs translate code correctly, over 20% of the time it's surprisingly inefficient due to algorithmic flaws, poor language choices, or resource mismanagement.
