collaborators
Showing cs.LGShow all

5 papers · 1 filter

cs.LG2026

MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI

Bohan Lyu, Yucheng Yang, Siqiao Huang +25

Modern AI progress has been driven by ML methods that are generalizable across settings and scalable to larger regimes. As large language models demonstrate advanced capabilities i…

cs.LG2026

Few-Step Boltzmann Generators via Scalable Likelihood Flow Maps

RuiKang OuYang, Hanlin Yu, Xinyue Ai +7

Recent progress in flow-based generative modeling has led to models that output high-quality samples while using only a small number of function evaluations. However, at present, t…

cs.LG2026

Double Preconditioning (DoPr): Optimization for Test-Time Performance, not Validation Loss

Thomas T. Zhang, Alok Shah, Yifei Zhang +3

Many modern applications of deep learning involve training a neural network via a one-step prediction loss (e.g., regression, cross-entropy), but deploy the network by rollin…

cs.LG2026

Diamond Maps: Efficient Reward Alignment via Stochastic Flow Maps

Peter Holderrieth, Douglas Chen, Luca Eyring +7

Flow and diffusion models produce high-quality samples, but adapting them to user preferences or constraints post-training remains costly and brittle, a challenge commonly called r…

cs.LG2026

Joint Distillation for Fast Likelihood Evaluation and Sampling in Flow-based Models

Xinyue Ai, Yutong He, Albert Gu +4

Log-likelihood evaluation enables important capabilities in generative models, including model comparison, certain fine-tuning objectives, and many downstream applications. Yet par…