On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,695 papers · 148 categories

Trend · papers per month

count % of corpus

4 results for “classifier-guided”

Reduce, Reuse, Recycle: Compositional Generation with Energy-Based Diffusion Models and MCMCcs.LG

New samplers improve compositional generation with diffusion models.

problem Improving compositional generation with diffusion models.

method Score-based interpretation, energy-based parameterization, Metropolis-corrected samplers.

result New samplers enable successful compositional generation across various tasks.

diffusion models compositional generation MCMC classifier-guided text-to-image

2023-02-22abs ↗pdf ↗

Provably Reliable Classifier Guidance via Cross-Entropy Controlstat.ML

New method controls classifier guidance in diffusion models.

problem Improving classifier guidance in diffusion models.

method Cross-entropy control of classifier gradients.

result Effective guidance vectors with mean squared error

O(d \varepsilon )

classifier guidance diffusion models cross-entropy log-Sobolev inequality KL divergence

2026-01-29abs ↗pdf ↗

Elucidating The Design Space of Classifier-Guided Diffusion Generationcs.LG

New method uses off-the-shelf classifiers to improve diffusion generation without extra training.

problem Improving sample quality and controllability in conditional diffusion generation.

method Leveraging off-the-shelf classifiers in a training-free fashion with calibration and pre-conditioning techniques.

result Significant performance improvements (up to 20%) over existing guidance schemes.

classifier-guided diffusion training-free calibration pre-conditioning image generation

2023-10-17abs ↗pdf ↗

What Does It Take to Build a Performant Selective Classifier?cs.LG

New analysis reveals gaps in selective classifiers, guiding improvements.

problem Improving selective classifiers to match perfect-ordering oracle performance.

method Formalized selective classification gap, decomposed into five sources of looseness.

result Monotone post-hoc calibration has limited impact on closing the gap.

Selective classifiers Bayes noise approximation error ranking error statistical noise

2025-10-23abs ↗pdf ↗