Education
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
LLMs has become a critical research problem.
Efficient Discrepancy Testing for Learning with Distribution Shift Gautam Chandrasekaran UT Austin Adam R. Klivans UT Austin Vasilis Kontonis UT Austin Konstantinos Stavropoulos
Our approach generalizes and improves all prior work on TDS learning: (1) we obtain universal learners that succeed simultaneously for large classes of test distributions, (2) achieve near-optimal error rates, and (3) give exponential improvements for constant depth circuits.
Aligning LLM Agents by Learning Latent Preference from User Edits Ge Gao Alexey T aymanov Eduardo Salinas Paul Mineiro Dipendra Misra Department of Computer Science, Cornell University
The inferred user preference descriptions are used to define prompts for generating responses in the future.
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Building on this, our study investigates the interplay between sharpness and diversity within deep ensembles, illustrating their crucial role in robust generalization to both in-distribution (ID) and out-of-distribution (OOD) data.
Noether's Razor: Learning Conserved Quantities
Symmetries have proven useful in machine learning models, improving generalisation and overall performance.