Track synthesis, materials and catalysis as it is published.
Search papers, labs, and topics across Lattice.
University of British Columbia ,, Vector Institute * Equal contribution ,, University of British Columbia
8
1
9
8
A new framework slashes LLM fact-checking costs for peer reviews by 75% while maintaining state-of-the-art accuracy.
Looped decision models achieve significant accuracy gains with increased depth on the same weights, outperforming dense models and matching latency-constrained cascades.
Optimal quantum circuit synthesis for a key classically simulable family is NP-complete on trees but polynomial on paths and complete graphs.
ModularRSI is proposed, a benchmark-disjoint, contrastive, and modular framework for generalizable harness evolution that contrasts successful and failed trajectories for the same task and aggregates evidence across tasks to identify recurring behavioral deficiencies.
Wrapping standard CLI coding agents in a state-persisting orchestration layer beats unconstrained autonomous agents at research completeness without altering the underlying model.
Self-improvement in LLMs is not automatic; the pathway to effective learning depends critically on the task structure and the nature of the feedback received.
Current video generation models struggle with visual reasoning, with the best achieving only 51% accuracy on a new benchmark designed to probe their capabilities.
Mid-training with function-aware fill-in-the-middle boosts coding agent performance while preventing capability erosion in non-agentic tasks.